{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KSOP3FGLJPKW5Y2D4EBS4QNFTW","short_pith_number":"pith:KSOP3FGL","schema_version":"1.0","canonical_sha256":"549cfd94cb4bd56ee343e1032e41a59d93bc759bb89158fed3c3471bec4c7de8","source":{"kind":"arxiv","id":"2503.09969","version":2},"attestation_state":"computed","paper":{"title":"Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adarsh Subbaswamy, Ayah Zirikly, Keith Harrigian, Mathias Unberath, Mitchell Pavlak, Mohammad Mehdi Farhangi, Nathan Drenkow, Nicholas Petrick","submitted_at":"2025-03-13T02:16:48Z","abstract_excerpt":"Artificial Intelligence (AI) is now firmly at the center of evidence-based medicine. Despite many success stories that edge the path of AI's rise in healthcare, there are comparably many reports of significant shortcomings and unexpected behavior of AI in deployment. A major reason for these limitations is AI's reliance on association-based learning, where non-representative machine learning datasets can amplify latent bias during training and/or hide it during testing. To unlock new tools capable of foreseeing and preventing such AI bias issues, we present G-AUDIT. Generalized Attribute Utili"},"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":"2503.09969","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T02:16:48Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"95666a7d7feaafca1fc9004aabc70c7071e61523919d4625b3d75bd92fb9b1fb","abstract_canon_sha256":"a17751d072cadcebfeabaa616978a669fdb4e1c641955e3419000a7ab61e8671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:20.061362Z","signature_b64":"rDMa3G3GtnJobd7hNHITvItGh5GqISisVrWz10P79h/lOYD+DhkkVjHAc1Ql3UHpMQZZ9qm4xJovq7E4LS/VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"549cfd94cb4bd56ee343e1032e41a59d93bc759bb89158fed3c3471bec4c7de8","last_reissued_at":"2026-07-05T11:15:20.060806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:20.060806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adarsh Subbaswamy, Ayah Zirikly, Keith Harrigian, Mathias Unberath, Mitchell Pavlak, Mohammad Mehdi Farhangi, Nathan Drenkow, Nicholas Petrick","submitted_at":"2025-03-13T02:16:48Z","abstract_excerpt":"Artificial Intelligence (AI) is now firmly at the center of evidence-based medicine. Despite many success stories that edge the path of AI's rise in healthcare, there are comparably many reports of significant shortcomings and unexpected behavior of AI in deployment. A major reason for these limitations is AI's reliance on association-based learning, where non-representative machine learning datasets can amplify latent bias during training and/or hide it during testing. To unlock new tools capable of foreseeing and preventing such AI bias issues, we present G-AUDIT. Generalized Attribute Utili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09969","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/2503.09969/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":"2503.09969","created_at":"2026-07-05T11:15:20.060883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09969v2","created_at":"2026-07-05T11:15:20.060883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09969","created_at":"2026-07-05T11:15:20.060883+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSOP3FGLJPKW","created_at":"2026-07-05T11:15:20.060883+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSOP3FGLJPKW5Y2D","created_at":"2026-07-05T11:15:20.060883+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSOP3FGL","created_at":"2026-07-05T11:15:20.060883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.11906","citing_title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW","json":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW.json","graph_json":"https://pith.science/api/pith-number/KSOP3FGLJPKW5Y2D4EBS4QNFTW/graph.json","events_json":"https://pith.science/api/pith-number/KSOP3FGLJPKW5Y2D4EBS4QNFTW/events.json","paper":"https://pith.science/paper/KSOP3FGL"},"agent_actions":{"view_html":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW","download_json":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW.json","view_paper":"https://pith.science/paper/KSOP3FGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09969&json=true","fetch_graph":"https://pith.science/api/pith-number/KSOP3FGLJPKW5Y2D4EBS4QNFTW/graph.json","fetch_events":"https://pith.science/api/pith-number/KSOP3FGLJPKW5Y2D4EBS4QNFTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW/action/storage_attestation","attest_author":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW/action/author_attestation","sign_citation":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW/action/citation_signature","submit_replication":"https://pith.science/pith/KSOP3FGLJPKW5Y2D4EBS4QNFTW/action/replication_record"}},"created_at":"2026-07-05T11:15:20.060883+00:00","updated_at":"2026-07-05T11:15:20.060883+00:00"}