{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7HJRWUWDLTUI4FP6FRXCUSMUK4","short_pith_number":"pith:7HJRWUWD","schema_version":"1.0","canonical_sha256":"f9d31b52c35ce88e15fe2c6e2a4994570ab28c14047afde666ea3d11cf1eec6e","source":{"kind":"arxiv","id":"2504.12970","version":2},"attestation_state":"computed","paper":{"title":"MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Long Qian, Ming Tang, Yingying Chen","submitted_at":"2025-04-17T14:22:27Z","abstract_excerpt":"Currently, industrial anomaly detection suffers from two bottlenecks: (i) the rarity of real-world defect images and (ii) the opacity of sample quality when synthetic data are used. Existing synthetic strategies (e.g., cut-and-paste) overlook the underlying physical causes of defects, leading to inconsistent, low-fidelity anomalies that hamper model generalization to real-world complexities. In this paper, we introduce a novel and lightweight pipeline that generates synthetic anomalies through Math-Phys model guidance, refines them via a Coarse-to-Fine approach and employs a bi-level optimizat"},"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":"2504.12970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T14:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"f54584476033b918bfef03d8a091e9bcafb0d77827e090a001b50e5e7ae11fee","abstract_canon_sha256":"cc2c50ca4a57e34890eaea2c34d4a2b4f0bf08af013673850864fe93cb07148c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:02.607742Z","signature_b64":"F/vLK8eetsKuO6BZTCof7kn7OZvcj/BIM5cLlSBGDY/jhHtGnmRP0N6uybNkhYW/g/TpOMN7JQXkLBgqLK0sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d31b52c35ce88e15fe2c6e2a4994570ab28c14047afde666ea3d11cf1eec6e","last_reissued_at":"2026-07-05T11:48:02.607243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:02.607243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Long Qian, Ming Tang, Yingying Chen","submitted_at":"2025-04-17T14:22:27Z","abstract_excerpt":"Currently, industrial anomaly detection suffers from two bottlenecks: (i) the rarity of real-world defect images and (ii) the opacity of sample quality when synthetic data are used. Existing synthetic strategies (e.g., cut-and-paste) overlook the underlying physical causes of defects, leading to inconsistent, low-fidelity anomalies that hamper model generalization to real-world complexities. In this paper, we introduce a novel and lightweight pipeline that generates synthetic anomalies through Math-Phys model guidance, refines them via a Coarse-to-Fine approach and employs a bi-level optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12970","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/2504.12970/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":"2504.12970","created_at":"2026-07-05T11:48:02.607302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12970v2","created_at":"2026-07-05T11:48:02.607302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12970","created_at":"2026-07-05T11:48:02.607302+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HJRWUWDLTUI","created_at":"2026-07-05T11:48:02.607302+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HJRWUWDLTUI4FP6","created_at":"2026-07-05T11:48:02.607302+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HJRWUWD","created_at":"2026-07-05T11:48:02.607302+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/7HJRWUWDLTUI4FP6FRXCUSMUK4","json":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4.json","graph_json":"https://pith.science/api/pith-number/7HJRWUWDLTUI4FP6FRXCUSMUK4/graph.json","events_json":"https://pith.science/api/pith-number/7HJRWUWDLTUI4FP6FRXCUSMUK4/events.json","paper":"https://pith.science/paper/7HJRWUWD"},"agent_actions":{"view_html":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4","download_json":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4.json","view_paper":"https://pith.science/paper/7HJRWUWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12970&json=true","fetch_graph":"https://pith.science/api/pith-number/7HJRWUWDLTUI4FP6FRXCUSMUK4/graph.json","fetch_events":"https://pith.science/api/pith-number/7HJRWUWDLTUI4FP6FRXCUSMUK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4/action/storage_attestation","attest_author":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4/action/author_attestation","sign_citation":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4/action/citation_signature","submit_replication":"https://pith.science/pith/7HJRWUWDLTUI4FP6FRXCUSMUK4/action/replication_record"}},"created_at":"2026-07-05T11:48:02.607302+00:00","updated_at":"2026-07-05T11:48:02.607302+00:00"}