{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BCRFMH4OVAL667JJIVS75DBPTB","short_pith_number":"pith:BCRFMH4O","schema_version":"1.0","canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","source":{"kind":"arxiv","id":"2601.05847","version":2},"attestation_state":"computed","paper":{"title":"Schema-Grounded LLM Extraction for FHIR Patient Digital Twins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luoxi Tang, Rafael Brens, Yuqiao Meng, Zhaohan Xi","submitted_at":"2026-01-09T15:20:11Z","abstract_excerpt":"We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the task is better cast not as a cascade of extraction modules but as constrained generation of a valid FHIR bundle. We introduce SG-LLM, a schema-grounded LLM extractor that (i) augments the prompt with candidate SNOMED-CT, RxNorm, and LOINC codes retrieved through a SapBERT index, (ii) decodes under a JSON Schema derived directly from FHIR R4 StructureDefinitions, and (iii) closes a validator-in-the-loop repair stage whose diagnostics are fed back as st"},"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":"2601.05847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"3acc5c424935b7ecd7a5fa16e49d5617f50949c165f1be1fdf68f732c8fbe03b","abstract_canon_sha256":"b5c6c9866227e02c504057afe38219df667907a0fe6e110d72656aecd2d52d68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:30.432254Z","signature_b64":"7sNLHtJ+JRxHsbMw6ZipffvJO+SXei8acUbD2hhRkUpF2c/jMirep0DJNXpg2daaQ43uQp0doeYY0RkXd3xxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","last_reissued_at":"2026-05-26T01:02:30.431297Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:30.431297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Schema-Grounded LLM Extraction for FHIR Patient Digital Twins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luoxi Tang, Rafael Brens, Yuqiao Meng, Zhaohan Xi","submitted_at":"2026-01-09T15:20:11Z","abstract_excerpt":"We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the task is better cast not as a cascade of extraction modules but as constrained generation of a valid FHIR bundle. We introduce SG-LLM, a schema-grounded LLM extractor that (i) augments the prompt with candidate SNOMED-CT, RxNorm, and LOINC codes retrieved through a SapBERT index, (ii) decodes under a JSON Schema derived directly from FHIR R4 StructureDefinitions, and (iii) closes a validator-in-the-loop repair stage whose diagnostics are fed back as st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05847","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/2601.05847/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":"2601.05847","created_at":"2026-05-26T01:02:30.431449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.05847v2","created_at":"2026-05-26T01:02:30.431449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05847","created_at":"2026-05-26T01:02:30.431449+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCRFMH4OVAL6","created_at":"2026-05-26T01:02:30.431449+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCRFMH4OVAL667JJ","created_at":"2026-05-26T01:02:30.431449+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCRFMH4O","created_at":"2026-05-26T01:02:30.431449+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/BCRFMH4OVAL667JJIVS75DBPTB","json":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB.json","graph_json":"https://pith.science/api/pith-number/BCRFMH4OVAL667JJIVS75DBPTB/graph.json","events_json":"https://pith.science/api/pith-number/BCRFMH4OVAL667JJIVS75DBPTB/events.json","paper":"https://pith.science/paper/BCRFMH4O"},"agent_actions":{"view_html":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB","download_json":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB.json","view_paper":"https://pith.science/paper/BCRFMH4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.05847&json=true","fetch_graph":"https://pith.science/api/pith-number/BCRFMH4OVAL667JJIVS75DBPTB/graph.json","fetch_events":"https://pith.science/api/pith-number/BCRFMH4OVAL667JJIVS75DBPTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/action/storage_attestation","attest_author":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/action/author_attestation","sign_citation":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/action/citation_signature","submit_replication":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/action/replication_record"}},"created_at":"2026-05-26T01:02:30.431449+00:00","updated_at":"2026-05-26T01:02:30.431449+00:00"}