{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2U2TB3SBVMKTYW4V7U56B2UHWB","short_pith_number":"pith:2U2TB3SB","schema_version":"1.0","canonical_sha256":"d53530ee41ab153c5b95fd3be0ea87b0569fa55f1adcd9ef29b85154f1c8f10c","source":{"kind":"arxiv","id":"1905.07002","version":2},"attestation_state":"computed","paper":{"title":"Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaitanya Shivade, Oren Melamud","submitted_at":"2019-05-16T19:14:18Z","abstract_excerpt":"Large-scale clinical data is invaluable to driving many computational scientific advances today. However, understandable concerns regarding patient privacy hinder the open dissemination of such data and give rise to suboptimal siloed research. De-identification methods attempt to address these concerns but were shown to be susceptible to adversarial attacks. In this work, we focus on the vast amounts of unstructured natural language data stored in clinical notes and propose to automatically generate synthetic clinical notes that are more amenable to sharing using generative models trained on 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":"1905.07002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T19:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"ae6704e49ca573c18cbb8799ac55973e8cb3d006bdea1ca34ef65358bbc1091c","abstract_canon_sha256":"904735bd194a2db89b98998517879e076a9442280cbe3a0f339dc2e601e871bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:25.634959Z","signature_b64":"XJv+PSWBsCjPRVSpCVTLFgTh5DwR/CW863+lJOUTAb7Q0J0Hl7lrX2DYrMueiJn3mRBiR2sYaLPPajFVGMqYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53530ee41ab153c5b95fd3be0ea87b0569fa55f1adcd9ef29b85154f1c8f10c","last_reissued_at":"2026-05-17T23:45:25.634507Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:25.634507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaitanya Shivade, Oren Melamud","submitted_at":"2019-05-16T19:14:18Z","abstract_excerpt":"Large-scale clinical data is invaluable to driving many computational scientific advances today. However, understandable concerns regarding patient privacy hinder the open dissemination of such data and give rise to suboptimal siloed research. De-identification methods attempt to address these concerns but were shown to be susceptible to adversarial attacks. In this work, we focus on the vast amounts of unstructured natural language data stored in clinical notes and propose to automatically generate synthetic clinical notes that are more amenable to sharing using generative models trained on r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07002","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":""},"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":"1905.07002","created_at":"2026-05-17T23:45:25.634585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07002v2","created_at":"2026-05-17T23:45:25.634585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07002","created_at":"2026-05-17T23:45:25.634585+00:00"},{"alias_kind":"pith_short_12","alias_value":"2U2TB3SBVMKT","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2U2TB3SBVMKTYW4V","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2U2TB3SB","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14079","citing_title":"DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB","json":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB.json","graph_json":"https://pith.science/api/pith-number/2U2TB3SBVMKTYW4V7U56B2UHWB/graph.json","events_json":"https://pith.science/api/pith-number/2U2TB3SBVMKTYW4V7U56B2UHWB/events.json","paper":"https://pith.science/paper/2U2TB3SB"},"agent_actions":{"view_html":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB","download_json":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB.json","view_paper":"https://pith.science/paper/2U2TB3SB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07002&json=true","fetch_graph":"https://pith.science/api/pith-number/2U2TB3SBVMKTYW4V7U56B2UHWB/graph.json","fetch_events":"https://pith.science/api/pith-number/2U2TB3SBVMKTYW4V7U56B2UHWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB/action/storage_attestation","attest_author":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB/action/author_attestation","sign_citation":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB/action/citation_signature","submit_replication":"https://pith.science/pith/2U2TB3SBVMKTYW4V7U56B2UHWB/action/replication_record"}},"created_at":"2026-05-17T23:45:25.634585+00:00","updated_at":"2026-05-17T23:45:25.634585+00:00"}