{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RW7P2UEQPAF2YFPFDDULKX5BTE","short_pith_number":"pith:RW7P2UEQ","schema_version":"1.0","canonical_sha256":"8dbefd5090780bac15e518e8b55fa1992f8c1ceef0a8526ac2c67ede5b476d97","source":{"kind":"arxiv","id":"2406.13894","version":1},"attestation_state":"computed","paper":{"title":"Using Multimodal Large Language Models for Automated Detection of Traffic Safety Critical Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Huthaifa I. Ashqar, Mohammad Abu Tami, Mohammed Elhenawy","submitted_at":"2024-06-19T23:50:41Z","abstract_excerpt":"Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs) offers a novel approach by integrating textual, visual, and audio modalities, thereby providing automated analyses of driving videos. Our framework leverages the reasoning power of MLLMs, directing their output through context-specific prompts to ensure accurate, reliable, and actionable insights for hazard detection. By incorporating models like Gemini-Pro-V"},"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":"2406.13894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T23:50:41Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"0600e77a0cfbc47bc01a94be7f4d4f1e5d0927ca5d93657b0cc137a8f1e25310","abstract_canon_sha256":"e899a73a3cc5170bcf53359cbe393bcc4f8ff05e05419145b0f1e2a079760a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:36.079058Z","signature_b64":"dkizo76Vj9QNnmqK1fav5v96l7LyjcVGhJiDp1MLjDxQfzczRLEVN5gclSYit7go8a0XDUq64RIp0vC6JNWdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dbefd5090780bac15e518e8b55fa1992f8c1ceef0a8526ac2c67ede5b476d97","last_reissued_at":"2026-07-05T08:34:36.078574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:36.078574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Multimodal Large Language Models for Automated Detection of Traffic Safety Critical Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Huthaifa I. Ashqar, Mohammad Abu Tami, Mohammed Elhenawy","submitted_at":"2024-06-19T23:50:41Z","abstract_excerpt":"Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs) offers a novel approach by integrating textual, visual, and audio modalities, thereby providing automated analyses of driving videos. Our framework leverages the reasoning power of MLLMs, directing their output through context-specific prompts to ensure accurate, reliable, and actionable insights for hazard detection. By incorporating models like Gemini-Pro-V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13894","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/2406.13894/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":"2406.13894","created_at":"2026-07-05T08:34:36.078631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13894v1","created_at":"2026-07-05T08:34:36.078631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13894","created_at":"2026-07-05T08:34:36.078631+00:00"},{"alias_kind":"pith_short_12","alias_value":"RW7P2UEQPAF2","created_at":"2026-07-05T08:34:36.078631+00:00"},{"alias_kind":"pith_short_16","alias_value":"RW7P2UEQPAF2YFPF","created_at":"2026-07-05T08:34:36.078631+00:00"},{"alias_kind":"pith_short_8","alias_value":"RW7P2UEQ","created_at":"2026-07-05T08:34:36.078631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17590","citing_title":"DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE","json":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE.json","graph_json":"https://pith.science/api/pith-number/RW7P2UEQPAF2YFPFDDULKX5BTE/graph.json","events_json":"https://pith.science/api/pith-number/RW7P2UEQPAF2YFPFDDULKX5BTE/events.json","paper":"https://pith.science/paper/RW7P2UEQ"},"agent_actions":{"view_html":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE","download_json":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE.json","view_paper":"https://pith.science/paper/RW7P2UEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13894&json=true","fetch_graph":"https://pith.science/api/pith-number/RW7P2UEQPAF2YFPFDDULKX5BTE/graph.json","fetch_events":"https://pith.science/api/pith-number/RW7P2UEQPAF2YFPFDDULKX5BTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE/action/storage_attestation","attest_author":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE/action/author_attestation","sign_citation":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE/action/citation_signature","submit_replication":"https://pith.science/pith/RW7P2UEQPAF2YFPFDDULKX5BTE/action/replication_record"}},"created_at":"2026-07-05T08:34:36.078631+00:00","updated_at":"2026-07-05T08:34:36.078631+00:00"}