{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:55RGRDWD5A6ZEFSNQ2VTCOOLSA","short_pith_number":"pith:55RGRDWD","schema_version":"1.0","canonical_sha256":"ef62688ec3e83d92164d86ab3139cb9018ee23aa05a3f44a6ecfdef710b7051d","source":{"kind":"arxiv","id":"2605.27748","version":1},"attestation_state":"computed","paper":{"title":"Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Evelina Lamma, Niccol\\`o Ferrari, Oligert Osmani","submitted_at":"2026-05-26T22:48:00Z","abstract_excerpt":"Industrial visual anomaly detection is usually one-class: normal images are abundant, while defects are rare, heterogeneous, and often unavailable during system design. PatchCore-style retrieval suits this setting because it scores test images from a memory bank of normal patch features, but the standard Euclidean geometry ignores feature correlations and its offline construction materialises the full patch pool before subsampling.\n  We introduce Mahalanobis PatchCore, a covariance-aware, streaming-compatible extension of PatchCore. Its artificial intelligence contribution is a retrieval detec"},"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":"2605.27748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T22:48:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"13d8212645c34aa39cb2bfa0a0b76e743baaaa872b9c91c53a60ac7f4179012d","abstract_canon_sha256":"4e3af75fa976305384f84a8c38e58f0f29a770d4473e43c8142f464d339111e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:47.826666Z","signature_b64":"evjwye/mCEwctzSH8FBoF6HJfugEMdB/YVg+4AQrvLK7z5CHuCSJdoQpdFXGKzWKYzulkW8rjTTwW5P6ZVCMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef62688ec3e83d92164d86ab3139cb9018ee23aa05a3f44a6ecfdef710b7051d","last_reissued_at":"2026-05-28T01:04:47.826181Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:47.826181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Evelina Lamma, Niccol\\`o Ferrari, Oligert Osmani","submitted_at":"2026-05-26T22:48:00Z","abstract_excerpt":"Industrial visual anomaly detection is usually one-class: normal images are abundant, while defects are rare, heterogeneous, and often unavailable during system design. PatchCore-style retrieval suits this setting because it scores test images from a memory bank of normal patch features, but the standard Euclidean geometry ignores feature correlations and its offline construction materialises the full patch pool before subsampling.\n  We introduce Mahalanobis PatchCore, a covariance-aware, streaming-compatible extension of PatchCore. Its artificial intelligence contribution is a retrieval detec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27748","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/2605.27748/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":"2605.27748","created_at":"2026-05-28T01:04:47.826254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27748v1","created_at":"2026-05-28T01:04:47.826254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27748","created_at":"2026-05-28T01:04:47.826254+00:00"},{"alias_kind":"pith_short_12","alias_value":"55RGRDWD5A6Z","created_at":"2026-05-28T01:04:47.826254+00:00"},{"alias_kind":"pith_short_16","alias_value":"55RGRDWD5A6ZEFSN","created_at":"2026-05-28T01:04:47.826254+00:00"},{"alias_kind":"pith_short_8","alias_value":"55RGRDWD","created_at":"2026-05-28T01:04:47.826254+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/55RGRDWD5A6ZEFSNQ2VTCOOLSA","json":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA.json","graph_json":"https://pith.science/api/pith-number/55RGRDWD5A6ZEFSNQ2VTCOOLSA/graph.json","events_json":"https://pith.science/api/pith-number/55RGRDWD5A6ZEFSNQ2VTCOOLSA/events.json","paper":"https://pith.science/paper/55RGRDWD"},"agent_actions":{"view_html":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA","download_json":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA.json","view_paper":"https://pith.science/paper/55RGRDWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27748&json=true","fetch_graph":"https://pith.science/api/pith-number/55RGRDWD5A6ZEFSNQ2VTCOOLSA/graph.json","fetch_events":"https://pith.science/api/pith-number/55RGRDWD5A6ZEFSNQ2VTCOOLSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA/action/storage_attestation","attest_author":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA/action/author_attestation","sign_citation":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA/action/citation_signature","submit_replication":"https://pith.science/pith/55RGRDWD5A6ZEFSNQ2VTCOOLSA/action/replication_record"}},"created_at":"2026-05-28T01:04:47.826254+00:00","updated_at":"2026-05-28T01:04:47.826254+00:00"}