{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4ICHZXGRIWGZIJQ4L6QIO6U73S","short_pith_number":"pith:4ICHZXGR","schema_version":"1.0","canonical_sha256":"e2047cdcd1458d94261c5fa0877a9fdc94ad9cadcbe42acabcec39993181b52d","source":{"kind":"arxiv","id":"2206.08783","version":2},"attestation_state":"computed","paper":{"title":"A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Balint Gyevnar, Cheng Wang, Christopher G. Lucas, Massimiliano Tamborski, Shay B. Cohen, Stefano V. Albrecht","submitted_at":"2022-06-17T13:53:18Z","abstract_excerpt":"Inscrutable AI systems are difficult to trust, especially if they operate in safety-critical settings like autonomous driving. Therefore, there is a need to build transparent and queryable systems to increase trust levels. We propose a transparent, human-centric explanation generation method for autonomous vehicle motion planning and prediction based on an existing white-box system called IGP2. Our method integrates Bayesian networks with context-free generative rules and can give causal natural language explanations for the high-level driving behaviour of autonomous vehicles. Preliminary test"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.08783","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-06-17T13:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"8d565cc157d8c9bcc9b212469ebb093004d69a38f90b6fa7973f955ce2469ddd","abstract_canon_sha256":"ea93ee4a494d82b081b1dd6e604437cb489e6ca99f135b7c827a57448a0b8cef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:54.730233Z","signature_b64":"FVu3kMgooh4OQmwUjW+A8h4uxP2nzFEYaEz4G3NVXbsYQEqnIgboGn6CPQDpNEyfdR5pGoKZvPQ7mrMFiiB4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2047cdcd1458d94261c5fa0877a9fdc94ad9cadcbe42acabcec39993181b52d","last_reissued_at":"2026-07-05T04:34:54.729768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:54.729768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Balint Gyevnar, Cheng Wang, Christopher G. Lucas, Massimiliano Tamborski, Shay B. Cohen, Stefano V. Albrecht","submitted_at":"2022-06-17T13:53:18Z","abstract_excerpt":"Inscrutable AI systems are difficult to trust, especially if they operate in safety-critical settings like autonomous driving. Therefore, there is a need to build transparent and queryable systems to increase trust levels. We propose a transparent, human-centric explanation generation method for autonomous vehicle motion planning and prediction based on an existing white-box system called IGP2. Our method integrates Bayesian networks with context-free generative rules and can give causal natural language explanations for the high-level driving behaviour of autonomous vehicles. Preliminary test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08783","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.08783/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.08783","created_at":"2026-07-05T04:34:54.729824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08783v2","created_at":"2026-07-05T04:34:54.729824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08783","created_at":"2026-07-05T04:34:54.729824+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ICHZXGRIWGZ","created_at":"2026-07-05T04:34:54.729824+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ICHZXGRIWGZIJQ4","created_at":"2026-07-05T04:34:54.729824+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ICHZXGR","created_at":"2026-07-05T04:34:54.729824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04299","citing_title":"Beyond Fixed Thresholds and Domain-Specific Benchmarks for Explainable Multi-Task Classification in Autonomous Vehicles","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S","json":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S.json","graph_json":"https://pith.science/api/pith-number/4ICHZXGRIWGZIJQ4L6QIO6U73S/graph.json","events_json":"https://pith.science/api/pith-number/4ICHZXGRIWGZIJQ4L6QIO6U73S/events.json","paper":"https://pith.science/paper/4ICHZXGR"},"agent_actions":{"view_html":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S","download_json":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S.json","view_paper":"https://pith.science/paper/4ICHZXGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08783&json=true","fetch_graph":"https://pith.science/api/pith-number/4ICHZXGRIWGZIJQ4L6QIO6U73S/graph.json","fetch_events":"https://pith.science/api/pith-number/4ICHZXGRIWGZIJQ4L6QIO6U73S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S/action/storage_attestation","attest_author":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S/action/author_attestation","sign_citation":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S/action/citation_signature","submit_replication":"https://pith.science/pith/4ICHZXGRIWGZIJQ4L6QIO6U73S/action/replication_record"}},"created_at":"2026-07-05T04:34:54.729824+00:00","updated_at":"2026-07-05T04:34:54.729824+00:00"}