{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UUD4QC5V4SEOZAO6BS6KCYG5NQ","short_pith_number":"pith:UUD4QC5V","schema_version":"1.0","canonical_sha256":"a507c80bb5e488ec81de0cbca160dd6c2590629db513c4db91da5a6132249979","source":{"kind":"arxiv","id":"2605.17780","version":1},"attestation_state":"computed","paper":{"title":"Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingguo Liu, Dong Ye, Guodong Liu, Hang-Cheng Dong","submitted_at":"2026-05-18T02:59:33Z","abstract_excerpt":"Deep learning-based methods have become the de facto standard for industrial defect detection. However, their data-hungry nature and inherent \"black-box\" characteristics often lead to performance bottlenecks and limited trustworthiness in real-world applications. To address these challenges, this paper proposes a novel knowledge-guided loss function that seamlessly integrates model interpretability into the training process without incurring any additional inference cost. Our method operates in two phases: first, a primary classification network is trained, and its explanations, in the form of"},"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":"2605.17780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T02:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"1e39a7a854dba274e1f9bc39d7cd5db04f1eeb665ca99d01adf037ea03719018","abstract_canon_sha256":"133bf1ee2e4690bd5495e3e6569d59255666dcf3c703ff0e354b3c30b61ce29b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:57.858080Z","signature_b64":"CNVxH16yvSazv0wT19YxNOJwtzrwFQktRcKDCJEJ2nqvDYqXeAHcJj2kI7mFaDWzL9dBon6/2vSD62uunHDICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a507c80bb5e488ec81de0cbca160dd6c2590629db513c4db91da5a6132249979","last_reissued_at":"2026-05-20T00:04:57.857283Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:57.857283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingguo Liu, Dong Ye, Guodong Liu, Hang-Cheng Dong","submitted_at":"2026-05-18T02:59:33Z","abstract_excerpt":"Deep learning-based methods have become the de facto standard for industrial defect detection. However, their data-hungry nature and inherent \"black-box\" characteristics often lead to performance bottlenecks and limited trustworthiness in real-world applications. To address these challenges, this paper proposes a novel knowledge-guided loss function that seamlessly integrates model interpretability into the training process without incurring any additional inference cost. Our method operates in two phases: first, a primary classification network is trained, and its explanations, in the form of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17780","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/2605.17780/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":"2605.17780","created_at":"2026-05-20T00:04:57.857432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17780v1","created_at":"2026-05-20T00:04:57.857432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17780","created_at":"2026-05-20T00:04:57.857432+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUD4QC5V4SEO","created_at":"2026-05-20T00:04:57.857432+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUD4QC5V4SEOZAO6","created_at":"2026-05-20T00:04:57.857432+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUD4QC5V","created_at":"2026-05-20T00:04:57.857432+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/UUD4QC5V4SEOZAO6BS6KCYG5NQ","json":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ.json","graph_json":"https://pith.science/api/pith-number/UUD4QC5V4SEOZAO6BS6KCYG5NQ/graph.json","events_json":"https://pith.science/api/pith-number/UUD4QC5V4SEOZAO6BS6KCYG5NQ/events.json","paper":"https://pith.science/paper/UUD4QC5V"},"agent_actions":{"view_html":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ","download_json":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ.json","view_paper":"https://pith.science/paper/UUD4QC5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17780&json=true","fetch_graph":"https://pith.science/api/pith-number/UUD4QC5V4SEOZAO6BS6KCYG5NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UUD4QC5V4SEOZAO6BS6KCYG5NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ/action/storage_attestation","attest_author":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ/action/author_attestation","sign_citation":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ/action/citation_signature","submit_replication":"https://pith.science/pith/UUD4QC5V4SEOZAO6BS6KCYG5NQ/action/replication_record"}},"created_at":"2026-05-20T00:04:57.857432+00:00","updated_at":"2026-05-20T00:04:57.857432+00:00"}