{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F2UPIKMO5LIVAK4UNH7OBG55Q3","short_pith_number":"pith:F2UPIKMO","schema_version":"1.0","canonical_sha256":"2ea8f4298eead1502b9469fee09bbd86c162bb196744adc6aeebb32a2f4aae51","source":{"kind":"arxiv","id":"2410.00982","version":2},"attestation_state":"computed","paper":{"title":"ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyu Jiang, Feng Guo, Liang Shi, Tong Zeng","submitted_at":"2024-10-01T18:10:23Z","abstract_excerpt":"Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare events, most general vision-language models (VLMs) have not been trained sufficiently to link SCE videos and narratives, which could lead to hallucinations and missing key safety characteristics. Here, we introduce ScVLM, a novel hybrid methodology that integrates supervised and contrastive learning techniques to classify the severity and t"},"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":"2410.00982","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T18:10:23Z","cross_cats_sorted":[],"title_canon_sha256":"ea15581650ebef087b3b1f0cc4cf70e6ccdc56b6dfaa6eaad221f48f9ac28ab4","abstract_canon_sha256":"33457bd9893a405ec3f37761364ca4c5fd90d21ba1f8ca227768667394c7264a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:15.925421Z","signature_b64":"V2InG81Izp9HmaeYkcV4R+1P9NcFm7iqKUlJ+f4SH2HXL5f7uYgRHGR/zsC4wVp0S02zhhVg9dEsd5kUPQJXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea8f4298eead1502b9469fee09bbd86c162bb196744adc6aeebb32a2f4aae51","last_reissued_at":"2026-07-05T10:27:15.924775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:15.924775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyu Jiang, Feng Guo, Liang Shi, Tong Zeng","submitted_at":"2024-10-01T18:10:23Z","abstract_excerpt":"Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare events, most general vision-language models (VLMs) have not been trained sufficiently to link SCE videos and narratives, which could lead to hallucinations and missing key safety characteristics. Here, we introduce ScVLM, a novel hybrid methodology that integrates supervised and contrastive learning techniques to classify the severity and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00982","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/2410.00982/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":"2410.00982","created_at":"2026-07-05T10:27:15.924843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00982v2","created_at":"2026-07-05T10:27:15.924843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00982","created_at":"2026-07-05T10:27:15.924843+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2UPIKMO5LIV","created_at":"2026-07-05T10:27:15.924843+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2UPIKMO5LIVAK4U","created_at":"2026-07-05T10:27:15.924843+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2UPIKMO","created_at":"2026-07-05T10:27:15.924843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02074","citing_title":"Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3","json":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3.json","graph_json":"https://pith.science/api/pith-number/F2UPIKMO5LIVAK4UNH7OBG55Q3/graph.json","events_json":"https://pith.science/api/pith-number/F2UPIKMO5LIVAK4UNH7OBG55Q3/events.json","paper":"https://pith.science/paper/F2UPIKMO"},"agent_actions":{"view_html":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3","download_json":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3.json","view_paper":"https://pith.science/paper/F2UPIKMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00982&json=true","fetch_graph":"https://pith.science/api/pith-number/F2UPIKMO5LIVAK4UNH7OBG55Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/F2UPIKMO5LIVAK4UNH7OBG55Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3/action/storage_attestation","attest_author":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3/action/author_attestation","sign_citation":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3/action/citation_signature","submit_replication":"https://pith.science/pith/F2UPIKMO5LIVAK4UNH7OBG55Q3/action/replication_record"}},"created_at":"2026-07-05T10:27:15.924843+00:00","updated_at":"2026-07-05T10:27:15.924843+00:00"}