{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6HQSYRK2RTVQXG7N6PYBYB4G4","short_pith_number":"pith:G6HQSYRK","schema_version":"1.0","canonical_sha256":"378f09622ad467585cdf6f9f80e03c3738f321fcf63aa876760ddb3a83c2c727","source":{"kind":"arxiv","id":"2309.07068","version":1},"attestation_state":"computed","paper":{"title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Jiang, Bing Li, Feiyang Wang, Leqi Geng, Tongkun Liu, Xiao Du, Zhuo Zhao","submitted_at":"2023-09-13T16:28:43Z","abstract_excerpt":"Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. In this paper, we find that the above trade-off can be better mitigated by leveraging the distinct frequency biases between normal and abnormal reconstruction errors. To this end, we propose Frequency-aware Image Restoration (FAIR), a novel self-supervised image restoration task that restores images from their high-f"},"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":"2309.07068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T16:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"f49e1dbd003c1dc32e1d8c8b694d5de29734085985d3e8ce038088ef6cea89b7","abstract_canon_sha256":"db7d1bc8bfc7545d769a0cad64ef325bf9445edcbc1c92c03ce07f1b35e0eb7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:51.262388Z","signature_b64":"wP89Z2zvdOMBgObsy8f4Q1kccob9+RySncYiU/qLATxa5aC6Oj/i7rzAvUueuTQCPBp5GkFDb8o+Ux9AVH6vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"378f09622ad467585cdf6f9f80e03c3738f321fcf63aa876760ddb3a83c2c727","last_reissued_at":"2026-07-05T10:30:51.261651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:51.261651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingke Jiang, Bing Li, Feiyang Wang, Leqi Geng, Tongkun Liu, Xiao Du, Zhuo Zhao","submitted_at":"2023-09-13T16:28:43Z","abstract_excerpt":"Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. In this paper, we find that the above trade-off can be better mitigated by leveraging the distinct frequency biases between normal and abnormal reconstruction errors. To this end, we propose Frequency-aware Image Restoration (FAIR), a novel self-supervised image restoration task that restores images from their high-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07068","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/2309.07068/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":"2309.07068","created_at":"2026-07-05T10:30:51.261777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07068v1","created_at":"2026-07-05T10:30:51.261777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07068","created_at":"2026-07-05T10:30:51.261777+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6HQSYRK2RTV","created_at":"2026-07-05T10:30:51.261777+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6HQSYRK2RTVQXG7","created_at":"2026-07-05T10:30:51.261777+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6HQSYRK","created_at":"2026-07-05T10:30:51.261777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19259","citing_title":"Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4","json":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4.json","graph_json":"https://pith.science/api/pith-number/G6HQSYRK2RTVQXG7N6PYBYB4G4/graph.json","events_json":"https://pith.science/api/pith-number/G6HQSYRK2RTVQXG7N6PYBYB4G4/events.json","paper":"https://pith.science/paper/G6HQSYRK"},"agent_actions":{"view_html":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4","download_json":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4.json","view_paper":"https://pith.science/paper/G6HQSYRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07068&json=true","fetch_graph":"https://pith.science/api/pith-number/G6HQSYRK2RTVQXG7N6PYBYB4G4/graph.json","fetch_events":"https://pith.science/api/pith-number/G6HQSYRK2RTVQXG7N6PYBYB4G4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4/action/storage_attestation","attest_author":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4/action/author_attestation","sign_citation":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4/action/citation_signature","submit_replication":"https://pith.science/pith/G6HQSYRK2RTVQXG7N6PYBYB4G4/action/replication_record"}},"created_at":"2026-07-05T10:30:51.261777+00:00","updated_at":"2026-07-05T10:30:51.261777+00:00"}