{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKJMNLUUXROCX4RYSKTHAAS7NM","short_pith_number":"pith:OKJMNLUU","schema_version":"1.0","canonical_sha256":"7292c6ae94bc5c2bf23892a670025f6b2bffa9b4159b8995b7e5b192ea35667b","source":{"kind":"arxiv","id":"2408.15628","version":2},"attestation_state":"computed","paper":{"title":"CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shang-Hong Lai, Yu-Hsuan Hsieh","submitted_at":"2024-08-28T08:27:41Z","abstract_excerpt":"To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods. Although these methods are effective, they frequently lead to unsatisfactory segmentation results and require manual annotations. To address these drawbacks, we develop an unsupervised component segmentation technique that leverages foundation models to autonomously generate training labels for a lightweight segmentation network without human labeling. Integrating this new segmentation technique with our proposed Patch Histogram module and the Local-Glo"},"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":"2408.15628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T08:27:41Z","cross_cats_sorted":[],"title_canon_sha256":"e00643fa6a50ebf08abeb7c9c26262fbcab69b3a3dbb877e0202761e181279a3","abstract_canon_sha256":"fb72321b2bfdfc6551ffb7e525411d0a3d4c145ce08b1e0ab81f42e1c9764578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:38.654882Z","signature_b64":"fXZqUajpxe+wGsb2HYwm/Q5vt1lTisZ8eSXrG10Y1CTAFkqCPEFex9zvK//bobzLsqbRq9DFRAY6PCjY8EQNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7292c6ae94bc5c2bf23892a670025f6b2bffa9b4159b8995b7e5b192ea35667b","last_reissued_at":"2026-07-05T09:01:38.654388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:38.654388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shang-Hong Lai, Yu-Hsuan Hsieh","submitted_at":"2024-08-28T08:27:41Z","abstract_excerpt":"To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods. Although these methods are effective, they frequently lead to unsatisfactory segmentation results and require manual annotations. To address these drawbacks, we develop an unsupervised component segmentation technique that leverages foundation models to autonomously generate training labels for a lightweight segmentation network without human labeling. Integrating this new segmentation technique with our proposed Patch Histogram module and the Local-Glo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15628","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/2408.15628/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":"2408.15628","created_at":"2026-07-05T09:01:38.654447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15628v2","created_at":"2026-07-05T09:01:38.654447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15628","created_at":"2026-07-05T09:01:38.654447+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKJMNLUUXROC","created_at":"2026-07-05T09:01:38.654447+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKJMNLUUXROCX4RY","created_at":"2026-07-05T09:01:38.654447+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKJMNLUU","created_at":"2026-07-05T09:01:38.654447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20768","citing_title":"UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM","json":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM.json","graph_json":"https://pith.science/api/pith-number/OKJMNLUUXROCX4RYSKTHAAS7NM/graph.json","events_json":"https://pith.science/api/pith-number/OKJMNLUUXROCX4RYSKTHAAS7NM/events.json","paper":"https://pith.science/paper/OKJMNLUU"},"agent_actions":{"view_html":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM","download_json":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM.json","view_paper":"https://pith.science/paper/OKJMNLUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15628&json=true","fetch_graph":"https://pith.science/api/pith-number/OKJMNLUUXROCX4RYSKTHAAS7NM/graph.json","fetch_events":"https://pith.science/api/pith-number/OKJMNLUUXROCX4RYSKTHAAS7NM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM/action/storage_attestation","attest_author":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM/action/author_attestation","sign_citation":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM/action/citation_signature","submit_replication":"https://pith.science/pith/OKJMNLUUXROCX4RYSKTHAAS7NM/action/replication_record"}},"created_at":"2026-07-05T09:01:38.654447+00:00","updated_at":"2026-07-05T09:01:38.654447+00:00"}