{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RKF7PDWXRZLTDHATFHGOGMLQCF","short_pith_number":"pith:RKF7PDWX","schema_version":"1.0","canonical_sha256":"8a8bf78ed78e57319c1329cce331701144c2fb6092d15a9b899f0fec0b5e91a2","source":{"kind":"arxiv","id":"2403.09303","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Kwang-Ting Cheng, Yu Cai","submitted_at":"2024-03-14T11:51:01Z","abstract_excerpt":"Medical anomaly detection aims to identify abnormal findings using only normal training data, playing a crucial role in health screening and recognizing rare diseases. Reconstruction-based methods, particularly those utilizing autoencoders (AEs), are dominant in this field. They work under the assumption that AEs trained on only normal data cannot reconstruct unseen abnormal regions well, thereby enabling the anomaly detection based on reconstruction errors. However, this assumption does not always hold due to the mismatch between the reconstruction training objective and the anomaly detection"},"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":"2403.09303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T11:51:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1c5220403bd22a9067b4db4fa18de57ef8b6db5b868ff4c68feea6551c1ced93","abstract_canon_sha256":"9606dbadae517c606db0495eeb1cdec402202871e9b4e328525025e0750859a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:44.030939Z","signature_b64":"Cr8pIFH+LIJmSFVeSj74XbdlYVb9+bXPTlEB2NHzO683gPJisJNiYi9kBIVXpx8E89TxMV06zMZQoz3iBSiLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a8bf78ed78e57319c1329cce331701144c2fb6092d15a9b899f0fec0b5e91a2","last_reissued_at":"2026-07-05T08:41:44.030411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:44.030411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Kwang-Ting Cheng, Yu Cai","submitted_at":"2024-03-14T11:51:01Z","abstract_excerpt":"Medical anomaly detection aims to identify abnormal findings using only normal training data, playing a crucial role in health screening and recognizing rare diseases. Reconstruction-based methods, particularly those utilizing autoencoders (AEs), are dominant in this field. They work under the assumption that AEs trained on only normal data cannot reconstruct unseen abnormal regions well, thereby enabling the anomaly detection based on reconstruction errors. However, this assumption does not always hold due to the mismatch between the reconstruction training objective and the anomaly detection"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09303","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/2403.09303/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":"2403.09303","created_at":"2026-07-05T08:41:44.030481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09303v3","created_at":"2026-07-05T08:41:44.030481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09303","created_at":"2026-07-05T08:41:44.030481+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKF7PDWXRZLT","created_at":"2026-07-05T08:41:44.030481+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKF7PDWXRZLTDHAT","created_at":"2026-07-05T08:41:44.030481+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKF7PDWX","created_at":"2026-07-05T08:41:44.030481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14515","citing_title":"Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF","json":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF.json","graph_json":"https://pith.science/api/pith-number/RKF7PDWXRZLTDHATFHGOGMLQCF/graph.json","events_json":"https://pith.science/api/pith-number/RKF7PDWXRZLTDHATFHGOGMLQCF/events.json","paper":"https://pith.science/paper/RKF7PDWX"},"agent_actions":{"view_html":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF","download_json":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF.json","view_paper":"https://pith.science/paper/RKF7PDWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09303&json=true","fetch_graph":"https://pith.science/api/pith-number/RKF7PDWXRZLTDHATFHGOGMLQCF/graph.json","fetch_events":"https://pith.science/api/pith-number/RKF7PDWXRZLTDHATFHGOGMLQCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF/action/storage_attestation","attest_author":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF/action/author_attestation","sign_citation":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF/action/citation_signature","submit_replication":"https://pith.science/pith/RKF7PDWXRZLTDHATFHGOGMLQCF/action/replication_record"}},"created_at":"2026-07-05T08:41:44.030481+00:00","updated_at":"2026-07-05T08:41:44.030481+00:00"}