{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OQPONRCQZ6MVUDD7VDYTCZ3I7V","short_pith_number":"pith:OQPONRCQ","schema_version":"1.0","canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","source":{"kind":"arxiv","id":"2204.07056","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"cs.CL","authors_text":"Christopher Meaney, Rahim Moineddin, Sumeet Kalia, Wali Hakimpour","submitted_at":"2022-03-25T19:42:03Z","abstract_excerpt":"Objective: To comparatively evaluate several transformer model architectures at identifying protected health information (PHI) in the i2b2/UTHealth 2014 clinical text de-identification challenge corpus.\n  Methods: The i2b2/UTHealth 2014 corpus contains N=1304 clinical notes obtained from N=296 patients. Using a transfer learning framework, we fine-tune several transformer model architectures on the corpus, including: BERT-base, BERT-large, ROBERTA-base, ROBERTA-large, ALBERT-base and ALBERT-xxlarge. During fine-tuning we vary the following model hyper-parameters: batch size, number training ep"},"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":"2204.07056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:42:03Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"d090b05bbfac6483fdd650e3436dfdcde77b2379abc4742ad4a60007e7f88ba0","abstract_canon_sha256":"41df171659181a11c1af0de4a836b67f45efe23015e2346b7cb1e7ff2384dfbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:48.835676Z","signature_b64":"BXTI5chqfKHmy4ypWqixSsAMN4tPPl/THFf+AVkPoHRmOlX/vCf3TSYc2QizlPrJUKY9POcMqpCbazzWa+p7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741ee6c450cf995a0c7fa8f1316768fd4e7663985944204cf60d3f0d11e4f1bc","last_reissued_at":"2026-07-05T04:14:48.835215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:48.835215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Evaluation Of Transformer Models For De-Identification Of Clinical Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"cs.CL","authors_text":"Christopher Meaney, Rahim Moineddin, Sumeet Kalia, Wali Hakimpour","submitted_at":"2022-03-25T19:42:03Z","abstract_excerpt":"Objective: To comparatively evaluate several transformer model architectures at identifying protected health information (PHI) in the i2b2/UTHealth 2014 clinical text de-identification challenge corpus.\n  Methods: The i2b2/UTHealth 2014 corpus contains N=1304 clinical notes obtained from N=296 patients. Using a transfer learning framework, we fine-tune several transformer model architectures on the corpus, including: BERT-base, BERT-large, ROBERTA-base, ROBERTA-large, ALBERT-base and ALBERT-xxlarge. During fine-tuning we vary the following model hyper-parameters: batch size, number training ep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07056","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/2204.07056/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":"2204.07056","created_at":"2026-07-05T04:14:48.835272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.07056v1","created_at":"2026-07-05T04:14:48.835272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07056","created_at":"2026-07-05T04:14:48.835272+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQPONRCQZ6MV","created_at":"2026-07-05T04:14:48.835272+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQPONRCQZ6MVUDD7","created_at":"2026-07-05T04:14:48.835272+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQPONRCQ","created_at":"2026-07-05T04:14:48.835272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11376","citing_title":"From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V","json":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V.json","graph_json":"https://pith.science/api/pith-number/OQPONRCQZ6MVUDD7VDYTCZ3I7V/graph.json","events_json":"https://pith.science/api/pith-number/OQPONRCQZ6MVUDD7VDYTCZ3I7V/events.json","paper":"https://pith.science/paper/OQPONRCQ"},"agent_actions":{"view_html":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V","download_json":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V.json","view_paper":"https://pith.science/paper/OQPONRCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.07056&json=true","fetch_graph":"https://pith.science/api/pith-number/OQPONRCQZ6MVUDD7VDYTCZ3I7V/graph.json","fetch_events":"https://pith.science/api/pith-number/OQPONRCQZ6MVUDD7VDYTCZ3I7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/action/storage_attestation","attest_author":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/action/author_attestation","sign_citation":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/action/citation_signature","submit_replication":"https://pith.science/pith/OQPONRCQZ6MVUDD7VDYTCZ3I7V/action/replication_record"}},"created_at":"2026-07-05T04:14:48.835272+00:00","updated_at":"2026-07-05T04:14:48.835272+00:00"}