{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U46RNKL2BFRV3GMFTK3E7RU3CY","short_pith_number":"pith:U46RNKL2","schema_version":"1.0","canonical_sha256":"a73d16a97a09635d99859ab64fc69b162fd884cc82510eaf39d929c533caf8cd","source":{"kind":"arxiv","id":"2405.16886","version":1},"attestation_state":"computed","paper":{"title":"Hawk: Learning to Understand Open-World Video Anomalies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Guo, Cheng Fang, Hao Lu, Jiangbo Lu, Jiaqi Tang, Ke Ma, Qifeng Chen, Ruizheng Wu, Xiaogang Xu, Ying-Cong Chen","submitted_at":"2024-05-27T07:08:58Z","abstract_excerpt":"Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (VLM) to interpret video anomalies precisely. Recognizing the difference in motion information b"},"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":"2405.16886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T07:08:58Z","cross_cats_sorted":[],"title_canon_sha256":"12d9811dc77d4fde8ce28097fb0fd400eaa1f2330d95d0f1669a9c73bd6a0286","abstract_canon_sha256":"bf46ac19f5f965428babbe61871cd6368dd00680a86b7d7d35ccc0ec72698437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:36.918117Z","signature_b64":"ErUA3aaKEdBz6nMUpsQjOpYCx6xm46r2CN8WZbWu8tLOhVM0udtHB5LihzryRTiND2jgGdLqJXoPhgG+5ZeeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a73d16a97a09635d99859ab64fc69b162fd884cc82510eaf39d929c533caf8cd","last_reissued_at":"2026-07-05T08:23:36.917588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:36.917588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hawk: Learning to Understand Open-World Video Anomalies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Guo, Cheng Fang, Hao Lu, Jiangbo Lu, Jiaqi Tang, Ke Ma, Qifeng Chen, Ruizheng Wu, Xiaogang Xu, Ying-Cong Chen","submitted_at":"2024-05-27T07:08:58Z","abstract_excerpt":"Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (VLM) to interpret video anomalies precisely. Recognizing the difference in motion information b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16886","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/2405.16886/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":"2405.16886","created_at":"2026-07-05T08:23:36.917664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16886v1","created_at":"2026-07-05T08:23:36.917664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16886","created_at":"2026-07-05T08:23:36.917664+00:00"},{"alias_kind":"pith_short_12","alias_value":"U46RNKL2BFRV","created_at":"2026-07-05T08:23:36.917664+00:00"},{"alias_kind":"pith_short_16","alias_value":"U46RNKL2BFRV3GMF","created_at":"2026-07-05T08:23:36.917664+00:00"},{"alias_kind":"pith_short_8","alias_value":"U46RNKL2","created_at":"2026-07-05T08:23:36.917664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06171","citing_title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY","json":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY.json","graph_json":"https://pith.science/api/pith-number/U46RNKL2BFRV3GMFTK3E7RU3CY/graph.json","events_json":"https://pith.science/api/pith-number/U46RNKL2BFRV3GMFTK3E7RU3CY/events.json","paper":"https://pith.science/paper/U46RNKL2"},"agent_actions":{"view_html":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY","download_json":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY.json","view_paper":"https://pith.science/paper/U46RNKL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16886&json=true","fetch_graph":"https://pith.science/api/pith-number/U46RNKL2BFRV3GMFTK3E7RU3CY/graph.json","fetch_events":"https://pith.science/api/pith-number/U46RNKL2BFRV3GMFTK3E7RU3CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY/action/storage_attestation","attest_author":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY/action/author_attestation","sign_citation":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY/action/citation_signature","submit_replication":"https://pith.science/pith/U46RNKL2BFRV3GMFTK3E7RU3CY/action/replication_record"}},"created_at":"2026-07-05T08:23:36.917664+00:00","updated_at":"2026-07-05T08:23:36.917664+00:00"}