{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WP75UYSLJFE3LQGZJKUHMWW4DX","short_pith_number":"pith:WP75UYSL","schema_version":"1.0","canonical_sha256":"b3ffda624b4949b5c0d94aa8765adc1dcae520e9b2a273f9a58752f38e61e595","source":{"kind":"arxiv","id":"2209.13476","version":6},"attestation_state":"computed","paper":{"title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chenyu You, David A. Clifton, Fenglin Liu, James S. Duncan, Lawrence Staib, Nicha C. Dvornek, Weicheng Dai, Xiaoxiao Li, Yifei Min","submitted_at":"2022-09-27T15:50:31Z","abstract_excerpt":"Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping. However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent ana"},"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":"2209.13476","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2022-09-27T15:50:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"e4008b0ac60da1facbe483bbf92d7c47ea775e46544a34fed8c69ae526ffdc42","abstract_canon_sha256":"d9bba019a10ca9ae6a143fbe8c4f57f520e8a7ef23c65362e870f435ec4f06a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:49.329436Z","signature_b64":"k594u3zu3gP3Jv4VuUB+9eIWU7zibHHl6unU7dIk6uYQlIkbyfiFRodUuX2ma10eQvyaRHSkgpNHMEs1A0CrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ffda624b4949b5c0d94aa8765adc1dcae520e9b2a273f9a58752f38e61e595","last_reissued_at":"2026-07-05T09:09:49.328950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:49.328950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chenyu You, David A. Clifton, Fenglin Liu, James S. Duncan, Lawrence Staib, Nicha C. Dvornek, Weicheng Dai, Xiaoxiao Li, Yifei Min","submitted_at":"2022-09-27T15:50:31Z","abstract_excerpt":"Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping. However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13476","kind":"arxiv","version":6},"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/2209.13476/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":"2209.13476","created_at":"2026-07-05T09:09:49.329007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13476v6","created_at":"2026-07-05T09:09:49.329007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13476","created_at":"2026-07-05T09:09:49.329007+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP75UYSLJFE3","created_at":"2026-07-05T09:09:49.329007+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP75UYSLJFE3LQGZ","created_at":"2026-07-05T09:09:49.329007+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP75UYSL","created_at":"2026-07-05T09:09:49.329007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12105","citing_title":"Out-of-distribution data supervision towards biomedical semantic segmentation","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX","json":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX.json","graph_json":"https://pith.science/api/pith-number/WP75UYSLJFE3LQGZJKUHMWW4DX/graph.json","events_json":"https://pith.science/api/pith-number/WP75UYSLJFE3LQGZJKUHMWW4DX/events.json","paper":"https://pith.science/paper/WP75UYSL"},"agent_actions":{"view_html":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX","download_json":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX.json","view_paper":"https://pith.science/paper/WP75UYSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13476&json=true","fetch_graph":"https://pith.science/api/pith-number/WP75UYSLJFE3LQGZJKUHMWW4DX/graph.json","fetch_events":"https://pith.science/api/pith-number/WP75UYSLJFE3LQGZJKUHMWW4DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX/action/storage_attestation","attest_author":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX/action/author_attestation","sign_citation":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX/action/citation_signature","submit_replication":"https://pith.science/pith/WP75UYSLJFE3LQGZJKUHMWW4DX/action/replication_record"}},"created_at":"2026-07-05T09:09:49.329007+00:00","updated_at":"2026-07-05T09:09:49.329007+00:00"}