{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FZDBOAZPUTDNFFBXL5QY2TNCSE","short_pith_number":"pith:FZDBOAZP","schema_version":"1.0","canonical_sha256":"2e4617032fa4c6d294375f618d4da29113a055b616dc075c3fae7fcd9977ba95","source":{"kind":"arxiv","id":"2409.07809","version":1},"attestation_state":"computed","paper":{"title":"Controllable Synthetic Clinical Note Generation with Privacy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron (Ari) Bornstein, Andre Manoel, Daniel Jones, Huseyin Inan, Robert Sim, Shize Su, Tal Baumel","submitted_at":"2024-09-12T07:38:34Z","abstract_excerpt":"In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit the availability and sharing of medical datasets, which poses a substantial challenge for researchers and practitioners aiming to develop advanced machine learning models. In this paper, we introduce a novel method to \"clone\" datasets containing PHI. Our approach ensures that the cloned datasets ret"},"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":"2409.07809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T07:38:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64dac78d53d86b13346e5f404313017294144585ad2d981ae05f76ebc1a2a4b3","abstract_canon_sha256":"7e5dcb30a6b47d2cc54734b11d55af5258b97b1fc36eb8b95df22e7b89e406ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:15.410481Z","signature_b64":"AKx6IrRGIUWbjpVa7y9gAgOvWOtW2bDnutNdsrXar8sIsa9JfC7F4boGCUR4uNGJjbPlTaTjtqESKiPVYaopDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e4617032fa4c6d294375f618d4da29113a055b616dc075c3fae7fcd9977ba95","last_reissued_at":"2026-07-05T09:06:15.410088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:15.410088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Synthetic Clinical Note Generation with Privacy Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron (Ari) Bornstein, Andre Manoel, Daniel Jones, Huseyin Inan, Robert Sim, Shize Su, Tal Baumel","submitted_at":"2024-09-12T07:38:34Z","abstract_excerpt":"In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit the availability and sharing of medical datasets, which poses a substantial challenge for researchers and practitioners aiming to develop advanced machine learning models. In this paper, we introduce a novel method to \"clone\" datasets containing PHI. Our approach ensures that the cloned datasets ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07809","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/2409.07809/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":"2409.07809","created_at":"2026-07-05T09:06:15.410141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07809v1","created_at":"2026-07-05T09:06:15.410141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07809","created_at":"2026-07-05T09:06:15.410141+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZDBOAZPUTDN","created_at":"2026-07-05T09:06:15.410141+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZDBOAZPUTDNFFBX","created_at":"2026-07-05T09:06:15.410141+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZDBOAZP","created_at":"2026-07-05T09:06:15.410141+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/FZDBOAZPUTDNFFBXL5QY2TNCSE","json":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE.json","graph_json":"https://pith.science/api/pith-number/FZDBOAZPUTDNFFBXL5QY2TNCSE/graph.json","events_json":"https://pith.science/api/pith-number/FZDBOAZPUTDNFFBXL5QY2TNCSE/events.json","paper":"https://pith.science/paper/FZDBOAZP"},"agent_actions":{"view_html":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE","download_json":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE.json","view_paper":"https://pith.science/paper/FZDBOAZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07809&json=true","fetch_graph":"https://pith.science/api/pith-number/FZDBOAZPUTDNFFBXL5QY2TNCSE/graph.json","fetch_events":"https://pith.science/api/pith-number/FZDBOAZPUTDNFFBXL5QY2TNCSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE/action/storage_attestation","attest_author":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE/action/author_attestation","sign_citation":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE/action/citation_signature","submit_replication":"https://pith.science/pith/FZDBOAZPUTDNFFBXL5QY2TNCSE/action/replication_record"}},"created_at":"2026-07-05T09:06:15.410141+00:00","updated_at":"2026-07-05T09:06:15.410141+00:00"}