{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JPIGIFYLDHPLUM7JI4R2QRHTQL","short_pith_number":"pith:JPIGIFYL","schema_version":"1.0","canonical_sha256":"4bd064170b19deba33e94723a844f382eec9b5e7633ab85f15fa84750a881ce3","source":{"kind":"arxiv","id":"2504.13092","version":3},"attestation_state":"computed","paper":{"title":"EventVAD: Training-Free Event-Aware Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Ma, Fanhu Zeng, Haojin He, Hao Tang, Muyang Zhang, Shuyan Li, Sijie Li, Siyu Chen, Xiaochen Wang, Xinwei Long, Yan Wang, Yihua Shao, Yuxuan Fan, Ziyang Yan","submitted_at":"2025-04-17T16:59:04Z","abstract_excerpt":"Video Anomaly Detection~(VAD) focuses on identifying anomalies within videos. Supervised methods require an amount of in-domain training data and often struggle to generalize to unseen anomalies. In contrast, training-free methods leverage the intrinsic world knowledge of large language models (LLMs) to detect anomalies but face challenges in localizing fine-grained visual transitions and diverse events. Therefore, we propose EventVAD, an event-aware video anomaly detection framework that combines tailored dynamic graph architectures and multimodal LLMs through temporal-event reasoning. Specif"},"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":"2504.13092","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T16:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"93e2c5fc06c7204c6777bfa5d920dcb012641b964f4b8b0321b19d7a0c373041","abstract_canon_sha256":"ab3e2247a8b0f6563ea08259a5c5eab96ac0853909a13655d9b5efc48d4bf35f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:04.307511Z","signature_b64":"Ec/IPmz4sYx25i4968eDcDaRIY5j7d34srkWWR1M30a9rfAvIxpZ9bwY2sS27bMIFn0NOaFF6E3ZLBriKzQCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd064170b19deba33e94723a844f382eec9b5e7633ab85f15fa84750a881ce3","last_reissued_at":"2026-07-05T11:44:04.306975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:04.306975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EventVAD: Training-Free Event-Aware Video Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Ma, Fanhu Zeng, Haojin He, Hao Tang, Muyang Zhang, Shuyan Li, Sijie Li, Siyu Chen, Xiaochen Wang, Xinwei Long, Yan Wang, Yihua Shao, Yuxuan Fan, Ziyang Yan","submitted_at":"2025-04-17T16:59:04Z","abstract_excerpt":"Video Anomaly Detection~(VAD) focuses on identifying anomalies within videos. Supervised methods require an amount of in-domain training data and often struggle to generalize to unseen anomalies. In contrast, training-free methods leverage the intrinsic world knowledge of large language models (LLMs) to detect anomalies but face challenges in localizing fine-grained visual transitions and diverse events. Therefore, we propose EventVAD, an event-aware video anomaly detection framework that combines tailored dynamic graph architectures and multimodal LLMs through temporal-event reasoning. Specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13092","kind":"arxiv","version":3},"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/2504.13092/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":"2504.13092","created_at":"2026-07-05T11:44:04.307031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13092v3","created_at":"2026-07-05T11:44:04.307031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13092","created_at":"2026-07-05T11:44:04.307031+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPIGIFYLDHPL","created_at":"2026-07-05T11:44:04.307031+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPIGIFYLDHPLUM7J","created_at":"2026-07-05T11:44:04.307031+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPIGIFYL","created_at":"2026-07-05T11:44:04.307031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL","json":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL.json","graph_json":"https://pith.science/api/pith-number/JPIGIFYLDHPLUM7JI4R2QRHTQL/graph.json","events_json":"https://pith.science/api/pith-number/JPIGIFYLDHPLUM7JI4R2QRHTQL/events.json","paper":"https://pith.science/paper/JPIGIFYL"},"agent_actions":{"view_html":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL","download_json":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL.json","view_paper":"https://pith.science/paper/JPIGIFYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13092&json=true","fetch_graph":"https://pith.science/api/pith-number/JPIGIFYLDHPLUM7JI4R2QRHTQL/graph.json","fetch_events":"https://pith.science/api/pith-number/JPIGIFYLDHPLUM7JI4R2QRHTQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL/action/storage_attestation","attest_author":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL/action/author_attestation","sign_citation":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL/action/citation_signature","submit_replication":"https://pith.science/pith/JPIGIFYLDHPLUM7JI4R2QRHTQL/action/replication_record"}},"created_at":"2026-07-05T11:44:04.307031+00:00","updated_at":"2026-07-05T11:44:04.307031+00:00"}