{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QF3MS5JLKQXCFNWIPKB57QHKIL","short_pith_number":"pith:QF3MS5JL","schema_version":"1.0","canonical_sha256":"8176c9752b542e22b6c87a83dfc0ea42e55d25ab2a792b8d8cc8c4542aacfbfe","source":{"kind":"arxiv","id":"2103.03423","version":2},"attestation_state":"computed","paper":{"title":"Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengbei Liu, Guansong Pang, Gustavo Carneiro, Johan W. Verjans, Rajvinder Singh, Seon Ho Shin, Yuanhong Chen, Yu Tian","submitted_at":"2021-03-05T01:56:58Z","abstract_excerpt":"Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potential"},"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":"2103.03423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T01:56:58Z","cross_cats_sorted":[],"title_canon_sha256":"9b8b6058b4e7e335c38e3320b6ae2d07c95b396b1627a52362bd4337357eebb7","abstract_canon_sha256":"cee993ddff697c48be2fb60232aa84969b7d73ad9b5eac74639a4cd3ad23aa8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:56.142627Z","signature_b64":"wfR0uDsfMSOIqbfmSlp6apFtxrkmSc/wkGzOBR03RJt0/NU7Or2rgp14qeP4EPPS8uPF3UJq3vK3mGSwUIxfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8176c9752b542e22b6c87a83dfc0ea42e55d25ab2a792b8d8cc8c4542aacfbfe","last_reissued_at":"2026-07-05T02:53:56.142198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:56.142198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengbei Liu, Guansong Pang, Gustavo Carneiro, Johan W. Verjans, Rajvinder Singh, Seon Ho Shin, Yuanhong Chen, Yu Tian","submitted_at":"2021-03-05T01:56:58Z","abstract_excerpt":"Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potential"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03423","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/2103.03423/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":"2103.03423","created_at":"2026-07-05T02:53:56.142258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03423v2","created_at":"2026-07-05T02:53:56.142258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03423","created_at":"2026-07-05T02:53:56.142258+00:00"},{"alias_kind":"pith_short_12","alias_value":"QF3MS5JLKQXC","created_at":"2026-07-05T02:53:56.142258+00:00"},{"alias_kind":"pith_short_16","alias_value":"QF3MS5JLKQXCFNWI","created_at":"2026-07-05T02:53:56.142258+00:00"},{"alias_kind":"pith_short_8","alias_value":"QF3MS5JL","created_at":"2026-07-05T02:53:56.142258+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/QF3MS5JLKQXCFNWIPKB57QHKIL","json":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL.json","graph_json":"https://pith.science/api/pith-number/QF3MS5JLKQXCFNWIPKB57QHKIL/graph.json","events_json":"https://pith.science/api/pith-number/QF3MS5JLKQXCFNWIPKB57QHKIL/events.json","paper":"https://pith.science/paper/QF3MS5JL"},"agent_actions":{"view_html":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL","download_json":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL.json","view_paper":"https://pith.science/paper/QF3MS5JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03423&json=true","fetch_graph":"https://pith.science/api/pith-number/QF3MS5JLKQXCFNWIPKB57QHKIL/graph.json","fetch_events":"https://pith.science/api/pith-number/QF3MS5JLKQXCFNWIPKB57QHKIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL/action/storage_attestation","attest_author":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL/action/author_attestation","sign_citation":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL/action/citation_signature","submit_replication":"https://pith.science/pith/QF3MS5JLKQXCFNWIPKB57QHKIL/action/replication_record"}},"created_at":"2026-07-05T02:53:56.142258+00:00","updated_at":"2026-07-05T02:53:56.142258+00:00"}