{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XV7AJNJILNLS5M2Z36VZ4K6MHW","short_pith_number":"pith:XV7AJNJI","schema_version":"1.0","canonical_sha256":"bd7e04b5285b572eb359dfab9e2bcc3d89ed2349569e686f275e608039a6182a","source":{"kind":"arxiv","id":"2103.04257","version":3},"attestation_state":"computed","paper":{"title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Huang, Errui Ding, Guodong Wang, Shumin Han","submitted_at":"2021-03-07T04:25:04Z","abstract_excerpt":"Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial"},"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":"2103.04257","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-07T04:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"e614b17724060aa5adcf9614e37e5a118730887a18bde4ac75bc1756997daf6d","abstract_canon_sha256":"3b5551997266a5ead5f87e9af8d2ea246607a534d7142ae123b54bc1403e2a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:39.580179Z","signature_b64":"bVJbPXMYmqD1X2o1K5YGrhNRHOgp/xL0PlNJyZ9wBSREwKUKj4dpI9Ok+v5mkAKtIWpWpnJr+ZwiGI72aFXkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd7e04b5285b572eb359dfab9e2bcc3d89ed2349569e686f275e608039a6182a","last_reissued_at":"2026-07-05T03:26:39.579673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:39.579673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Huang, Errui Ding, Guodong Wang, Shumin Han","submitted_at":"2021-03-07T04:25:04Z","abstract_excerpt":"Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04257","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/2103.04257/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":"2103.04257","created_at":"2026-07-05T03:26:39.579733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.04257v3","created_at":"2026-07-05T03:26:39.579733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04257","created_at":"2026-07-05T03:26:39.579733+00:00"},{"alias_kind":"pith_short_12","alias_value":"XV7AJNJILNLS","created_at":"2026-07-05T03:26:39.579733+00:00"},{"alias_kind":"pith_short_16","alias_value":"XV7AJNJILNLS5M2Z","created_at":"2026-07-05T03:26:39.579733+00:00"},{"alias_kind":"pith_short_8","alias_value":"XV7AJNJI","created_at":"2026-07-05T03:26:39.579733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22556","citing_title":"HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2405.02068","citing_title":"Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23766","citing_title":"Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12440","citing_title":"IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15291","citing_title":"AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW","json":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW.json","graph_json":"https://pith.science/api/pith-number/XV7AJNJILNLS5M2Z36VZ4K6MHW/graph.json","events_json":"https://pith.science/api/pith-number/XV7AJNJILNLS5M2Z36VZ4K6MHW/events.json","paper":"https://pith.science/paper/XV7AJNJI"},"agent_actions":{"view_html":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW","download_json":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW.json","view_paper":"https://pith.science/paper/XV7AJNJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.04257&json=true","fetch_graph":"https://pith.science/api/pith-number/XV7AJNJILNLS5M2Z36VZ4K6MHW/graph.json","fetch_events":"https://pith.science/api/pith-number/XV7AJNJILNLS5M2Z36VZ4K6MHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW/action/storage_attestation","attest_author":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW/action/author_attestation","sign_citation":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW/action/citation_signature","submit_replication":"https://pith.science/pith/XV7AJNJILNLS5M2Z36VZ4K6MHW/action/replication_record"}},"created_at":"2026-07-05T03:26:39.579733+00:00","updated_at":"2026-07-05T03:26:39.579733+00:00"}