{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEA7WKUVRPE23WGYLA4KZCINUU","short_pith_number":"pith:YEA7WKUV","schema_version":"1.0","canonical_sha256":"c101fb2a958bc9add8d85838ac890da5109dc1afb4332ac35d33abc7c2061a85","source":{"kind":"arxiv","id":"2408.04396","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Impact of Pulse Oximetry Bias in Machine Learning under Counterfactual Thinking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Ian Wong, In\\^es Martins, Jaime S. Cardoso, Jo\\~ao Matos, Leo A. Celi, Tiago Gon\\c{c}alves","submitted_at":"2024-08-08T12:03:03Z","abstract_excerpt":"Algorithmic bias in healthcare mirrors existing data biases. However, the factors driving unfairness are not always known. Medical devices capture significant amounts of data but are prone to errors; for instance, pulse oximeters overestimate the arterial oxygen saturation of darker-skinned individuals, leading to worse outcomes. The impact of this bias in machine learning (ML) models remains unclear. This study addresses the technical challenges of quantifying the impact of medical device bias in downstream ML. Our experiments compare a \"perfect world\", without pulse oximetry bias, using SaO2"},"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":"2408.04396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T12:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"ba30c21e97fbeb6fa796ed7ff6f48d4be2c72a9d635dafbb1845fc9ba5b7b1d5","abstract_canon_sha256":"d9d5626b21ec97ab5ea8d60152fef3e281b30b1bf2787832ef9f81bd36b17f4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:32.705245Z","signature_b64":"qUWOd/KSms8k/O8PWrrE5xPtyTbgBDQDKvKPASMbv8KmW2dRT3U4yzbZl3pHAOjmKaoA66hpEL0KlEdYFfv6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c101fb2a958bc9add8d85838ac890da5109dc1afb4332ac35d33abc7c2061a85","last_reissued_at":"2026-07-05T08:53:32.704857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:32.704857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Impact of Pulse Oximetry Bias in Machine Learning under Counterfactual Thinking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Ian Wong, In\\^es Martins, Jaime S. Cardoso, Jo\\~ao Matos, Leo A. Celi, Tiago Gon\\c{c}alves","submitted_at":"2024-08-08T12:03:03Z","abstract_excerpt":"Algorithmic bias in healthcare mirrors existing data biases. However, the factors driving unfairness are not always known. Medical devices capture significant amounts of data but are prone to errors; for instance, pulse oximeters overestimate the arterial oxygen saturation of darker-skinned individuals, leading to worse outcomes. The impact of this bias in machine learning (ML) models remains unclear. This study addresses the technical challenges of quantifying the impact of medical device bias in downstream ML. Our experiments compare a \"perfect world\", without pulse oximetry bias, using SaO2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04396","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/2408.04396/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":"2408.04396","created_at":"2026-07-05T08:53:32.704917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04396v1","created_at":"2026-07-05T08:53:32.704917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04396","created_at":"2026-07-05T08:53:32.704917+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEA7WKUVRPE2","created_at":"2026-07-05T08:53:32.704917+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEA7WKUVRPE23WGY","created_at":"2026-07-05T08:53:32.704917+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEA7WKUV","created_at":"2026-07-05T08:53:32.704917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU","json":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU.json","graph_json":"https://pith.science/api/pith-number/YEA7WKUVRPE23WGYLA4KZCINUU/graph.json","events_json":"https://pith.science/api/pith-number/YEA7WKUVRPE23WGYLA4KZCINUU/events.json","paper":"https://pith.science/paper/YEA7WKUV"},"agent_actions":{"view_html":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU","download_json":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU.json","view_paper":"https://pith.science/paper/YEA7WKUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04396&json=true","fetch_graph":"https://pith.science/api/pith-number/YEA7WKUVRPE23WGYLA4KZCINUU/graph.json","fetch_events":"https://pith.science/api/pith-number/YEA7WKUVRPE23WGYLA4KZCINUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU/action/storage_attestation","attest_author":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU/action/author_attestation","sign_citation":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU/action/citation_signature","submit_replication":"https://pith.science/pith/YEA7WKUVRPE23WGYLA4KZCINUU/action/replication_record"}},"created_at":"2026-07-05T08:53:32.704917+00:00","updated_at":"2026-07-05T08:53:32.704917+00:00"}