{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BCRFMH4OVAL667JJIVS75DBPTB","short_pith_number":"pith:BCRFMH4O","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"},"canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","source":{"kind":"arxiv","id":"2601.05847","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05847","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05847v2","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05847","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"BCRFMH4OVAL6","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"BCRFMH4OVAL667JJ","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"BCRFMH4O","created_at":"2026-05-26T01:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BCRFMH4OVAL667JJIVS75DBPTB","target":"record","payload":{"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"},"canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","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"},"source_kind":"arxiv","source_id":"2601.05847","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZjHe7q5L5q8MEEqyN3SM45eZaFEVhocJ6iO51aI18Eo5g+KaECM87SRoDv4A+n4ZLseBQRo6pupAwI+O91nCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:09:38.656360Z"},"content_sha256":"7ec6b4b48b94f868233c9be61e46acbd4423b9ab483a39988ab30b8ccf407d2d","schema_version":"1.0","event_id":"sha256:7ec6b4b48b94f868233c9be61e46acbd4423b9ab483a39988ab30b8ccf407d2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BCRFMH4OVAL667JJIVS75DBPTB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"22yivnnHHnRbSnttxj4Cqxf+BXlvILznKlhHJDGsbEJMyvcnKEO5WZn4qKBdRKhGPk+D7uwrW4RsJI3PgzuuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:09:38.657119Z"},"content_sha256":"3457751033b62961b32d37593b69a8853ebb024ef8bcbcd42004d263fad86e38","schema_version":"1.0","event_id":"sha256:3457751033b62961b32d37593b69a8853ebb024ef8bcbcd42004d263fad86e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/bundle.json","state_url":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCRFMH4OVAL667JJIVS75DBPTB/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":"2026-05-27T01:09:38Z","links":{"resolver":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB","bundle":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/bundle.json","state":"https://pith.science/pith/BCRFMH4OVAL667JJIVS75DBPTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCRFMH4OVAL667JJIVS75DBPTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BCRFMH4OVAL667JJIVS75DBPTB","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":"b5c6c9866227e02c504057afe38219df667907a0fe6e110d72656aecd2d52d68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:20:11Z","title_canon_sha256":"3acc5c424935b7ecd7a5fa16e49d5617f50949c165f1be1fdf68f732c8fbe03b"},"schema_version":"1.0","source":{"id":"2601.05847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05847","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05847v2","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05847","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"BCRFMH4OVAL6","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"BCRFMH4OVAL667JJ","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"BCRFMH4O","created_at":"2026-05-26T01:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:3457751033b62961b32d37593b69a8853ebb024ef8bcbcd42004d263fad86e38","target":"graph","created_at":"2026-05-26T01:02:30Z","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/2601.05847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Luoxi Tang, Rafael Brens, Yuqiao Meng, Zhaohan Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:20:11Z","title":"Schema-Grounded LLM Extraction for FHIR Patient Digital Twins"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05847","kind":"arxiv","version":2},"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":"sha256:7ec6b4b48b94f868233c9be61e46acbd4423b9ab483a39988ab30b8ccf407d2d","target":"record","created_at":"2026-05-26T01:02:30Z","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":"b5c6c9866227e02c504057afe38219df667907a0fe6e110d72656aecd2d52d68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:20:11Z","title_canon_sha256":"3acc5c424935b7ecd7a5fa16e49d5617f50949c165f1be1fdf68f732c8fbe03b"},"schema_version":"1.0","source":{"id":"2601.05847","kind":"arxiv","version":2}},"canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08a2561f8ea817ef7d294565fe8c2f9865aea952f953b1326597c456bce987b5","first_computed_at":"2026-05-26T01:02:30.431297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:30.431297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7sNLHtJ+JRxHsbMw6ZipffvJO+SXei8acUbD2hhRkUpF2c/jMirep0DJNXpg2daaQ43uQp0doeYY0RkXd3xxCw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:30.432254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.05847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec6b4b48b94f868233c9be61e46acbd4423b9ab483a39988ab30b8ccf407d2d","sha256:3457751033b62961b32d37593b69a8853ebb024ef8bcbcd42004d263fad86e38"],"state_sha256":"5e7c4d84c8cc012725bffdbb59b7f4652d419c81053661c67440fc3ffc869f32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYjeh/wek+LavLG4gDKxTNy9Q9tzoMOC7qar7sBUcYi8kkbDDLY8c18bXq2SpKEqzhq/6v4Mmd9TMzsKpJUiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:09:38.661728Z","bundle_sha256":"aa04b90b2d3da215c69ef9076c46bf4d23c2d34ced477e2c2bf8e787767567e7"}}