{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LBMRNARFKIRDJ6K732BNIV2FP4","short_pith_number":"pith:LBMRNARF","schema_version":"1.0","canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","source":{"kind":"arxiv","id":"1803.02728","version":1},"attestation_state":"computed","paper":{"title":"Towards the Creation of a Large Corpus of Synthetically-Identified Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Peter Szolovits, Tristan Naumann, Willie Boag","submitted_at":"2018-03-07T15:51:11Z","abstract_excerpt":"Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as deidentification. Tools to automatically de-identify clinical notes are needed but are difficult to create without access to those very same notes containing PHI. This work presents a first step toward creating a large synthetically-identified corpus of clinical notes and corres"},"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":"1803.02728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T15:51:11Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"43a71cc4ab38fa2cc55be8461d6bec546edb415e4041754dafd4b49917d055c1","abstract_canon_sha256":"98a887bee06d1afa3b921b941930901fb996fb5dee855b85894ded093d887372"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:49.402942Z","signature_b64":"2mAZn+3QigjszJfhzdZ9SljethZxMkezMoCQ3QcuPqBMKZxpLLTeN0o5tzB/mZnoqOxSNQmvj72xalhmW2aZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5859168225522234f95fde82d457457f3b91dd1d632c141afe6f59f6ba15ce91","last_reissued_at":"2026-05-18T00:21:49.402289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:49.402289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards the Creation of a Large Corpus of Synthetically-Identified Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Peter Szolovits, Tristan Naumann, Willie Boag","submitted_at":"2018-03-07T15:51:11Z","abstract_excerpt":"Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as deidentification. Tools to automatically de-identify clinical notes are needed but are difficult to create without access to those very same notes containing PHI. This work presents a first step toward creating a large synthetically-identified corpus of clinical notes and corres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02728","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.02728","created_at":"2026-05-18T00:21:49.402402+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.02728v1","created_at":"2026-05-18T00:21:49.402402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02728","created_at":"2026-05-18T00:21:49.402402+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBMRNARFKIRD","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBMRNARFKIRDJ6K7","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBMRNARF","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4","json":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4.json","graph_json":"https://pith.science/api/pith-number/LBMRNARFKIRDJ6K732BNIV2FP4/graph.json","events_json":"https://pith.science/api/pith-number/LBMRNARFKIRDJ6K732BNIV2FP4/events.json","paper":"https://pith.science/paper/LBMRNARF"},"agent_actions":{"view_html":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4","download_json":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4.json","view_paper":"https://pith.science/paper/LBMRNARF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.02728&json=true","fetch_graph":"https://pith.science/api/pith-number/LBMRNARFKIRDJ6K732BNIV2FP4/graph.json","fetch_events":"https://pith.science/api/pith-number/LBMRNARFKIRDJ6K732BNIV2FP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/action/storage_attestation","attest_author":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/action/author_attestation","sign_citation":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/action/citation_signature","submit_replication":"https://pith.science/pith/LBMRNARFKIRDJ6K732BNIV2FP4/action/replication_record"}},"created_at":"2026-05-18T00:21:49.402402+00:00","updated_at":"2026-05-18T00:21:49.402402+00:00"}