{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GATBTF2TR3B7G7ZW36ZN6ZCDM4","short_pith_number":"pith:GATBTF2T","schema_version":"1.0","canonical_sha256":"30261997538ec3f37f36dfb2df64436725f75df4b551bb3eff78fb9db82a3e73","source":{"kind":"arxiv","id":"2606.26879","version":1},"attestation_state":"computed","paper":{"title":"A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"William Poulett","submitted_at":"2026-06-25T11:08:40Z","abstract_excerpt":"Synthetic data is increasingly used to enable the development and evaluation of AI systems in domains where access to real-world data is restricted. In healthcare, clinical documentation presents particular challenges due to its sensitivity. This work introduces a synthetic clinical notes pipeline and dataset designed to support the development of clinical AI tools while avoiding the privacy risks associated with real patient data. The dataset is generated using a modular pipeline that combines structured patient generation, semi-structured patient journey simulation, and unstructured clinical"},"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":"2606.26879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T11:08:40Z","cross_cats_sorted":[],"title_canon_sha256":"c0b97768483e2d1aa60f0c0df4532ec4d50b2c32575f22fe3d24b7448cf39a6f","abstract_canon_sha256":"156041a5df7a8552e8ff154b4a399124540be123bed2ad4f36532679bc80660f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:02.792163Z","signature_b64":"CJ0meEOpwWRpCYLEU10dnvSfC31ptfpDwBOUo1dKIVvLfkamFzzXUD9xHH/lwQxBcJ3HM3owc3bh3NE0NCrRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30261997538ec3f37f36dfb2df64436725f75df4b551bb3eff78fb9db82a3e73","last_reissued_at":"2026-06-26T01:16:02.791748Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:02.791748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"William Poulett","submitted_at":"2026-06-25T11:08:40Z","abstract_excerpt":"Synthetic data is increasingly used to enable the development and evaluation of AI systems in domains where access to real-world data is restricted. In healthcare, clinical documentation presents particular challenges due to its sensitivity. This work introduces a synthetic clinical notes pipeline and dataset designed to support the development of clinical AI tools while avoiding the privacy risks associated with real patient data. The dataset is generated using a modular pipeline that combines structured patient generation, semi-structured patient journey simulation, and unstructured clinical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26879","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/2606.26879/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":"2606.26879","created_at":"2026-06-26T01:16:02.791802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26879v1","created_at":"2026-06-26T01:16:02.791802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26879","created_at":"2026-06-26T01:16:02.791802+00:00"},{"alias_kind":"pith_short_12","alias_value":"GATBTF2TR3B7","created_at":"2026-06-26T01:16:02.791802+00:00"},{"alias_kind":"pith_short_16","alias_value":"GATBTF2TR3B7G7ZW","created_at":"2026-06-26T01:16:02.791802+00:00"},{"alias_kind":"pith_short_8","alias_value":"GATBTF2T","created_at":"2026-06-26T01:16:02.791802+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/GATBTF2TR3B7G7ZW36ZN6ZCDM4","json":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4.json","graph_json":"https://pith.science/api/pith-number/GATBTF2TR3B7G7ZW36ZN6ZCDM4/graph.json","events_json":"https://pith.science/api/pith-number/GATBTF2TR3B7G7ZW36ZN6ZCDM4/events.json","paper":"https://pith.science/paper/GATBTF2T"},"agent_actions":{"view_html":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4","download_json":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4.json","view_paper":"https://pith.science/paper/GATBTF2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26879&json=true","fetch_graph":"https://pith.science/api/pith-number/GATBTF2TR3B7G7ZW36ZN6ZCDM4/graph.json","fetch_events":"https://pith.science/api/pith-number/GATBTF2TR3B7G7ZW36ZN6ZCDM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4/action/storage_attestation","attest_author":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4/action/author_attestation","sign_citation":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4/action/citation_signature","submit_replication":"https://pith.science/pith/GATBTF2TR3B7G7ZW36ZN6ZCDM4/action/replication_record"}},"created_at":"2026-06-26T01:16:02.791802+00:00","updated_at":"2026-06-26T01:16:02.791802+00:00"}