{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HPX5BTB4IISMUW35KKOJ4OTLEW","short_pith_number":"pith:HPX5BTB4","schema_version":"1.0","canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","source":{"kind":"arxiv","id":"2410.01648","version":2},"attestation_state":"computed","paper":{"title":"DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angel Paul, Dhivin Shaji, Goran Nenadic, Lifeng Han, Suzan Verberne, Warren Del-Pinto","submitted_at":"2024-10-02T15:16:02Z","abstract_excerpt":"The increasing availability of sensitive textual data has created an urgent need for robust de-identification methods that enable compliant data sharing while preserving downstream utility. This paper presents DeID-Clinic, a multi-layered framework for automated pseudonymization and re-identification risk assessment of clinical free-text data. Our approach integrates domain-adapted transformer models, including BioBERT and ClinicalBERT, into the MASK de-identification framework to improve the detection and masking of protected health information (PHI). Beyond entity recognition, we introduce a"},"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":"2410.01648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"8ea129acd8aea566a43e2ae37787da49aefb492487e00c7c0db91fc73011fca4","abstract_canon_sha256":"145dfe7fbd2c00813fee4db3658e7493fa6e045fa068237a0b502c2dae1ccd52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:09.143119Z","signature_b64":"0Kis+XtJMjfL8cDDdhq1mMiiAKe7rql2XOLBAp+tdNe47PhyrCbqCc2c4qRIaeBMEIb+PsenEA4MEAEPg8MuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","last_reissued_at":"2026-05-26T01:03:09.142141Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:09.142141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angel Paul, Dhivin Shaji, Goran Nenadic, Lifeng Han, Suzan Verberne, Warren Del-Pinto","submitted_at":"2024-10-02T15:16:02Z","abstract_excerpt":"The increasing availability of sensitive textual data has created an urgent need for robust de-identification methods that enable compliant data sharing while preserving downstream utility. This paper presents DeID-Clinic, a multi-layered framework for automated pseudonymization and re-identification risk assessment of clinical free-text data. Our approach integrates domain-adapted transformer models, including BioBERT and ClinicalBERT, into the MASK de-identification framework to improve the detection and masking of protected health information (PHI). Beyond entity recognition, we introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01648","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/2410.01648/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":"2410.01648","created_at":"2026-05-26T01:03:09.142285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01648v2","created_at":"2026-05-26T01:03:09.142285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01648","created_at":"2026-05-26T01:03:09.142285+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPX5BTB4IISM","created_at":"2026-05-26T01:03:09.142285+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPX5BTB4IISMUW35","created_at":"2026-05-26T01:03:09.142285+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPX5BTB4","created_at":"2026-05-26T01:03:09.142285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.03399","citing_title":"Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW","json":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW.json","graph_json":"https://pith.science/api/pith-number/HPX5BTB4IISMUW35KKOJ4OTLEW/graph.json","events_json":"https://pith.science/api/pith-number/HPX5BTB4IISMUW35KKOJ4OTLEW/events.json","paper":"https://pith.science/paper/HPX5BTB4"},"agent_actions":{"view_html":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW","download_json":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW.json","view_paper":"https://pith.science/paper/HPX5BTB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01648&json=true","fetch_graph":"https://pith.science/api/pith-number/HPX5BTB4IISMUW35KKOJ4OTLEW/graph.json","fetch_events":"https://pith.science/api/pith-number/HPX5BTB4IISMUW35KKOJ4OTLEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/action/storage_attestation","attest_author":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/action/author_attestation","sign_citation":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/action/citation_signature","submit_replication":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/action/replication_record"}},"created_at":"2026-05-26T01:03:09.142285+00:00","updated_at":"2026-05-26T01:03:09.142285+00:00"}