{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FMCLJKJV3UD5A5PV2P6PCK5NFZ","short_pith_number":"pith:FMCLJKJV","schema_version":"1.0","canonical_sha256":"2b04b4a935dd07d075f5d3fcf12bad2e69e09027cbfaf745d1a5524012384cf3","source":{"kind":"arxiv","id":"2406.12235","version":2},"attestation_state":"computed","paper":{"title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Chuchu Han, Huaxin Zhang, Jialong Zuo, Nong Sang, Xiang Wang, Xiaohao Xu, Xiaonan Huang, Yuehuan Wang","submitted_at":"2024-06-18T03:19:24Z","abstract_excerpt":"Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi"},"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":"2406.12235","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T03:19:24Z","cross_cats_sorted":[],"title_canon_sha256":"988e93dbb11ef684201b7cbcd93c89e271f1b71615901f0280cfed8ec3afd610","abstract_canon_sha256":"0ef194bb2f4ecd3dcdddf57fce257cc38514987de442550e01b4e635b9e0cda7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:11.349334Z","signature_b64":"q6OFa/Cc7I4i7bNFKn6uHM4APMLQIl8tmCUvaox/00nyvoNR6twf6gHHBthQGSU9y+WgLM/L1khiyr63H6CeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b04b4a935dd07d075f5d3fcf12bad2e69e09027cbfaf745d1a5524012384cf3","last_reissued_at":"2026-07-05T08:38:11.348797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:11.348797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Chuchu Han, Huaxin Zhang, Jialong Zuo, Nong Sang, Xiang Wang, Xiaohao Xu, Xiaonan Huang, Yuehuan Wang","submitted_at":"2024-06-18T03:19:24Z","abstract_excerpt":"Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12235","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/2406.12235/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":"2406.12235","created_at":"2026-07-05T08:38:11.348867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12235v2","created_at":"2026-07-05T08:38:11.348867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12235","created_at":"2026-07-05T08:38:11.348867+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMCLJKJV3UD5","created_at":"2026-07-05T08:38:11.348867+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMCLJKJV3UD5A5PV","created_at":"2026-07-05T08:38:11.348867+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMCLJKJV","created_at":"2026-07-05T08:38:11.348867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15054","citing_title":"LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31196","citing_title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14360","citing_title":"Digital Guardians: The Past and The Future of Cyber-Physical Resilience","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07818","citing_title":"Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ","json":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ.json","graph_json":"https://pith.science/api/pith-number/FMCLJKJV3UD5A5PV2P6PCK5NFZ/graph.json","events_json":"https://pith.science/api/pith-number/FMCLJKJV3UD5A5PV2P6PCK5NFZ/events.json","paper":"https://pith.science/paper/FMCLJKJV"},"agent_actions":{"view_html":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ","download_json":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ.json","view_paper":"https://pith.science/paper/FMCLJKJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12235&json=true","fetch_graph":"https://pith.science/api/pith-number/FMCLJKJV3UD5A5PV2P6PCK5NFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FMCLJKJV3UD5A5PV2P6PCK5NFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ/action/storage_attestation","attest_author":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ/action/author_attestation","sign_citation":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ/action/citation_signature","submit_replication":"https://pith.science/pith/FMCLJKJV3UD5A5PV2P6PCK5NFZ/action/replication_record"}},"created_at":"2026-07-05T08:38:11.348867+00:00","updated_at":"2026-07-05T08:38:11.348867+00:00"}