{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5RMKWPZVR6B6EZGQ2VCUGZV2KE","short_pith_number":"pith:5RMKWPZV","schema_version":"1.0","canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","source":{"kind":"arxiv","id":"2310.04468","version":1},"attestation_state":"computed","paper":{"title":"Validating transformers for redaction of text from electronic health records in real-world healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anoop D. Shah, Anthony Shek, Ewart Jonathan Sheldon, Haris Shuaib, James Teo, Joshua Au Yeung, Kawsar Noor, Mohammad Al-Agil, Richard Dobson, Xi Bai, Zeljko Kraljevic","submitted_at":"2023-10-05T19:10:18Z","abstract_excerpt":"Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across diffe"},"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":"2310.04468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T19:10:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"419d6f550b5f67ddfe4dec04ac7fa0c223227f724e801caa57e4045e1ae2abc5","abstract_canon_sha256":"71120c66f8e4ec98a5e375c9e82bbcccc6a2dc4f7cfbd19d7d211be5e4f7fabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:18.792517Z","signature_b64":"4EOej3YJy5m9lJgTZPPhCDtNVQUwejPilUdPzwAGwbkUFyOPuKv5Vpal1RwHwaN+UMemn0usjN90FxKVXmFHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec58ab3f358f83e264d0d5454366ba511e9f201b4f99f2cde6384e508428c8fd","last_reissued_at":"2026-07-05T06:58:18.792033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:18.792033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Validating transformers for redaction of text from electronic health records in real-world healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anoop D. Shah, Anthony Shek, Ewart Jonathan Sheldon, Haris Shuaib, James Teo, Joshua Au Yeung, Kawsar Noor, Mohammad Al-Agil, Richard Dobson, Xi Bai, Zeljko Kraljevic","submitted_at":"2023-10-05T19:10:18Z","abstract_excerpt":"Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04468","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/2310.04468/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":"2310.04468","created_at":"2026-07-05T06:58:18.792090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04468v1","created_at":"2026-07-05T06:58:18.792090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04468","created_at":"2026-07-05T06:58:18.792090+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RMKWPZVR6B6","created_at":"2026-07-05T06:58:18.792090+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RMKWPZVR6B6EZGQ","created_at":"2026-07-05T06:58:18.792090+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RMKWPZV","created_at":"2026-07-05T06:58:18.792090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03301","citing_title":"SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03301","citing_title":"SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE","json":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE.json","graph_json":"https://pith.science/api/pith-number/5RMKWPZVR6B6EZGQ2VCUGZV2KE/graph.json","events_json":"https://pith.science/api/pith-number/5RMKWPZVR6B6EZGQ2VCUGZV2KE/events.json","paper":"https://pith.science/paper/5RMKWPZV"},"agent_actions":{"view_html":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE","download_json":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE.json","view_paper":"https://pith.science/paper/5RMKWPZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04468&json=true","fetch_graph":"https://pith.science/api/pith-number/5RMKWPZVR6B6EZGQ2VCUGZV2KE/graph.json","fetch_events":"https://pith.science/api/pith-number/5RMKWPZVR6B6EZGQ2VCUGZV2KE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/action/storage_attestation","attest_author":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/action/author_attestation","sign_citation":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/action/citation_signature","submit_replication":"https://pith.science/pith/5RMKWPZVR6B6EZGQ2VCUGZV2KE/action/replication_record"}},"created_at":"2026-07-05T06:58:18.792090+00:00","updated_at":"2026-07-05T06:58:18.792090+00:00"}