{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5UQGOIMIYCRIROOSMW75UID7NF","short_pith_number":"pith:5UQGOIMI","schema_version":"1.0","canonical_sha256":"ed20672188c0a288b9d265bfda207f6979ecf2de67b35e7d21939c9574e261d0","source":{"kind":"arxiv","id":"2410.17035","version":1},"attestation_state":"computed","paper":{"title":"DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akhil Raj, Curtis L. Cole, John X. Morris, Ramin Zabih, Sri Laasya Nutheti, Thomas R. Campion, Yifan Peng","submitted_at":"2024-10-22T14:06:31Z","abstract_excerpt":"Sharing protected health information (PHI) is critical for furthering biomedical research. Before data can be distributed, practitioners often perform deidentification to remove any PHI contained in the text. Contemporary deidentification methods are evaluated on highly saturated datasets (tools achieve near-perfect accuracy) which may not reflect the full variability or complexity of real-world clinical text and annotating them is resource intensive, which is a barrier to real-world applications. To address this gap, we developed an adversarial approach using a large language model (LLM) to r"},"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":"2410.17035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T14:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"148c7501b54fb0c369473faeaca9c07011e38a82f3357c4e52ea85f6cf4e0fab","abstract_canon_sha256":"06868165b595d41d126208b1237d5435f2a060bd7acb715352bdada74e497107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:11.051559Z","signature_b64":"E/0ZIcXvciqO4R1VMLRdzELlu2Ek54SxoDVKz4ZXcM6OsF/2/Fx6enKiJ7X+/34zT9cc0m41iHC2wUuT3FZcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed20672188c0a288b9d265bfda207f6979ecf2de67b35e7d21939c9574e261d0","last_reissued_at":"2026-07-05T09:24:11.051013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:11.051013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akhil Raj, Curtis L. Cole, John X. Morris, Ramin Zabih, Sri Laasya Nutheti, Thomas R. Campion, Yifan Peng","submitted_at":"2024-10-22T14:06:31Z","abstract_excerpt":"Sharing protected health information (PHI) is critical for furthering biomedical research. Before data can be distributed, practitioners often perform deidentification to remove any PHI contained in the text. Contemporary deidentification methods are evaluated on highly saturated datasets (tools achieve near-perfect accuracy) which may not reflect the full variability or complexity of real-world clinical text and annotating them is resource intensive, which is a barrier to real-world applications. To address this gap, we developed an adversarial approach using a large language model (LLM) to r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17035","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/2410.17035/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":"2410.17035","created_at":"2026-07-05T09:24:11.051075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17035v1","created_at":"2026-07-05T09:24:11.051075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17035","created_at":"2026-07-05T09:24:11.051075+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UQGOIMIYCRI","created_at":"2026-07-05T09:24:11.051075+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UQGOIMIYCRIROOS","created_at":"2026-07-05T09:24:11.051075+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UQGOIMI","created_at":"2026-07-05T09:24:11.051075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00052","citing_title":"VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF","json":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF.json","graph_json":"https://pith.science/api/pith-number/5UQGOIMIYCRIROOSMW75UID7NF/graph.json","events_json":"https://pith.science/api/pith-number/5UQGOIMIYCRIROOSMW75UID7NF/events.json","paper":"https://pith.science/paper/5UQGOIMI"},"agent_actions":{"view_html":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF","download_json":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF.json","view_paper":"https://pith.science/paper/5UQGOIMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17035&json=true","fetch_graph":"https://pith.science/api/pith-number/5UQGOIMIYCRIROOSMW75UID7NF/graph.json","fetch_events":"https://pith.science/api/pith-number/5UQGOIMIYCRIROOSMW75UID7NF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF/action/storage_attestation","attest_author":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF/action/author_attestation","sign_citation":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF/action/citation_signature","submit_replication":"https://pith.science/pith/5UQGOIMIYCRIROOSMW75UID7NF/action/replication_record"}},"created_at":"2026-07-05T09:24:11.051075+00:00","updated_at":"2026-07-05T09:24:11.051075+00:00"}