{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FAIHP4JK7NLYRFN32U53R3AFBN","short_pith_number":"pith:FAIHP4JK","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"},"canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","source":{"kind":"arxiv","id":"1906.05000","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05000","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05000v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05000","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"FAIHP4JK7NLY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAIHP4JK7NLYRFN3","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAIHP4JK","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FAIHP4JK7NLYRFN32U53R3AFBN","target":"record","payload":{"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"},"canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","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"},"source_kind":"arxiv","source_id":"1906.05000","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJS6xYAvXxb8etQ6/shjkC48MudCDoRnzhOc2RV3MTvcOMLWOIgi5bzxajjL44Ie71MaFflSDFCc4pfFXiaEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:23:34.678393Z"},"content_sha256":"8e362a976f2c6779d3715960b829ac1a31e4fc9ff95a2ac37483a5ea2bdec174","schema_version":"1.0","event_id":"sha256:8e362a976f2c6779d3715960b829ac1a31e4fc9ff95a2ac37483a5ea2bdec174"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FAIHP4JK7NLYRFN32U53R3AFBN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LtocDO8wubvaci6D4MvP/Z20tJsmvZL/MVKXEWo0YK1jZuHBFcsd+AdsE6ZQ8RbBe9iqktmVxj2Qs+5ave/cBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T08:23:34.678733Z"},"content_sha256":"7222618735fa7600b50a0bb6a1f02fa662eab922e0a95ed449d605c401305758","schema_version":"1.0","event_id":"sha256:7222618735fa7600b50a0bb6a1f02fa662eab922e0a95ed449d605c401305758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/bundle.json","state_url":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAIHP4JK7NLYRFN32U53R3AFBN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T08:23:34Z","links":{"resolver":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN","bundle":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/bundle.json","state":"https://pith.science/pith/FAIHP4JK7NLYRFN32U53R3AFBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAIHP4JK7NLYRFN32U53R3AFBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FAIHP4JK7NLYRFN32U53R3AFBN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d08a469a122fd682df10ec40fab2719097f10b37de8932db6c11bf8df645ad07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T08:29:24Z","title_canon_sha256":"a9dd86124a423a76deef40a4080447c81ea007d0635ec6ab57e6eff9d9cfa981"},"schema_version":"1.0","source":{"id":"1906.05000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05000","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05000v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05000","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"FAIHP4JK7NLY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAIHP4JK7NLYRFN3","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAIHP4JK","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:7222618735fa7600b50a0bb6a1f02fa662eab922e0a95ed449d605c401305758","target":"graph","created_at":"2026-05-17T23:43:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Arne K\\\"ohn, Chris Biemann, Gregor Wiedemann, Max Friedrich","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T08:29:24Z","title":"Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05000","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e362a976f2c6779d3715960b829ac1a31e4fc9ff95a2ac37483a5ea2bdec174","target":"record","created_at":"2026-05-17T23:43:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d08a469a122fd682df10ec40fab2719097f10b37de8932db6c11bf8df645ad07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T08:29:24Z","title_canon_sha256":"a9dd86124a423a76deef40a4080447c81ea007d0635ec6ab57e6eff9d9cfa981"},"schema_version":"1.0","source":{"id":"1906.05000","kind":"arxiv","version":1}},"canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"281077f12afb578895bbd53bb8ec050b60449fb9059504afa6437d08d6a28d0a","first_computed_at":"2026-05-17T23:43:29.820248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.820248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+nI9t5XHP+qEsLi9+cS0Ew3RyZHfuD9qWn44FKploe18JFWBWCTGts+30v7JRieATRJyiSkXOB5KyG3FJlTODA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.820764Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e362a976f2c6779d3715960b829ac1a31e4fc9ff95a2ac37483a5ea2bdec174","sha256:7222618735fa7600b50a0bb6a1f02fa662eab922e0a95ed449d605c401305758"],"state_sha256":"b401709eab82a6b8c8c227858ab30d54a843b2b3297c06494bd570296e865a6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rzjzPdjgUWuDT435E5vcFAcwtN5ffgKdsswFUgnKoz5WJ8gOZiYoY3VtiTujlqRlZPlpxekIh70JCjjf6apiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T08:23:34.680677Z","bundle_sha256":"453f64592bcc707256f540b4f57c892d9a993c41daa6a94464a01f90f4ad6aeb"}}