{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVV2R3TTR6KVBKYZWSWGL2BCRA","short_pith_number":"pith:MVV2R3TT","schema_version":"1.0","canonical_sha256":"656ba8ee738f9550ab19b4ac65e8228810271bf37ab3e4b761bf9df525c47daf","source":{"kind":"arxiv","id":"2506.23282","version":1},"attestation_state":"computed","paper":{"title":"Autoregressive Denoising Score Matching is a Good Video Anomaly Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congqi Cao, Hanwen Zhang, Lingtong Min, Qinyi Lv, Yanning Zhang","submitted_at":"2025-06-29T15:14:32Z","abstract_excerpt":"Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching growing interest, as it can model normal distribution and detect out-of-distribution anomalies. However, these likelihood-based methods are blind to the anomalies located in local modes near the learned distribution. To handle these ``unseen\" anomalies, we dive into three gaps uniquely existing in VAD regarding scene, motion and appearance. Specifically, we first build a noise-conditioned score transformer for denoising "},"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":"2506.23282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T15:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"c1ba31936f008a35d165dcff72ec226e5f9972955924e7e4dc9a44ef22bd34b3","abstract_canon_sha256":"62f4a55507ca4eb9ff4ce394aaa4997c8d9737619310833e9c0747ed05ddf73f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:19.164114Z","signature_b64":"DtNveYzB9JbGpTiTAd0NBHP+e/vNWxLO/WVrBqOnBsZU0wTMR7RjrbGyZssrLpA1RKNMPcw+ht4gysnjLp4ZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656ba8ee738f9550ab19b4ac65e8228810271bf37ab3e4b761bf9df525c47daf","last_reissued_at":"2026-07-05T11:29:19.163627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:19.163627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Denoising Score Matching is a Good Video Anomaly Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congqi Cao, Hanwen Zhang, Lingtong Min, Qinyi Lv, Yanning Zhang","submitted_at":"2025-06-29T15:14:32Z","abstract_excerpt":"Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching growing interest, as it can model normal distribution and detect out-of-distribution anomalies. However, these likelihood-based methods are blind to the anomalies located in local modes near the learned distribution. To handle these ``unseen\" anomalies, we dive into three gaps uniquely existing in VAD regarding scene, motion and appearance. Specifically, we first build a noise-conditioned score transformer for denoising "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23282","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/2506.23282/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":"2506.23282","created_at":"2026-07-05T11:29:19.163689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23282v1","created_at":"2026-07-05T11:29:19.163689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23282","created_at":"2026-07-05T11:29:19.163689+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVV2R3TTR6KV","created_at":"2026-07-05T11:29:19.163689+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVV2R3TTR6KVBKYZ","created_at":"2026-07-05T11:29:19.163689+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVV2R3TT","created_at":"2026-07-05T11:29:19.163689+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/MVV2R3TTR6KVBKYZWSWGL2BCRA","json":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA.json","graph_json":"https://pith.science/api/pith-number/MVV2R3TTR6KVBKYZWSWGL2BCRA/graph.json","events_json":"https://pith.science/api/pith-number/MVV2R3TTR6KVBKYZWSWGL2BCRA/events.json","paper":"https://pith.science/paper/MVV2R3TT"},"agent_actions":{"view_html":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA","download_json":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA.json","view_paper":"https://pith.science/paper/MVV2R3TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23282&json=true","fetch_graph":"https://pith.science/api/pith-number/MVV2R3TTR6KVBKYZWSWGL2BCRA/graph.json","fetch_events":"https://pith.science/api/pith-number/MVV2R3TTR6KVBKYZWSWGL2BCRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA/action/storage_attestation","attest_author":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA/action/author_attestation","sign_citation":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA/action/citation_signature","submit_replication":"https://pith.science/pith/MVV2R3TTR6KVBKYZWSWGL2BCRA/action/replication_record"}},"created_at":"2026-07-05T11:29:19.163689+00:00","updated_at":"2026-07-05T11:29:19.163689+00:00"}