{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7UQ4FJNTRNQEBNDCFRTGNMYMFM","short_pith_number":"pith:7UQ4FJNT","schema_version":"1.0","canonical_sha256":"fd21c2a5b38b6040b4622c6666b30c2b0babc2c5e24e2428f51be118029f84c5","source":{"kind":"arxiv","id":"2310.05055","version":3},"attestation_state":"computed","paper":{"title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ondrej Bohdal, Raman Dutt, Sotirios A. Tsaftaris, Timothy Hospedales","submitted_at":"2023-10-08T07:41:15Z","abstract_excerpt":"Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to minimise demographic bias in AI, this problem remains challenging. A key reason for this challenge is the fairness generalisation gap: High-capacity deep learning models can fit all training data nearly perfectly, and thus also exhibit perfect fairness during training. In this case, bias emerges only during testing when generalisation performance differs across subgroups. This motivates us to take a bi-level optimisation"},"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":"2310.05055","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T07:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"a7bf2f40a64408b1c1834403bbe9c59d8ecf19f632b8f12730d6bf487576b7d8","abstract_canon_sha256":"a84d5031edf620876603903bf51aff7a3400c4d04039760e12bd7e88dc9398e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:35.733709Z","signature_b64":"+C4FIHdtb/LJtBTYUvtUUKRH60Aq2DVl9CGGwRDmoRwqwv5VPl0ongwQWyYGhUvdXGUySMZ8HRXDNyrhRvi5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd21c2a5b38b6040b4622c6666b30c2b0babc2c5e24e2428f51be118029f84c5","last_reissued_at":"2026-07-05T07:34:35.733233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:35.733233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ondrej Bohdal, Raman Dutt, Sotirios A. Tsaftaris, Timothy Hospedales","submitted_at":"2023-10-08T07:41:15Z","abstract_excerpt":"Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to minimise demographic bias in AI, this problem remains challenging. A key reason for this challenge is the fairness generalisation gap: High-capacity deep learning models can fit all training data nearly perfectly, and thus also exhibit perfect fairness during training. In this case, bias emerges only during testing when generalisation performance differs across subgroups. This motivates us to take a bi-level optimisation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05055","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/2310.05055/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":"2310.05055","created_at":"2026-07-05T07:34:35.733305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05055v3","created_at":"2026-07-05T07:34:35.733305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05055","created_at":"2026-07-05T07:34:35.733305+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UQ4FJNTRNQE","created_at":"2026-07-05T07:34:35.733305+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UQ4FJNTRNQEBNDC","created_at":"2026-07-05T07:34:35.733305+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UQ4FJNT","created_at":"2026-07-05T07:34:35.733305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11939","citing_title":"Fair Distillation: Teaching Fairness from Biased Teachers in Medical Imaging","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM","json":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM.json","graph_json":"https://pith.science/api/pith-number/7UQ4FJNTRNQEBNDCFRTGNMYMFM/graph.json","events_json":"https://pith.science/api/pith-number/7UQ4FJNTRNQEBNDCFRTGNMYMFM/events.json","paper":"https://pith.science/paper/7UQ4FJNT"},"agent_actions":{"view_html":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM","download_json":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM.json","view_paper":"https://pith.science/paper/7UQ4FJNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05055&json=true","fetch_graph":"https://pith.science/api/pith-number/7UQ4FJNTRNQEBNDCFRTGNMYMFM/graph.json","fetch_events":"https://pith.science/api/pith-number/7UQ4FJNTRNQEBNDCFRTGNMYMFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM/action/storage_attestation","attest_author":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM/action/author_attestation","sign_citation":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM/action/citation_signature","submit_replication":"https://pith.science/pith/7UQ4FJNTRNQEBNDCFRTGNMYMFM/action/replication_record"}},"created_at":"2026-07-05T07:34:35.733305+00:00","updated_at":"2026-07-05T07:34:35.733305+00:00"}