{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OGJW6B2SIMQD77LAJIMLCNYL32","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":"70044de1934a0369cf6bff8104973d5d227b5bddb0c1218519ff6430e93023a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T05:40:24Z","title_canon_sha256":"b6e63d6d79afffa5de257a08638dfb4d57ee1f7a2d4004bedf2ef20b18959e7e"},"schema_version":"1.0","source":{"id":"2604.13502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13502","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13502v2","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13502","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"OGJW6B2SIMQD","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"OGJW6B2SIMQD77LA","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"OGJW6B2S","created_at":"2026-05-27T02:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:3d5d756e48fb13aa552ef4a17df1a71ec53057cc8420e9b8ecce1e7cd591015b","target":"graph","created_at":"2026-05-27T02:05:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our approach achieved a micro-F1 score of 0.866, demonstrating competitive performance compared to the leading models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the combination of guideline-integrated prompts, curated few-shot examples, self-consistency, and post-processing will produce reliable structured outputs on unseen clinical notes without extensive per-site tuning or validation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Reasoning LLMs using concise prompts, few-shot examples, self-consistency, and post-processing extract SDOH events at micro-F1 0.866, matching leading BERT models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reasoning LLMs extract social and environmental health factors from clinical notes at competitive accuracy"}],"snapshot_sha256":"0ac0c19040d306196accdfae2772982af3122758c2746390f83510c35c6aa260"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.13502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social Determinants of Health (SDOH) refer to environmental, behavioral, and social conditions that influence how individuals live, work, and age. SDOH have a significant impact on personal health outcomes, and their systematic identification and management can yield substantial improvements in patient care. However, SDOH information is predominantly captured in unstructured clinical notes within electronic health records, which limits its direct use as machine-readable entities. To address this issue, researchers have employed Natural Language Processing (NLP) techniques using pre-trained BER","authors_text":"Ertan Dogan, Kunyu Yu, Yifan Peng","cross_cats":[],"headline":"Reasoning LLMs extract social and environmental health factors from clinical notes at competitive accuracy","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T05:40:24Z","title":"Using reasoning LLMs to extract SDOH events from clinical notes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.13502","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T14:18:57.384176Z","id":"5db7e678-9007-4c48-94d1-d57fb78639ff","model_set":{"reader":"grok-4.3"},"one_line_summary":"Reasoning LLMs using concise prompts, few-shot examples, self-consistency, and post-processing extract SDOH events at micro-F1 0.866, matching leading BERT models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Reasoning LLMs extract social and environmental health factors from clinical notes at competitive accuracy","strongest_claim":"Our approach achieved a micro-F1 score of 0.866, demonstrating competitive performance compared to the leading models.","weakest_assumption":"That the combination of guideline-integrated prompts, curated few-shot examples, self-consistency, and post-processing will produce reliable structured outputs on unseen clinical notes without extensive per-site tuning or validation."}},"verdict_id":"5db7e678-9007-4c48-94d1-d57fb78639ff"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:faf751f2c4cf34ad9333d3f1e3b66833d91ad1062478bb14fa87db90a80cef2a","target":"record","created_at":"2026-05-27T02:05:19Z","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":"70044de1934a0369cf6bff8104973d5d227b5bddb0c1218519ff6430e93023a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T05:40:24Z","title_canon_sha256":"b6e63d6d79afffa5de257a08638dfb4d57ee1f7a2d4004bedf2ef20b18959e7e"},"schema_version":"1.0","source":{"id":"2604.13502","kind":"arxiv","version":2}},"canonical_sha256":"71936f075243203ffd604a18b1370bdeb78ec481cbbe294b5ba94da7b8a47ba3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71936f075243203ffd604a18b1370bdeb78ec481cbbe294b5ba94da7b8a47ba3","first_computed_at":"2026-05-27T02:05:19.734721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:19.734721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aRXGIGBwLZWHIM1Zfx6Pg2b9Aolx8qPTRkiODIU6913yTs6DM7YQaEX89wnSLDE7ulZa3P2Xuu+yu1znJcOIAw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:19.735247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.13502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faf751f2c4cf34ad9333d3f1e3b66833d91ad1062478bb14fa87db90a80cef2a","sha256:3d5d756e48fb13aa552ef4a17df1a71ec53057cc8420e9b8ecce1e7cd591015b"],"state_sha256":"5747ab859741e8fe504974ef6d5f43699d2acb5cca9a45a1deff6b534f11f1ad"}