{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FAIHP4JK7NLYRFN32U53R3AFBN","short_pith_number":"pith:FAIHP4JK","schema_version":"1.0","canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","source":{"kind":"arxiv","id":"1906.05000","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arne K\\\"ohn, Chris Biemann, Gregor Wiedemann, Max Friedrich","submitted_at":"2019-06-12T08:29:24Z","abstract_excerpt":"De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHRs) to be shared for research. Automatic de-identification classifierscan significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works wellacross many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain 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":"1906.05000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T08:29:24Z","cross_cats_sorted":[],"title_canon_sha256":"a9dd86124a423a76deef40a4080447c81ea007d0635ec6ab57e6eff9d9cfa981","abstract_canon_sha256":"d08a469a122fd682df10ec40fab2719097f10b37de8932db6c11bf8df645ad07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.820764Z","signature_b64":"+nI9t5XHP+qEsLi9+cS0Ew3RyZHfuD9qWn44FKploe18JFWBWCTGts+30v7JRieATRJyiSkXOB5KyG3FJlTODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","last_reissued_at":"2026-05-17T23:43:29.820248Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.820248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arne K\\\"ohn, Chris Biemann, Gregor Wiedemann, Max Friedrich","submitted_at":"2019-06-12T08:29:24Z","abstract_excerpt":"De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHRs) to be shared for research. Automatic de-identification classifierscan significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works wellacross many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05000","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":""},"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":"1906.05000","created_at":"2026-05-17T23:43:29.820335+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05000v1","created_at":"2026-05-17T23:43:29.820335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05000","created_at":"2026-05-17T23:43:29.820335+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAIHP4JK7NLY","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAIHP4JK7NLYRFN3","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAIHP4JK","created_at":"2026-05-18T12:33:15.570797+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/FAIHP4JK7NLYRFN32U53R3AFBN","json":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN.json","graph_json":"https://pith.science/api/pith-number/FAIHP4JK7NLYRFN32U53R3AFBN/graph.json","events_json":"https://pith.science/api/pith-number/FAIHP4JK7NLYRFN32U53R3AFBN/events.json","paper":"https://pith.science/paper/FAIHP4JK"},"agent_actions":{"view_html":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN","download_json":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN.json","view_paper":"https://pith.science/paper/FAIHP4JK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05000&json=true","fetch_graph":"https://pith.science/api/pith-number/FAIHP4JK7NLYRFN32U53R3AFBN/graph.json","fetch_events":"https://pith.science/api/pith-number/FAIHP4JK7NLYRFN32U53R3AFBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/action/storage_attestation","attest_author":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/action/author_attestation","sign_citation":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/action/citation_signature","submit_replication":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/action/replication_record"}},"created_at":"2026-05-17T23:43:29.820335+00:00","updated_at":"2026-05-17T23:43:29.820335+00:00"}