{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YSX26JDFPRGV26W425BBWYNR4I","short_pith_number":"pith:YSX26JDF","schema_version":"1.0","canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","source":{"kind":"arxiv","id":"2507.03067","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models for Automating Clinical Data Standardization: HL7 FHIR Use Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alvaro Riquelme, Catalina Martinez, Pedro Costa","submitted_at":"2025-07-03T17:32:57Z","abstract_excerpt":"For years, semantic interoperability standards have sought to streamline the exchange of clinical data, yet their deployment remains time-consuming, resource-intensive, and technically challenging. To address this, we introduce a semi-automated approach that leverages large language models specifically GPT-4o and Llama 3.2 405b to convert structured clinical datasets into HL7 FHIR format while assessing accuracy, reliability, and security. Applying our method to the MIMIC-IV database, we combined embedding techniques, clustering algorithms, and semantic retrieval to craft prompts that guide th"},"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":"2507.03067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:32:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64a5d0299eb1b0279539328572bce088112ed74ba9e79c1451d8c141453ee112","abstract_canon_sha256":"0d8b66e3a92fb46cb4352383861828011169fe826d021ebf264a1af9f0debebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:52.032739Z","signature_b64":"vt7K75dF+1pB1QR9WqKCyKDiQoY0a8H5dxL35CoydW2s1hoHaYWbi9ot6wiqCizSoAypeK7a174NHZgTyebeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","last_reissued_at":"2026-07-05T11:31:52.032270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:52.032270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Automating Clinical Data Standardization: HL7 FHIR Use Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alvaro Riquelme, Catalina Martinez, Pedro Costa","submitted_at":"2025-07-03T17:32:57Z","abstract_excerpt":"For years, semantic interoperability standards have sought to streamline the exchange of clinical data, yet their deployment remains time-consuming, resource-intensive, and technically challenging. To address this, we introduce a semi-automated approach that leverages large language models specifically GPT-4o and Llama 3.2 405b to convert structured clinical datasets into HL7 FHIR format while assessing accuracy, reliability, and security. Applying our method to the MIMIC-IV database, we combined embedding techniques, clustering algorithms, and semantic retrieval to craft prompts that guide th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03067","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/2507.03067/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":"2507.03067","created_at":"2026-07-05T11:31:52.032333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03067v1","created_at":"2026-07-05T11:31:52.032333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03067","created_at":"2026-07-05T11:31:52.032333+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSX26JDFPRGV","created_at":"2026-07-05T11:31:52.032333+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSX26JDFPRGV26W4","created_at":"2026-07-05T11:31:52.032333+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSX26JDF","created_at":"2026-07-05T11:31:52.032333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I","json":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I.json","graph_json":"https://pith.science/api/pith-number/YSX26JDFPRGV26W425BBWYNR4I/graph.json","events_json":"https://pith.science/api/pith-number/YSX26JDFPRGV26W425BBWYNR4I/events.json","paper":"https://pith.science/paper/YSX26JDF"},"agent_actions":{"view_html":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I","download_json":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I.json","view_paper":"https://pith.science/paper/YSX26JDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03067&json=true","fetch_graph":"https://pith.science/api/pith-number/YSX26JDFPRGV26W425BBWYNR4I/graph.json","fetch_events":"https://pith.science/api/pith-number/YSX26JDFPRGV26W425BBWYNR4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/action/storage_attestation","attest_author":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/action/author_attestation","sign_citation":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/action/citation_signature","submit_replication":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/action/replication_record"}},"created_at":"2026-07-05T11:31:52.032333+00:00","updated_at":"2026-07-05T11:31:52.032333+00:00"}