{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JB4G52YKLGX246A56JLFSSDLL2","short_pith_number":"pith:JB4G52YK","schema_version":"1.0","canonical_sha256":"48786eeb0a59afae781df25659486b5e94c28a153ccff261cb3b0a32903266ff","source":{"kind":"arxiv","id":"2106.08265","version":2},"attestation_state":"computed","paper":{"title":"Towards Total Recall in Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Sch\\\"olkopf, Joaquin Zepeda, Karsten Roth, Latha Pemula, Peter Gehler, Thomas Brox","submitted_at":"2021-06-15T16:27:02Z","abstract_excerpt":"Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose \\textbf{PatchCore}, which uses a maximally rep"},"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":"2106.08265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-15T16:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"051d3fb1381add211580fa07f4218584378dc5fdb43f821434a84731237e20dd","abstract_canon_sha256":"76822797b8a24165644c5e58659c31d79d85328a1221af82361ec8c2c3ffd12a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:42.607633Z","signature_b64":"/XTbtlNJ26vNFi1Hs8VGiHLZCx5KDh0ulW8byBpI1smlCZoj4zUMWGCMRa203HOpNQ9NhPz4r0rHmbqElYygAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48786eeb0a59afae781df25659486b5e94c28a153ccff261cb3b0a32903266ff","last_reissued_at":"2026-07-05T04:20:42.607082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:42.607082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Total Recall in Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Sch\\\"olkopf, Joaquin Zepeda, Karsten Roth, Latha Pemula, Peter Gehler, Thomas Brox","submitted_at":"2021-06-15T16:27:02Z","abstract_excerpt":"Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose \\textbf{PatchCore}, which uses a maximally rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08265","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/2106.08265/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":"2106.08265","created_at":"2026-07-05T04:20:42.607150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08265v2","created_at":"2026-07-05T04:20:42.607150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08265","created_at":"2026-07-05T04:20:42.607150+00:00"},{"alias_kind":"pith_short_12","alias_value":"JB4G52YKLGX2","created_at":"2026-07-05T04:20:42.607150+00:00"},{"alias_kind":"pith_short_16","alias_value":"JB4G52YKLGX246A5","created_at":"2026-07-05T04:20:42.607150+00:00"},{"alias_kind":"pith_short_8","alias_value":"JB4G52YK","created_at":"2026-07-05T04:20:42.607150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29506","citing_title":"Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09524","citing_title":"HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03437","citing_title":"Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07802","citing_title":"Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15291","citing_title":"AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03437","citing_title":"Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2","json":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2.json","graph_json":"https://pith.science/api/pith-number/JB4G52YKLGX246A56JLFSSDLL2/graph.json","events_json":"https://pith.science/api/pith-number/JB4G52YKLGX246A56JLFSSDLL2/events.json","paper":"https://pith.science/paper/JB4G52YK"},"agent_actions":{"view_html":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2","download_json":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2.json","view_paper":"https://pith.science/paper/JB4G52YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08265&json=true","fetch_graph":"https://pith.science/api/pith-number/JB4G52YKLGX246A56JLFSSDLL2/graph.json","fetch_events":"https://pith.science/api/pith-number/JB4G52YKLGX246A56JLFSSDLL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2/action/storage_attestation","attest_author":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2/action/author_attestation","sign_citation":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2/action/citation_signature","submit_replication":"https://pith.science/pith/JB4G52YKLGX246A56JLFSSDLL2/action/replication_record"}},"created_at":"2026-07-05T04:20:42.607150+00:00","updated_at":"2026-07-05T04:20:42.607150+00:00"}