{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OBI57LO2PMHI3LHNK7CSRQRNUO","short_pith_number":"pith:OBI57LO2","schema_version":"1.0","canonical_sha256":"7051dfadda7b0e8daced57c528c22da3accb84b7250d0127336944fc9f63d7f1","source":{"kind":"arxiv","id":"2210.07829","version":2},"attestation_state":"computed","paper":{"title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bastian Wandt, Bodo Rosenhahn, Marco Rudolph, Tom Wehrbein","submitted_at":"2022-10-14T13:56:50Z","abstract_excerpt":"Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is available. This work discovers previously unknown problems of student-teacher approaches for AD and proposes a solution, where two neural networks are trained to produce the same output for the defect-free training examples. The core assumption of student-teacher networks is that the distance between the outputs of both networks is larger for anomalies since they are absent in training. However, previous methods suffer from the similarity 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":"2210.07829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-14T13:56:50Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"75b3794f1b3cd81dc6e6e3706b2f9f969a6a8206b03adbf0386dafe8ca46aaa7","abstract_canon_sha256":"584f5b8c55861bc6fc87185f2c6a84a7f1c5b7c2fbd6eeaa46b8ff91959408c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:55.271763Z","signature_b64":"wv+GzJIm67ar37sKMlIpN68fTDC/UYDqatwBZVKoh24Rd9jTwhw6bcQRbZvDZSrVHBMo55HedwyFVNaMQIUSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7051dfadda7b0e8daced57c528c22da3accb84b7250d0127336944fc9f63d7f1","last_reissued_at":"2026-07-05T05:07:55.271404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:55.271404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bastian Wandt, Bodo Rosenhahn, Marco Rudolph, Tom Wehrbein","submitted_at":"2022-10-14T13:56:50Z","abstract_excerpt":"Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is available. This work discovers previously unknown problems of student-teacher approaches for AD and proposes a solution, where two neural networks are trained to produce the same output for the defect-free training examples. The core assumption of student-teacher networks is that the distance between the outputs of both networks is larger for anomalies since they are absent in training. However, previous methods suffer from the similarity of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07829","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/2210.07829/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":"2210.07829","created_at":"2026-07-05T05:07:55.271460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07829v2","created_at":"2026-07-05T05:07:55.271460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07829","created_at":"2026-07-05T05:07:55.271460+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBI57LO2PMHI","created_at":"2026-07-05T05:07:55.271460+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBI57LO2PMHI3LHN","created_at":"2026-07-05T05:07:55.271460+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBI57LO2","created_at":"2026-07-05T05:07:55.271460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13461","citing_title":"Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO","json":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO.json","graph_json":"https://pith.science/api/pith-number/OBI57LO2PMHI3LHNK7CSRQRNUO/graph.json","events_json":"https://pith.science/api/pith-number/OBI57LO2PMHI3LHNK7CSRQRNUO/events.json","paper":"https://pith.science/paper/OBI57LO2"},"agent_actions":{"view_html":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO","download_json":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO.json","view_paper":"https://pith.science/paper/OBI57LO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07829&json=true","fetch_graph":"https://pith.science/api/pith-number/OBI57LO2PMHI3LHNK7CSRQRNUO/graph.json","fetch_events":"https://pith.science/api/pith-number/OBI57LO2PMHI3LHNK7CSRQRNUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO/action/storage_attestation","attest_author":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO/action/author_attestation","sign_citation":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO/action/citation_signature","submit_replication":"https://pith.science/pith/OBI57LO2PMHI3LHNK7CSRQRNUO/action/replication_record"}},"created_at":"2026-07-05T05:07:55.271460+00:00","updated_at":"2026-07-05T05:07:55.271460+00:00"}