{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YSX26JDFPRGV26W425BBWYNR4I","short_pith_number":"pith:YSX26JDF","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"},"canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","source":{"kind":"arxiv","id":"2507.03067","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03067","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03067v1","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03067","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"YSX26JDFPRGV","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"YSX26JDFPRGV26W4","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"YSX26JDF","created_at":"2026-07-05T11:31:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YSX26JDFPRGV26W425BBWYNR4I","target":"record","payload":{"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"},"canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","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"},"source_kind":"arxiv","source_id":"2507.03067","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DBH6IzsSgMI5dcXLMzu8AYcIU6nY2yDBWY1eZPZHw1pXZAErXzncP1kt/5J2or+TgGNsEEZZ1ZfGbxLZeMyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:59.701189Z"},"content_sha256":"10a9d6dea3080cc1b8a4c54fda31706ea215f366e5359a45b37dc360725c64da","schema_version":"1.0","event_id":"sha256:10a9d6dea3080cc1b8a4c54fda31706ea215f366e5359a45b37dc360725c64da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YSX26JDFPRGV26W425BBWYNR4I","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"btnrKcxwN2VrtTApHCwfej/CusTZatLVuJE2jJV9PxOwBiBf+cWaFN2sYw7bDwQ/0CmVj9TaqO0rgvhR4xRIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:59.701692Z"},"content_sha256":"1744578777860f07d01fdd72daa7cb1b25ebc07bc1bfbea9449ac1efced94776","schema_version":"1.0","event_id":"sha256:1744578777860f07d01fdd72daa7cb1b25ebc07bc1bfbea9449ac1efced94776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/bundle.json","state_url":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSX26JDFPRGV26W425BBWYNR4I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T06:58:59Z","links":{"resolver":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I","bundle":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/bundle.json","state":"https://pith.science/pith/YSX26JDFPRGV26W425BBWYNR4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSX26JDFPRGV26W425BBWYNR4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YSX26JDFPRGV26W425BBWYNR4I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0d8b66e3a92fb46cb4352383861828011169fe826d021ebf264a1af9f0debebd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:32:57Z","title_canon_sha256":"64a5d0299eb1b0279539328572bce088112ed74ba9e79c1451d8c141453ee112"},"schema_version":"1.0","source":{"id":"2507.03067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03067","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03067v1","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03067","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"YSX26JDFPRGV","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"YSX26JDFPRGV26W4","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"YSX26JDF","created_at":"2026-07-05T11:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:1744578777860f07d01fdd72daa7cb1b25ebc07bc1bfbea9449ac1efced94776","target":"graph","created_at":"2026-07-05T11:31:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.03067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alvaro Riquelme, Catalina Martinez, Pedro Costa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:32:57Z","title":"Large Language Models for Automating Clinical Data Standardization: HL7 FHIR Use Case"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03067","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:10a9d6dea3080cc1b8a4c54fda31706ea215f366e5359a45b37dc360725c64da","target":"record","created_at":"2026-07-05T11:31:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0d8b66e3a92fb46cb4352383861828011169fe826d021ebf264a1af9f0debebd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:32:57Z","title_canon_sha256":"64a5d0299eb1b0279539328572bce088112ed74ba9e79c1451d8c141453ee112"},"schema_version":"1.0","source":{"id":"2507.03067","kind":"arxiv","version":1}},"canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4afaf24657c4d5d7adcd7421b61b1e234ed883296672adbdea3e485023518ca","first_computed_at":"2026-07-05T11:31:52.032270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:52.032270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vt7K75dF+1pB1QR9WqKCyKDiQoY0a8H5dxL35CoydW2s1hoHaYWbi9ot6wiqCizSoAypeK7a174NHZgTyebeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:52.032739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10a9d6dea3080cc1b8a4c54fda31706ea215f366e5359a45b37dc360725c64da","sha256:1744578777860f07d01fdd72daa7cb1b25ebc07bc1bfbea9449ac1efced94776"],"state_sha256":"9605e715163af54a6f19c95b791ac106b183aebddc4b55fae843b178bb29f61e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BuyczQ9sP7LyVnsrzoWw0f9an5d7haO5dol/SQTRG4NcDWkBIxrySreCidsQmHAGccItF532Tsx9oOAb3TWqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:58:59.705144Z","bundle_sha256":"2c7814f5051ee6b03e4825162298fc4347611c2513d8a2e6e057d0614e528f01"}}