{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZWNO53EWLJDIMWHL5HSMFDRJP3","short_pith_number":"pith:ZWNO53EW","schema_version":"1.0","canonical_sha256":"cd9aeeec965a468658ebe9e4c28e297ed47d84f4d65e9fbbb3f03c387539cbd8","source":{"kind":"arxiv","id":"2501.05617","version":1},"attestation_state":"computed","paper":{"title":"Datasheets for Healthcare AI: A Framework for Transparency and Bias Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CY","authors_text":"Harshvardhan J. Pandit, Marjia Siddik","submitted_at":"2025-01-09T23:36:34Z","abstract_excerpt":"The use of AI in healthcare has the potential to improve patient care, optimize clinical workflows, and enhance decision-making. However, bias, data incompleteness, and inaccuracies in training datasets can lead to unfair outcomes and amplify existing disparities. This research investigates the current state of dataset documentation practices, focusing on their ability to address these challenges and support ethical AI development. We identify shortcomings in existing documentation methods, which limit the recognition and mitigation of bias, incompleteness, and other issues in datasets. We pro"},"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":"2501.05617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-01-09T23:36:34Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"dbc2bfd21c010b9e842d49af856ab379f2930cf3afb5e847a9ebec17c4a2781c","abstract_canon_sha256":"d24c203a012901744f78112feca58419ec10c675df3dc3b731bd31d45ebb35c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:26.189146Z","signature_b64":"FkI54oA194Yxob/J+yvr1U1a1JsBfOmFc7t7Ha7HMj8M/yw8JRRaRjQ1Zl0jGvdV9A57fa3prvCnC1aR1vWpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd9aeeec965a468658ebe9e4c28e297ed47d84f4d65e9fbbb3f03c387539cbd8","last_reissued_at":"2026-07-05T09:59:26.188747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:26.188747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Datasheets for Healthcare AI: A Framework for Transparency and Bias Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CY","authors_text":"Harshvardhan J. Pandit, Marjia Siddik","submitted_at":"2025-01-09T23:36:34Z","abstract_excerpt":"The use of AI in healthcare has the potential to improve patient care, optimize clinical workflows, and enhance decision-making. However, bias, data incompleteness, and inaccuracies in training datasets can lead to unfair outcomes and amplify existing disparities. This research investigates the current state of dataset documentation practices, focusing on their ability to address these challenges and support ethical AI development. We identify shortcomings in existing documentation methods, which limit the recognition and mitigation of bias, incompleteness, and other issues in datasets. We pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05617","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/2501.05617/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":"2501.05617","created_at":"2026-07-05T09:59:26.188801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05617v1","created_at":"2026-07-05T09:59:26.188801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05617","created_at":"2026-07-05T09:59:26.188801+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWNO53EWLJDI","created_at":"2026-07-05T09:59:26.188801+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWNO53EWLJDIMWHL","created_at":"2026-07-05T09:59:26.188801+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWNO53EW","created_at":"2026-07-05T09:59:26.188801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10911","citing_title":"Ethical and Technical Limits of Deepfake Speech Datasets","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3","json":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3.json","graph_json":"https://pith.science/api/pith-number/ZWNO53EWLJDIMWHL5HSMFDRJP3/graph.json","events_json":"https://pith.science/api/pith-number/ZWNO53EWLJDIMWHL5HSMFDRJP3/events.json","paper":"https://pith.science/paper/ZWNO53EW"},"agent_actions":{"view_html":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3","download_json":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3.json","view_paper":"https://pith.science/paper/ZWNO53EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05617&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWNO53EWLJDIMWHL5HSMFDRJP3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWNO53EWLJDIMWHL5HSMFDRJP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3/action/storage_attestation","attest_author":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3/action/author_attestation","sign_citation":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3/action/citation_signature","submit_replication":"https://pith.science/pith/ZWNO53EWLJDIMWHL5HSMFDRJP3/action/replication_record"}},"created_at":"2026-07-05T09:59:26.188801+00:00","updated_at":"2026-07-05T09:59:26.188801+00:00"}