{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XRMJMVFCH37PX253Z7IYCA5WLX","short_pith_number":"pith:XRMJMVFC","schema_version":"1.0","canonical_sha256":"bc589654a23efefbebbbcfd18103b65dffe115a7d85daa48af9976ae4a4ad4b2","source":{"kind":"arxiv","id":"2107.12571","version":1},"attestation_state":"computed","paper":{"title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Denis Gudovskiy, Kazuki Kozuka, Shun Ishizaka","submitted_at":"2021-07-27T03:10:38Z","abstract_excerpt":"Unsupervised anomaly detection with localization has many practical applications when labeling is infeasible and, moreover, when anomaly examples are completely missing in the train data. While recently proposed models for such data setup achieve high accuracy metrics, their complexity is a limiting factor for real-time processing. In this paper, we propose a real-time model and analytically derive its relationship to prior methods. Our CFLOW-AD model is based on a conditional normalizing flow framework adopted for anomaly detection with localization. In particular, CFLOW-AD consists of a disc"},"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":"2107.12571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-27T03:10:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7047e017b7c6e89d0cc048e79951b5fc2b3090f125e39c22eda787ab035cefa9","abstract_canon_sha256":"217b7c437ebe45c488be887456df134b5d3a672114731b029cb5e33eaa011218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:57.756684Z","signature_b64":"95QcnOrd5dlyB8M2ZCJOd4BaqEqzYOLIH61FOHA4hxoRISatc/28VorJzAOwrLxqzcl3HCN9GSIviewKyRUUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc589654a23efefbebbbcfd18103b65dffe115a7d85daa48af9976ae4a4ad4b2","last_reissued_at":"2026-07-05T03:00:57.756285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:57.756285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Denis Gudovskiy, Kazuki Kozuka, Shun Ishizaka","submitted_at":"2021-07-27T03:10:38Z","abstract_excerpt":"Unsupervised anomaly detection with localization has many practical applications when labeling is infeasible and, moreover, when anomaly examples are completely missing in the train data. While recently proposed models for such data setup achieve high accuracy metrics, their complexity is a limiting factor for real-time processing. In this paper, we propose a real-time model and analytically derive its relationship to prior methods. Our CFLOW-AD model is based on a conditional normalizing flow framework adopted for anomaly detection with localization. In particular, CFLOW-AD consists of a disc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12571","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/2107.12571/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":"2107.12571","created_at":"2026-07-05T03:00:57.756358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12571v1","created_at":"2026-07-05T03:00:57.756358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12571","created_at":"2026-07-05T03:00:57.756358+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRMJMVFCH37P","created_at":"2026-07-05T03:00:57.756358+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRMJMVFCH37PX253","created_at":"2026-07-05T03:00:57.756358+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRMJMVFC","created_at":"2026-07-05T03:00:57.756358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09187","citing_title":"Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX","json":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX.json","graph_json":"https://pith.science/api/pith-number/XRMJMVFCH37PX253Z7IYCA5WLX/graph.json","events_json":"https://pith.science/api/pith-number/XRMJMVFCH37PX253Z7IYCA5WLX/events.json","paper":"https://pith.science/paper/XRMJMVFC"},"agent_actions":{"view_html":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX","download_json":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX.json","view_paper":"https://pith.science/paper/XRMJMVFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12571&json=true","fetch_graph":"https://pith.science/api/pith-number/XRMJMVFCH37PX253Z7IYCA5WLX/graph.json","fetch_events":"https://pith.science/api/pith-number/XRMJMVFCH37PX253Z7IYCA5WLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX/action/storage_attestation","attest_author":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX/action/author_attestation","sign_citation":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX/action/citation_signature","submit_replication":"https://pith.science/pith/XRMJMVFCH37PX253Z7IYCA5WLX/action/replication_record"}},"created_at":"2026-07-05T03:00:57.756358+00:00","updated_at":"2026-07-05T03:00:57.756358+00:00"}