{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5MRVNOSO4TAHZ2AWXUSNYKQEE","short_pith_number":"pith:T5MRVNOS","schema_version":"1.0","canonical_sha256":"9f591ab5d2772603e740b5e926e150213d6c395c7ef8f63c70de8fcdc9cf3302","source":{"kind":"arxiv","id":"2401.03040","version":1},"attestation_state":"computed","paper":{"title":"AccidentGPT: Large Multi-Modal Foundation Model for Traffic Accident Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Kebin Wu, Wenbin Li, Xiaofei Xiao","submitted_at":"2024-01-05T19:33:21Z","abstract_excerpt":"Traffic accident analysis is pivotal for enhancing public safety and developing road regulations. Traditional approaches, although widely used, are often constrained by manual analysis processes, subjective decisions, uni-modal outputs, as well as privacy issues related to sensitive data. This paper introduces the idea of AccidentGPT, a foundation model of traffic accident analysis, which incorporates multi-modal input data to automatically reconstruct the accident process video with dynamics details, and furthermore provide multi-task analysis with multi-modal outputs. The design of the Accid"},"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":"2401.03040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-05T19:33:21Z","cross_cats_sorted":["cs.AI","cs.CV","cs.DC"],"title_canon_sha256":"fb8ebf62941c5af2a12a50a12e65c3195237344a42f6d88691ee3381fb2aebb8","abstract_canon_sha256":"45453a0148b8e629dc668b678b1df5143a17fb3156200223e7580e0acf267dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:01.464268Z","signature_b64":"XP/1bhcIBwdjVxWSQMzk0fJ8k9a5GVjfirXVOKHeQ5UcmT0qmez1HBxlR/9xw3EGuj8S3eAEydlQuor1KvsfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f591ab5d2772603e740b5e926e150213d6c395c7ef8f63c70de8fcdc9cf3302","last_reissued_at":"2026-07-05T07:31:01.463855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:01.463855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AccidentGPT: Large Multi-Modal Foundation Model for Traffic Accident Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Kebin Wu, Wenbin Li, Xiaofei Xiao","submitted_at":"2024-01-05T19:33:21Z","abstract_excerpt":"Traffic accident analysis is pivotal for enhancing public safety and developing road regulations. Traditional approaches, although widely used, are often constrained by manual analysis processes, subjective decisions, uni-modal outputs, as well as privacy issues related to sensitive data. This paper introduces the idea of AccidentGPT, a foundation model of traffic accident analysis, which incorporates multi-modal input data to automatically reconstruct the accident process video with dynamics details, and furthermore provide multi-task analysis with multi-modal outputs. The design of the Accid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03040","kind":"arxiv","version":1},"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/2401.03040/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":"2401.03040","created_at":"2026-07-05T07:31:01.463914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03040v1","created_at":"2026-07-05T07:31:01.463914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03040","created_at":"2026-07-05T07:31:01.463914+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5MRVNOSO4TA","created_at":"2026-07-05T07:31:01.463914+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5MRVNOSO4TAHZ2A","created_at":"2026-07-05T07:31:01.463914+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5MRVNOS","created_at":"2026-07-05T07:31:01.463914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01737","citing_title":"TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10959","citing_title":"Ozone: A Unified Platform for Transportation Research","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10959","citing_title":"Ozone: A Unified Platform for Transportation Research","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE","json":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE.json","graph_json":"https://pith.science/api/pith-number/T5MRVNOSO4TAHZ2AWXUSNYKQEE/graph.json","events_json":"https://pith.science/api/pith-number/T5MRVNOSO4TAHZ2AWXUSNYKQEE/events.json","paper":"https://pith.science/paper/T5MRVNOS"},"agent_actions":{"view_html":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE","download_json":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE.json","view_paper":"https://pith.science/paper/T5MRVNOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/T5MRVNOSO4TAHZ2AWXUSNYKQEE/graph.json","fetch_events":"https://pith.science/api/pith-number/T5MRVNOSO4TAHZ2AWXUSNYKQEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE/action/storage_attestation","attest_author":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE/action/author_attestation","sign_citation":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE/action/citation_signature","submit_replication":"https://pith.science/pith/T5MRVNOSO4TAHZ2AWXUSNYKQEE/action/replication_record"}},"created_at":"2026-07-05T07:31:01.463914+00:00","updated_at":"2026-07-05T07:31:01.463914+00:00"}