{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E5AY2VAODCNYEDHVRVCMT35CEM","short_pith_number":"pith:E5AY2VAO","schema_version":"1.0","canonical_sha256":"27418d540e189b820cf58d44c9efa2233ee7adc44dbfd551a95260ba01d8437e","source":{"kind":"arxiv","id":"2504.14657","version":2},"attestation_state":"computed","paper":{"title":"A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Simon Lee, Yihan Lin, Zhirong Bella Yu","submitted_at":"2025-04-20T15:37:05Z","abstract_excerpt":"Synthetic Electronic Health Records (EHRs) offer a valuable opportunity to create privacy preserving and harmonized structured data, supporting numerous applications in healthcare. Key benefits of synthetic data include precise control over the data schema, improved fairness and representation of patient populations, and the ability to share datasets without concerns about compromising real individuals privacy. Consequently, the AI community has increasingly turned to Large Language Models (LLMs) to generate synthetic data across various domains. However, a significant challenge in healthcare "},"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":"2504.14657","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T15:37:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"042c4731af73f28456ad4cf8e924b46013bfdf18dceb387a1c36cdbe9221ebf5","abstract_canon_sha256":"ae968b71a503a8bcc1404c43087733566c095a5c4e94dd8583514084615955d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:54.518910Z","signature_b64":"P/r2N4KYXPudoeBxN1tuVKcrwJ3BcuKOSR4ROt9Ae1UsfufrxpUTLr8DnyScC2+bBbDZLB/xwLjxlscjLE3wBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27418d540e189b820cf58d44c9efa2233ee7adc44dbfd551a95260ba01d8437e","last_reissued_at":"2026-07-05T10:53:54.518372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:54.518372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Simon Lee, Yihan Lin, Zhirong Bella Yu","submitted_at":"2025-04-20T15:37:05Z","abstract_excerpt":"Synthetic Electronic Health Records (EHRs) offer a valuable opportunity to create privacy preserving and harmonized structured data, supporting numerous applications in healthcare. Key benefits of synthetic data include precise control over the data schema, improved fairness and representation of patient populations, and the ability to share datasets without concerns about compromising real individuals privacy. Consequently, the AI community has increasingly turned to Large Language Models (LLMs) to generate synthetic data across various domains. However, a significant challenge in healthcare "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14657","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.14657/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":"2504.14657","created_at":"2026-07-05T10:53:54.518431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14657v2","created_at":"2026-07-05T10:53:54.518431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14657","created_at":"2026-07-05T10:53:54.518431+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5AY2VAODCNY","created_at":"2026-07-05T10:53:54.518431+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5AY2VAODCNYEDHV","created_at":"2026-07-05T10:53:54.518431+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5AY2VAO","created_at":"2026-07-05T10:53:54.518431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.12261","citing_title":"Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM","json":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM.json","graph_json":"https://pith.science/api/pith-number/E5AY2VAODCNYEDHVRVCMT35CEM/graph.json","events_json":"https://pith.science/api/pith-number/E5AY2VAODCNYEDHVRVCMT35CEM/events.json","paper":"https://pith.science/paper/E5AY2VAO"},"agent_actions":{"view_html":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM","download_json":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM.json","view_paper":"https://pith.science/paper/E5AY2VAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14657&json=true","fetch_graph":"https://pith.science/api/pith-number/E5AY2VAODCNYEDHVRVCMT35CEM/graph.json","fetch_events":"https://pith.science/api/pith-number/E5AY2VAODCNYEDHVRVCMT35CEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM/action/storage_attestation","attest_author":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM/action/author_attestation","sign_citation":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM/action/citation_signature","submit_replication":"https://pith.science/pith/E5AY2VAODCNYEDHVRVCMT35CEM/action/replication_record"}},"created_at":"2026-07-05T10:53:54.518431+00:00","updated_at":"2026-07-05T10:53:54.518431+00:00"}