{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IKR46L7ZFFM4F53DFDZVCIWFSL","short_pith_number":"pith:IKR46L7Z","schema_version":"1.0","canonical_sha256":"42a3cf2ff92959c2f76328f35122c592de328814184a569d94202909ffa47d37","source":{"kind":"arxiv","id":"2305.11348","version":2},"attestation_state":"computed","paper":{"title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CY"],"primary_cat":"cs.LG","authors_text":"Marzyeh Ghassemi, Shulammite Lim, Tom Joseph Pollard, Yuxin Xiao","submitted_at":"2023-05-18T23:47:00Z","abstract_excerpt":"Data sharing is crucial for open science and reproducible research, but the legal sharing of clinical data requires the removal of protected health information from electronic health records. This process, known as de-identification, is often achieved through the use of machine learning algorithms by many commercial and open-source systems. While these systems have shown compelling results on average, the variation in their performance across different demographic groups has not been thoroughly examined. In this work, we investigate the bias of de-identification systems on names in clinical no"},"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":"2305.11348","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:47:00Z","cross_cats_sorted":["cs.CL","cs.CR","cs.CY"],"title_canon_sha256":"ecbe23230adf4ebee6b74b26c503ccdcecb9948adc88147b49d52f64ccf08ab9","abstract_canon_sha256":"49df355dece36ad363dea3cc81257582d4d94e1013ecc8e00ca0e156c9917d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:38.588985Z","signature_b64":"XYwagXLT36SOwtg6mAGxuE9B/9gRNeAobEkiNOVTIIMb8CwNzqBorALuierq+g7xFexJ+OQk+v/Nuz7oD6YEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a3cf2ff92959c2f76328f35122c592de328814184a569d94202909ffa47d37","last_reissued_at":"2026-07-05T07:29:38.588578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:38.588578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CY"],"primary_cat":"cs.LG","authors_text":"Marzyeh Ghassemi, Shulammite Lim, Tom Joseph Pollard, Yuxin Xiao","submitted_at":"2023-05-18T23:47:00Z","abstract_excerpt":"Data sharing is crucial for open science and reproducible research, but the legal sharing of clinical data requires the removal of protected health information from electronic health records. This process, known as de-identification, is often achieved through the use of machine learning algorithms by many commercial and open-source systems. While these systems have shown compelling results on average, the variation in their performance across different demographic groups has not been thoroughly examined. In this work, we investigate the bias of de-identification systems on names in clinical no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11348","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/2305.11348/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":"2305.11348","created_at":"2026-07-05T07:29:38.588627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11348v2","created_at":"2026-07-05T07:29:38.588627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11348","created_at":"2026-07-05T07:29:38.588627+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKR46L7ZFFM4","created_at":"2026-07-05T07:29:38.588627+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKR46L7ZFFM4F53D","created_at":"2026-07-05T07:29:38.588627+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKR46L7Z","created_at":"2026-07-05T07:29:38.588627+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/IKR46L7ZFFM4F53DFDZVCIWFSL","json":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL.json","graph_json":"https://pith.science/api/pith-number/IKR46L7ZFFM4F53DFDZVCIWFSL/graph.json","events_json":"https://pith.science/api/pith-number/IKR46L7ZFFM4F53DFDZVCIWFSL/events.json","paper":"https://pith.science/paper/IKR46L7Z"},"agent_actions":{"view_html":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL","download_json":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL.json","view_paper":"https://pith.science/paper/IKR46L7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11348&json=true","fetch_graph":"https://pith.science/api/pith-number/IKR46L7ZFFM4F53DFDZVCIWFSL/graph.json","fetch_events":"https://pith.science/api/pith-number/IKR46L7ZFFM4F53DFDZVCIWFSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL/action/storage_attestation","attest_author":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL/action/author_attestation","sign_citation":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL/action/citation_signature","submit_replication":"https://pith.science/pith/IKR46L7ZFFM4F53DFDZVCIWFSL/action/replication_record"}},"created_at":"2026-07-05T07:29:38.588627+00:00","updated_at":"2026-07-05T07:29:38.588627+00:00"}