{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UFOUKWYKOELDZXD5J6BVFZ5FBE","short_pith_number":"pith:UFOUKWYK","schema_version":"1.0","canonical_sha256":"a15d455b0a71163cdc7d4f8352e7a5090ab61cd295b042dd5f3692eaaf7e1294","source":{"kind":"arxiv","id":"2412.06171","version":2},"attestation_state":"computed","paper":{"title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Huaxin Zhang, Jialong Zuo, Li Yu, Nong Sang, Shanjun Zhang, Xiang Wang, Xiaohao Xu, Xiaonan Huang","submitted_at":"2024-12-09T03:05:34Z","abstract_excerpt":"How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-autom"},"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":"2412.06171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T03:05:34Z","cross_cats_sorted":[],"title_canon_sha256":"ec5295dd9c4a1eb77d2c9fa929231f85eea93a032af8769e24be26f8c5a860df","abstract_canon_sha256":"a0513087e680e6057c71b8b2a8721e93507a4f5dbe0b245653b4af03f48e459e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:59.227689Z","signature_b64":"Ak9gUoXqYVClYv4+1tRe8lctjFEw9Bgdl8RIczLTmvQZlFuyZCF52/P56ge3YnLoL7fGlKqcTY9TJmo557yXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a15d455b0a71163cdc7d4f8352e7a5090ab61cd295b042dd5f3692eaaf7e1294","last_reissued_at":"2026-07-05T10:30:59.226745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:59.226745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Huaxin Zhang, Jialong Zuo, Li Yu, Nong Sang, Shanjun Zhang, Xiang Wang, Xiaohao Xu, Xiaonan Huang","submitted_at":"2024-12-09T03:05:34Z","abstract_excerpt":"How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-autom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06171","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/2412.06171/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":"2412.06171","created_at":"2026-07-05T10:30:59.226870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06171v2","created_at":"2026-07-05T10:30:59.226870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06171","created_at":"2026-07-05T10:30:59.226870+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFOUKWYKOELD","created_at":"2026-07-05T10:30:59.226870+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFOUKWYKOELDZXD5","created_at":"2026-07-05T10:30:59.226870+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFOUKWYK","created_at":"2026-07-05T10:30:59.226870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23504","citing_title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE","json":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE.json","graph_json":"https://pith.science/api/pith-number/UFOUKWYKOELDZXD5J6BVFZ5FBE/graph.json","events_json":"https://pith.science/api/pith-number/UFOUKWYKOELDZXD5J6BVFZ5FBE/events.json","paper":"https://pith.science/paper/UFOUKWYK"},"agent_actions":{"view_html":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE","download_json":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE.json","view_paper":"https://pith.science/paper/UFOUKWYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06171&json=true","fetch_graph":"https://pith.science/api/pith-number/UFOUKWYKOELDZXD5J6BVFZ5FBE/graph.json","fetch_events":"https://pith.science/api/pith-number/UFOUKWYKOELDZXD5J6BVFZ5FBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE/action/storage_attestation","attest_author":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE/action/author_attestation","sign_citation":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE/action/citation_signature","submit_replication":"https://pith.science/pith/UFOUKWYKOELDZXD5J6BVFZ5FBE/action/replication_record"}},"created_at":"2026-07-05T10:30:59.226870+00:00","updated_at":"2026-07-05T10:30:59.226870+00:00"}