{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:II7WVGPMBNYGQMHF67QV2KQF3I","short_pith_number":"pith:II7WVGPM","schema_version":"1.0","canonical_sha256":"423f6a99ec0b706830e5f7e15d2a05da256e6e0d28632625a352e8dfd83189d7","source":{"kind":"arxiv","id":"2507.21649","version":1},"attestation_state":"computed","paper":{"title":"The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Guo, Han Zhu, Jian Xu, Linlin Huang, Peipei Yang, Shibo Gao, Shuai Li, Xu-Yao Zhang, Yangyang Liu, Yi Chen","submitted_at":"2025-07-29T10:07:24Z","abstract_excerpt":"Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public safety. With the advancement of deep learning, the continuous evolution of deep model architectures has driven innovation in VAD methodologies, significantly enhancing feature representation and scene adaptability, thereby improving algorithm generalization and expanding application boundaries. More importantly, the rapid development of multi-modal large language (MLLMs) and large language models (LLMs) has introduc"},"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":"2507.21649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T10:07:24Z","cross_cats_sorted":[],"title_canon_sha256":"d7d679c0b90a0287ff44cfe409805bb0cb0deddf3073e12f4bd2b7c961ffb226","abstract_canon_sha256":"44eaaccd316f5544a2f0112e0c6b1125bd387fe527f0edbbf8aeb2b7fb27bf76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:03.871190Z","signature_b64":"POldYvV1MKR6+gMH1XbFwPZOfz1VWGH0ZIZk+TW+o6zjloXUfdIPhx4ofas1T01vPFyNqRytsPMxUexfDf9wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"423f6a99ec0b706830e5f7e15d2a05da256e6e0d28632625a352e8dfd83189d7","last_reissued_at":"2026-07-05T11:45:03.870753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:03.870753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Guo, Han Zhu, Jian Xu, Linlin Huang, Peipei Yang, Shibo Gao, Shuai Li, Xu-Yao Zhang, Yangyang Liu, Yi Chen","submitted_at":"2025-07-29T10:07:24Z","abstract_excerpt":"Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public safety. With the advancement of deep learning, the continuous evolution of deep model architectures has driven innovation in VAD methodologies, significantly enhancing feature representation and scene adaptability, thereby improving algorithm generalization and expanding application boundaries. More importantly, the rapid development of multi-modal large language (MLLMs) and large language models (LLMs) has introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21649","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/2507.21649/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":"2507.21649","created_at":"2026-07-05T11:45:03.870808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21649v1","created_at":"2026-07-05T11:45:03.870808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21649","created_at":"2026-07-05T11:45:03.870808+00:00"},{"alias_kind":"pith_short_12","alias_value":"II7WVGPMBNYG","created_at":"2026-07-05T11:45:03.870808+00:00"},{"alias_kind":"pith_short_16","alias_value":"II7WVGPMBNYGQMHF","created_at":"2026-07-05T11:45:03.870808+00:00"},{"alias_kind":"pith_short_8","alias_value":"II7WVGPM","created_at":"2026-07-05T11:45:03.870808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22884","citing_title":"Can Multimodal Large Language Models Truly Understand Small Objects?","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I","json":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I.json","graph_json":"https://pith.science/api/pith-number/II7WVGPMBNYGQMHF67QV2KQF3I/graph.json","events_json":"https://pith.science/api/pith-number/II7WVGPMBNYGQMHF67QV2KQF3I/events.json","paper":"https://pith.science/paper/II7WVGPM"},"agent_actions":{"view_html":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I","download_json":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I.json","view_paper":"https://pith.science/paper/II7WVGPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21649&json=true","fetch_graph":"https://pith.science/api/pith-number/II7WVGPMBNYGQMHF67QV2KQF3I/graph.json","fetch_events":"https://pith.science/api/pith-number/II7WVGPMBNYGQMHF67QV2KQF3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I/action/storage_attestation","attest_author":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I/action/author_attestation","sign_citation":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I/action/citation_signature","submit_replication":"https://pith.science/pith/II7WVGPMBNYGQMHF67QV2KQF3I/action/replication_record"}},"created_at":"2026-07-05T11:45:03.870808+00:00","updated_at":"2026-07-05T11:45:03.870808+00:00"}