{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZHWSD5JBQDB7FS53AKC7VJSBEB","short_pith_number":"pith:ZHWSD5JB","schema_version":"1.0","canonical_sha256":"c9ed21f52180c3f2cbbb0285faa641204a799e1d05b1e98bccf9d917e9a5793f","source":{"kind":"arxiv","id":"2406.10326","version":2},"attestation_state":"computed","paper":{"title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanan Gani, Muzammal Naseer, Rohit Bharadwaj, Salman Khan","submitted_at":"2024-06-14T17:59:01Z","abstract_excerpt":"The recent developments in Large Multi-modal Video Models (Video-LMMs) have significantly enhanced our ability to interpret and analyze video data. Despite their impressive capabilities, current Video-LMMs have not been evaluated for anomaly detection tasks, which is critical to their deployment in practical scenarios e.g., towards identifying deepfakes, manipulated video content, traffic accidents and crimes. In this paper, we introduce VANE-Bench, a benchmark designed to assess the proficiency of Video-LMMs in detecting and localizing anomalies and inconsistencies in videos. Our dataset comp"},"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":"2406.10326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"baafb7869fa277660f7f0e4878369a04c295f16b49b19faa2b09567e0470c46e","abstract_canon_sha256":"cd6f24ee0916c6349bf6cb1eed90a0f5ee15370d1e889baf79260dbe601a30e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:34.210145Z","signature_b64":"C55sX4S9fG2TALtoGbAbGuSNXs/1QSmvYVo7q9Z+LWg2lDWB0z5lrl0PzI9t0T0Z7WdEHUSURqE+fzaqJR0wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ed21f52180c3f2cbbb0285faa641204a799e1d05b1e98bccf9d917e9a5793f","last_reissued_at":"2026-07-05T10:38:34.209676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:34.209676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanan Gani, Muzammal Naseer, Rohit Bharadwaj, Salman Khan","submitted_at":"2024-06-14T17:59:01Z","abstract_excerpt":"The recent developments in Large Multi-modal Video Models (Video-LMMs) have significantly enhanced our ability to interpret and analyze video data. Despite their impressive capabilities, current Video-LMMs have not been evaluated for anomaly detection tasks, which is critical to their deployment in practical scenarios e.g., towards identifying deepfakes, manipulated video content, traffic accidents and crimes. In this paper, we introduce VANE-Bench, a benchmark designed to assess the proficiency of Video-LMMs in detecting and localizing anomalies and inconsistencies in videos. Our dataset comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10326","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/2406.10326/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":"2406.10326","created_at":"2026-07-05T10:38:34.209731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10326v2","created_at":"2026-07-05T10:38:34.209731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10326","created_at":"2026-07-05T10:38:34.209731+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHWSD5JBQDB7","created_at":"2026-07-05T10:38:34.209731+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHWSD5JBQDB7FS53","created_at":"2026-07-05T10:38:34.209731+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHWSD5JB","created_at":"2026-07-05T10:38:34.209731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06912","citing_title":"Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB","json":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB.json","graph_json":"https://pith.science/api/pith-number/ZHWSD5JBQDB7FS53AKC7VJSBEB/graph.json","events_json":"https://pith.science/api/pith-number/ZHWSD5JBQDB7FS53AKC7VJSBEB/events.json","paper":"https://pith.science/paper/ZHWSD5JB"},"agent_actions":{"view_html":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB","download_json":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB.json","view_paper":"https://pith.science/paper/ZHWSD5JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10326&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHWSD5JBQDB7FS53AKC7VJSBEB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHWSD5JBQDB7FS53AKC7VJSBEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB/action/storage_attestation","attest_author":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB/action/author_attestation","sign_citation":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB/action/citation_signature","submit_replication":"https://pith.science/pith/ZHWSD5JBQDB7FS53AKC7VJSBEB/action/replication_record"}},"created_at":"2026-07-05T10:38:34.209731+00:00","updated_at":"2026-07-05T10:38:34.209731+00:00"}