{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VDLBHV3FBE4637UB3NMGPHTRLS","short_pith_number":"pith:VDLBHV3F","schema_version":"1.0","canonical_sha256":"a8d613d7650939edfe81db58679e715c9aacd51795431a95ec1270c827a91748","source":{"kind":"arxiv","id":"2605.30295","version":1},"attestation_state":"computed","paper":{"title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eug\\'enie Dulout, Valentina Bui Muti, Ziquan Fu","submitted_at":"2026-05-28T17:42:43Z","abstract_excerpt":"Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in realistic, electronic health record-congruent settings remains limited. Existing benchmarks often rely on static datasets or unstructured inputs that do not reflect the structured, interoperable data formats used in clinical systems. We introduce a pipeline for generating clinically realistic HL7 FHIR R4 bundles from unstructured text, enabling controllable evaluation of clinical decision support systems. The pipeline combines staged LLM generation with terminology-grounded validation and r"},"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":"2605.30295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:42:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9da1ec6c78305ee68c4cac22bb89602ed2342347a9ff95f8de0ae6bfb32d97d2","abstract_canon_sha256":"d6bb5599fdc62a708b5415a6b5c2b26032e030f5842ed2ed45f37e8524f777cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:15.594307Z","signature_b64":"6RqG/Pp7BkTP0JSEWYt9A1gHhhBFoqoC4x5dK+pssfhnHwKKskp6y6Z1wYhAXP236RPNGNTaFuIrkKAPTssaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8d613d7650939edfe81db58679e715c9aacd51795431a95ec1270c827a91748","last_reissued_at":"2026-05-29T02:06:15.593883Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:15.593883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eug\\'enie Dulout, Valentina Bui Muti, Ziquan Fu","submitted_at":"2026-05-28T17:42:43Z","abstract_excerpt":"Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in realistic, electronic health record-congruent settings remains limited. Existing benchmarks often rely on static datasets or unstructured inputs that do not reflect the structured, interoperable data formats used in clinical systems. We introduce a pipeline for generating clinically realistic HL7 FHIR R4 bundles from unstructured text, enabling controllable evaluation of clinical decision support systems. The pipeline combines staged LLM generation with terminology-grounded validation and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30295","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/2605.30295/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":"2605.30295","created_at":"2026-05-29T02:06:15.593947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30295v1","created_at":"2026-05-29T02:06:15.593947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30295","created_at":"2026-05-29T02:06:15.593947+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDLBHV3FBE46","created_at":"2026-05-29T02:06:15.593947+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDLBHV3FBE4637UB","created_at":"2026-05-29T02:06:15.593947+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDLBHV3F","created_at":"2026-05-29T02:06:15.593947+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/VDLBHV3FBE4637UB3NMGPHTRLS","json":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS.json","graph_json":"https://pith.science/api/pith-number/VDLBHV3FBE4637UB3NMGPHTRLS/graph.json","events_json":"https://pith.science/api/pith-number/VDLBHV3FBE4637UB3NMGPHTRLS/events.json","paper":"https://pith.science/paper/VDLBHV3F"},"agent_actions":{"view_html":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS","download_json":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS.json","view_paper":"https://pith.science/paper/VDLBHV3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30295&json=true","fetch_graph":"https://pith.science/api/pith-number/VDLBHV3FBE4637UB3NMGPHTRLS/graph.json","fetch_events":"https://pith.science/api/pith-number/VDLBHV3FBE4637UB3NMGPHTRLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS/action/storage_attestation","attest_author":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS/action/author_attestation","sign_citation":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS/action/citation_signature","submit_replication":"https://pith.science/pith/VDLBHV3FBE4637UB3NMGPHTRLS/action/replication_record"}},"created_at":"2026-05-29T02:06:15.593947+00:00","updated_at":"2026-05-29T02:06:15.593947+00:00"}