{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y6PJPBDD44SZFDYZOB3LQ54KKQ","short_pith_number":"pith:Y6PJPBDD","schema_version":"1.0","canonical_sha256":"c79e978463e725928f197076b8778a5424fa549334ac52bba032bba762666416","source":{"kind":"arxiv","id":"2410.14987","version":3},"attestation_state":"computed","paper":{"title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xue, Haotian Liu, Shilei Zeng, Xurui Li, Yu Zhou, Zhewei Dai","submitted_at":"2024-10-19T05:37:11Z","abstract_excerpt":"We introduce SeaS, a unified industrial generative model for automatically creating diverse anomalies, authentic normal products, and precise anomaly masks. While extensive research exists, most efforts either focus on specific tasks, i.e., anomalies or normal products only, or require separate models for each anomaly type. Consequently, prior methods either offer limited generative capability or depend on a vast array of anomaly-specific models. We demonstrate that U-Net's differentiated learning ability captures the distinct visual traits of slightly-varied normal products and diverse anomal"},"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":"2410.14987","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T05:37:11Z","cross_cats_sorted":[],"title_canon_sha256":"7d499fd18925629bf554f99cb273e9fcdda84769bb20d3e795bab31954d6567b","abstract_canon_sha256":"0e70717d7a34140770a76038f17889f11b22fca051d3d0efce34816747884e54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:48.911447Z","signature_b64":"ma6gQDzZT+t/OL9Z6kP6Op+UX4/9C9gajtKSo8CaEr5OsiB2UzYwEaqmB4SnOQlLW0g/GEZ5CCkFwo9UY24DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c79e978463e725928f197076b8778a5424fa549334ac52bba032bba762666416","last_reissued_at":"2026-07-05T11:38:48.910957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:48.910957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xue, Haotian Liu, Shilei Zeng, Xurui Li, Yu Zhou, Zhewei Dai","submitted_at":"2024-10-19T05:37:11Z","abstract_excerpt":"We introduce SeaS, a unified industrial generative model for automatically creating diverse anomalies, authentic normal products, and precise anomaly masks. While extensive research exists, most efforts either focus on specific tasks, i.e., anomalies or normal products only, or require separate models for each anomaly type. Consequently, prior methods either offer limited generative capability or depend on a vast array of anomaly-specific models. We demonstrate that U-Net's differentiated learning ability captures the distinct visual traits of slightly-varied normal products and diverse anomal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14987","kind":"arxiv","version":3},"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/2410.14987/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":"2410.14987","created_at":"2026-07-05T11:38:48.911015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14987v3","created_at":"2026-07-05T11:38:48.911015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14987","created_at":"2026-07-05T11:38:48.911015+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6PJPBDD44SZ","created_at":"2026-07-05T11:38:48.911015+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6PJPBDD44SZFDYZ","created_at":"2026-07-05T11:38:48.911015+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6PJPBDD","created_at":"2026-07-05T11:38:48.911015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13779","citing_title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07900","citing_title":"AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ","json":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ.json","graph_json":"https://pith.science/api/pith-number/Y6PJPBDD44SZFDYZOB3LQ54KKQ/graph.json","events_json":"https://pith.science/api/pith-number/Y6PJPBDD44SZFDYZOB3LQ54KKQ/events.json","paper":"https://pith.science/paper/Y6PJPBDD"},"agent_actions":{"view_html":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ","download_json":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ.json","view_paper":"https://pith.science/paper/Y6PJPBDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14987&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6PJPBDD44SZFDYZOB3LQ54KKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6PJPBDD44SZFDYZOB3LQ54KKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y6PJPBDD44SZFDYZOB3LQ54KKQ/action/replication_record"}},"created_at":"2026-07-05T11:38:48.911015+00:00","updated_at":"2026-07-05T11:38:48.911015+00:00"}