{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJMRSOFPBLLQTMHFC4UGX4SHHI","short_pith_number":"pith:XJMRSOFP","schema_version":"1.0","canonical_sha256":"ba591938af0ad709b0e517286bf2473a233583bebb41f5573a4207fc35c40974","source":{"kind":"arxiv","id":"2407.17126","version":1},"attestation_state":"computed","paper":{"title":"SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bernardo Consoli, Huanmei Wu, Justin Rousseau, Li Shen, Qi Long, Song Wang, Tianlong Chen, Tom Hartvigsen, Xinyu Zhao, Xizhi Wu, Yanshan Wang, Yifan Peng, Ying Ding","submitted_at":"2024-07-24T09:57:51Z","abstract_excerpt":"Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It achieved tenfold and twentyfold reductions in time and cost respectively, and superior consistency with human annotators measured by C"},"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":"2407.17126","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T09:57:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e388bad45dd15c91686dc9d9b68df229ea32e46e3f34787c6aa51049e415fb38","abstract_canon_sha256":"a8cfcd5c56ea048d114abcf51feace6d91005b0425922273c35872279ddb9e4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:02.529690Z","signature_b64":"T3UhsOeBiirCuLBVrZL0x97MdCVbdIW3E6Hs56gyibgGRgTMdKdwVExlo9LjDLPKbHtXFpHoaGZlMu/9uoMGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba591938af0ad709b0e517286bf2473a233583bebb41f5573a4207fc35c40974","last_reissued_at":"2026-07-05T08:48:02.529254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:02.529254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bernardo Consoli, Huanmei Wu, Justin Rousseau, Li Shen, Qi Long, Song Wang, Tianlong Chen, Tom Hartvigsen, Xinyu Zhao, Xizhi Wu, Yanshan Wang, Yifan Peng, Ying Ding","submitted_at":"2024-07-24T09:57:51Z","abstract_excerpt":"Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It achieved tenfold and twentyfold reductions in time and cost respectively, and superior consistency with human annotators measured by C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17126","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/2407.17126/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":"2407.17126","created_at":"2026-07-05T08:48:02.529311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17126v1","created_at":"2026-07-05T08:48:02.529311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17126","created_at":"2026-07-05T08:48:02.529311+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJMRSOFPBLLQ","created_at":"2026-07-05T08:48:02.529311+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJMRSOFPBLLQTMHF","created_at":"2026-07-05T08:48:02.529311+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJMRSOFP","created_at":"2026-07-05T08:48:02.529311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05003","citing_title":"A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI","json":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI.json","graph_json":"https://pith.science/api/pith-number/XJMRSOFPBLLQTMHFC4UGX4SHHI/graph.json","events_json":"https://pith.science/api/pith-number/XJMRSOFPBLLQTMHFC4UGX4SHHI/events.json","paper":"https://pith.science/paper/XJMRSOFP"},"agent_actions":{"view_html":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI","download_json":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI.json","view_paper":"https://pith.science/paper/XJMRSOFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17126&json=true","fetch_graph":"https://pith.science/api/pith-number/XJMRSOFPBLLQTMHFC4UGX4SHHI/graph.json","fetch_events":"https://pith.science/api/pith-number/XJMRSOFPBLLQTMHFC4UGX4SHHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI/action/storage_attestation","attest_author":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI/action/author_attestation","sign_citation":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI/action/citation_signature","submit_replication":"https://pith.science/pith/XJMRSOFPBLLQTMHFC4UGX4SHHI/action/replication_record"}},"created_at":"2026-07-05T08:48:02.529311+00:00","updated_at":"2026-07-05T08:48:02.529311+00:00"}