{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7CORJMXL2KYLSLAWTTQKRYICZU","short_pith_number":"pith:7CORJMXL","schema_version":"1.0","canonical_sha256":"f89d14b2ebd2b0b92c169ce0a8e102cd0d964c32f6103c8f790ea0ed8c941f59","source":{"kind":"arxiv","id":"2409.04975","version":1},"attestation_state":"computed","paper":{"title":"PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aayushman, Gagan Raj Gupta, Hemanth Gaddey, Manisha Chawla, Vidhi Mittal","submitted_at":"2024-09-08T05:00:37Z","abstract_excerpt":"Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions needs to be addressed before deploying them. We introduce a novel approach, PatchAlign, to enhance skin condition image classification accuracy and fairness by aligning with clinical text representations of skin conditions. PatchAlign uses Graph Optimal Transport (GOT) Loss as a regularizer to perform cross-domain alignment. The representations obtained are robust and generalize well across skin tones, even with limited training samples. To reduce the"},"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":"2409.04975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-08T05:00:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8441c4872a2b93af3956889c46ee2d9fd4e3f122e2d5460a9e84abe358fd226","abstract_canon_sha256":"ff11cabf9978433c8a084717fb684967892779bd0e569eeb54ab8ee486d503c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:42.395876Z","signature_b64":"QVOyqfc8GAkpIi05nFytRsNKCtQl99i2mXk0RPMMCsaKaa7OczSECz4nVD4XNmiuGzpdugyljGuJYUbq22TZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f89d14b2ebd2b0b92c169ce0a8e102cd0d964c32f6103c8f790ea0ed8c941f59","last_reissued_at":"2026-07-05T09:04:42.395465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:42.395465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aayushman, Gagan Raj Gupta, Hemanth Gaddey, Manisha Chawla, Vidhi Mittal","submitted_at":"2024-09-08T05:00:37Z","abstract_excerpt":"Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions needs to be addressed before deploying them. We introduce a novel approach, PatchAlign, to enhance skin condition image classification accuracy and fairness by aligning with clinical text representations of skin conditions. PatchAlign uses Graph Optimal Transport (GOT) Loss as a regularizer to perform cross-domain alignment. The representations obtained are robust and generalize well across skin tones, even with limited training samples. To reduce the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04975","kind":"arxiv","version":1},"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/2409.04975/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":"2409.04975","created_at":"2026-07-05T09:04:42.395530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04975v1","created_at":"2026-07-05T09:04:42.395530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04975","created_at":"2026-07-05T09:04:42.395530+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CORJMXL2KYL","created_at":"2026-07-05T09:04:42.395530+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CORJMXL2KYLSLAW","created_at":"2026-07-05T09:04:42.395530+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CORJMXL","created_at":"2026-07-05T09:04:42.395530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11627","citing_title":"Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regression","ref_index":1988,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU","json":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU.json","graph_json":"https://pith.science/api/pith-number/7CORJMXL2KYLSLAWTTQKRYICZU/graph.json","events_json":"https://pith.science/api/pith-number/7CORJMXL2KYLSLAWTTQKRYICZU/events.json","paper":"https://pith.science/paper/7CORJMXL"},"agent_actions":{"view_html":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU","download_json":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU.json","view_paper":"https://pith.science/paper/7CORJMXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04975&json=true","fetch_graph":"https://pith.science/api/pith-number/7CORJMXL2KYLSLAWTTQKRYICZU/graph.json","fetch_events":"https://pith.science/api/pith-number/7CORJMXL2KYLSLAWTTQKRYICZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU/action/storage_attestation","attest_author":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU/action/author_attestation","sign_citation":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU/action/citation_signature","submit_replication":"https://pith.science/pith/7CORJMXL2KYLSLAWTTQKRYICZU/action/replication_record"}},"created_at":"2026-07-05T09:04:42.395530+00:00","updated_at":"2026-07-05T09:04:42.395530+00:00"}