{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SLWWCA3KY3KCQSOGNDLLPEN53Y","short_pith_number":"pith:SLWWCA3K","schema_version":"1.0","canonical_sha256":"92ed61036ac6d42849c668d6b791bdde25634fd867c66628f7c4257d15095370","source":{"kind":"arxiv","id":"2202.02998","version":2},"attestation_state":"computed","paper":{"title":"Automatic defect segmentation by unsupervised anomaly learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Levant, Nati Ofir, Omer Granoviter, Ore Shtalrid, Ran Yacobi","submitted_at":"2022-02-07T08:33:36Z","abstract_excerpt":"This paper addresses the problem of defect segmentation in semiconductor manufacturing. The input of our segmentation is a scanning-electron-microscopy (SEM) image of the candidate defect region. We train a U-net shape network to segment defects using a dataset of clean background images. The samples of the training phase are produced automatically such that no manual labeling is required. To enrich the dataset of clean background samples, we apply defect implant augmentation. To that end, we apply a copy-and-paste of a random image patch in the clean specimen. To improve the robustness of the"},"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":"2202.02998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-07T08:33:36Z","cross_cats_sorted":[],"title_canon_sha256":"7e33bf29971754abbce6239cf97f2c08952700045d6f2890a49d317756161884","abstract_canon_sha256":"309bdd1ca0462e682e27f177865c37903b0bd3dd24a38dfc61729f1012b496e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:15.029884Z","signature_b64":"D6InO3JWy6i1kcflNXL1k6w4jYQiNRkweYoe11jilV+23hnzsXqJmG+VzlmnZvahBA1ClvI4RYzPsBcxEjI1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92ed61036ac6d42849c668d6b791bdde25634fd867c66628f7c4257d15095370","last_reissued_at":"2026-07-05T05:08:15.029436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:15.029436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic defect segmentation by unsupervised anomaly learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Levant, Nati Ofir, Omer Granoviter, Ore Shtalrid, Ran Yacobi","submitted_at":"2022-02-07T08:33:36Z","abstract_excerpt":"This paper addresses the problem of defect segmentation in semiconductor manufacturing. The input of our segmentation is a scanning-electron-microscopy (SEM) image of the candidate defect region. We train a U-net shape network to segment defects using a dataset of clean background images. The samples of the training phase are produced automatically such that no manual labeling is required. To enrich the dataset of clean background samples, we apply defect implant augmentation. To that end, we apply a copy-and-paste of a random image patch in the clean specimen. To improve the robustness of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02998","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/2202.02998/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":"2202.02998","created_at":"2026-07-05T05:08:15.029496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02998v2","created_at":"2026-07-05T05:08:15.029496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02998","created_at":"2026-07-05T05:08:15.029496+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLWWCA3KY3KC","created_at":"2026-07-05T05:08:15.029496+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLWWCA3KY3KCQSOG","created_at":"2026-07-05T05:08:15.029496+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLWWCA3K","created_at":"2026-07-05T05:08:15.029496+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/SLWWCA3KY3KCQSOGNDLLPEN53Y","json":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y.json","graph_json":"https://pith.science/api/pith-number/SLWWCA3KY3KCQSOGNDLLPEN53Y/graph.json","events_json":"https://pith.science/api/pith-number/SLWWCA3KY3KCQSOGNDLLPEN53Y/events.json","paper":"https://pith.science/paper/SLWWCA3K"},"agent_actions":{"view_html":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y","download_json":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y.json","view_paper":"https://pith.science/paper/SLWWCA3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02998&json=true","fetch_graph":"https://pith.science/api/pith-number/SLWWCA3KY3KCQSOGNDLLPEN53Y/graph.json","fetch_events":"https://pith.science/api/pith-number/SLWWCA3KY3KCQSOGNDLLPEN53Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y/action/storage_attestation","attest_author":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y/action/author_attestation","sign_citation":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y/action/citation_signature","submit_replication":"https://pith.science/pith/SLWWCA3KY3KCQSOGNDLLPEN53Y/action/replication_record"}},"created_at":"2026-07-05T05:08:15.029496+00:00","updated_at":"2026-07-05T05:08:15.029496+00:00"}