{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ELEWJVUGACQVVSPKAF25PCMZR3","short_pith_number":"pith:ELEWJVUG","schema_version":"1.0","canonical_sha256":"22c964d68600a15ac9ea0175d789998ed0415966b2f71483a82f42fec33bd66b","source":{"kind":"arxiv","id":"2505.23504","version":1},"attestation_state":"computed","paper":{"title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyun Zhu, Qixiang Chen, Xiaodong Cun, Xi Shen","submitted_at":"2025-05-29T14:48:10Z","abstract_excerpt":"Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity. Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events. This limitation is further compounded by the absence of comprehensive benchmarks for evaluating reasoning ability in anomaly scenarios. To address both challenges, we introduce "},"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":"2505.23504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"9305be738dd34128d57c1d9e5113ac9f660f2752d7d1be479c29478686efe91d","abstract_canon_sha256":"e05dfb29e79a85a2388a9a0e8ba302858c5359b54813c563c39a3c5cc70697ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:03.151205Z","signature_b64":"L6fgsx+Z9xXRbhI6gAGjKLLjoo7vZC3cDifktfiJgeVApZvwmUoG9jZE8+QfowvYvhEoFV3iC8l+dAUSDgEcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22c964d68600a15ac9ea0175d789998ed0415966b2f71483a82f42fec33bd66b","last_reissued_at":"2026-07-05T11:12:03.150724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:03.150724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyun Zhu, Qixiang Chen, Xiaodong Cun, Xi Shen","submitted_at":"2025-05-29T14:48:10Z","abstract_excerpt":"Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity. Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events. This limitation is further compounded by the absence of comprehensive benchmarks for evaluating reasoning ability in anomaly scenarios. To address both challenges, we introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23504","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/2505.23504/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":"2505.23504","created_at":"2026-07-05T11:12:03.150777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23504v1","created_at":"2026-07-05T11:12:03.150777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23504","created_at":"2026-07-05T11:12:03.150777+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELEWJVUGACQV","created_at":"2026-07-05T11:12:03.150777+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELEWJVUGACQVVSPK","created_at":"2026-07-05T11:12:03.150777+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELEWJVUG","created_at":"2026-07-05T11:12:03.150777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00622","citing_title":"Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07772","citing_title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3","json":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3.json","graph_json":"https://pith.science/api/pith-number/ELEWJVUGACQVVSPKAF25PCMZR3/graph.json","events_json":"https://pith.science/api/pith-number/ELEWJVUGACQVVSPKAF25PCMZR3/events.json","paper":"https://pith.science/paper/ELEWJVUG"},"agent_actions":{"view_html":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3","download_json":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3.json","view_paper":"https://pith.science/paper/ELEWJVUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23504&json=true","fetch_graph":"https://pith.science/api/pith-number/ELEWJVUGACQVVSPKAF25PCMZR3/graph.json","fetch_events":"https://pith.science/api/pith-number/ELEWJVUGACQVVSPKAF25PCMZR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3/action/storage_attestation","attest_author":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3/action/author_attestation","sign_citation":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3/action/citation_signature","submit_replication":"https://pith.science/pith/ELEWJVUGACQVVSPKAF25PCMZR3/action/replication_record"}},"created_at":"2026-07-05T11:12:03.150777+00:00","updated_at":"2026-07-05T11:12:03.150777+00:00"}