{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YM3HSZY4CABD6E5G727QSD6Y2Z","short_pith_number":"pith:YM3HSZY4","schema_version":"1.0","canonical_sha256":"c33679671c10023f13a6febf090fd8d655d7f965c9dc50ab59543a91549220f7","source":{"kind":"arxiv","id":"2306.07170","version":1},"attestation_state":"computed","paper":{"title":"Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Han, Giridhar Kaushik Ramachandran, Kevin Lybarger, Meliha Yetisgen, Nicholas J Dobbins, \\\"Ozlem Uzuner, Yujuan Fu","submitted_at":"2023-06-12T15:08:25Z","abstract_excerpt":"Social determinants of health (SDOH) documented in the electronic health record through unstructured text are increasingly being studied to understand how SDOH impacts patient health outcomes. In this work, we utilize the Social History Annotation Corpus (SHAC), a multi-institutional corpus of de-identified social history sections annotated for SDOH, including substance use, employment, and living status information. We explore the automatic extraction of SDOH information with SHAC in both standoff and inline annotation formats using GPT-4 in a one-shot prompting setting. We compare GPT-4 extr"},"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":"2306.07170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T15:08:25Z","cross_cats_sorted":[],"title_canon_sha256":"9e03fb19313e536dd032641c84769ad988d35ba93c03031257f5f761bfc8e2ef","abstract_canon_sha256":"2de7e16476b8fdbf81dd4637cd276745ccc2c0ba3e674253670c119e5ca3a574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:48.573968Z","signature_b64":"1erSx4aN3UjNAXOgM+TnoS7NIlf5CYFu4OPHFA2uhK7T24S23aYLQpP4mFlfBbMj1msWGljmRMjRVnWpveAxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c33679671c10023f13a6febf090fd8d655d7f965c9dc50ab59543a91549220f7","last_reissued_at":"2026-07-05T06:19:48.573541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:48.573541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Han, Giridhar Kaushik Ramachandran, Kevin Lybarger, Meliha Yetisgen, Nicholas J Dobbins, \\\"Ozlem Uzuner, Yujuan Fu","submitted_at":"2023-06-12T15:08:25Z","abstract_excerpt":"Social determinants of health (SDOH) documented in the electronic health record through unstructured text are increasingly being studied to understand how SDOH impacts patient health outcomes. In this work, we utilize the Social History Annotation Corpus (SHAC), a multi-institutional corpus of de-identified social history sections annotated for SDOH, including substance use, employment, and living status information. We explore the automatic extraction of SDOH information with SHAC in both standoff and inline annotation formats using GPT-4 in a one-shot prompting setting. We compare GPT-4 extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07170","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/2306.07170/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":"2306.07170","created_at":"2026-07-05T06:19:48.573598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07170v1","created_at":"2026-07-05T06:19:48.573598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07170","created_at":"2026-07-05T06:19:48.573598+00:00"},{"alias_kind":"pith_short_12","alias_value":"YM3HSZY4CABD","created_at":"2026-07-05T06:19:48.573598+00:00"},{"alias_kind":"pith_short_16","alias_value":"YM3HSZY4CABD6E5G","created_at":"2026-07-05T06:19:48.573598+00:00"},{"alias_kind":"pith_short_8","alias_value":"YM3HSZY4","created_at":"2026-07-05T06:19:48.573598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05009","citing_title":"Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z","json":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z.json","graph_json":"https://pith.science/api/pith-number/YM3HSZY4CABD6E5G727QSD6Y2Z/graph.json","events_json":"https://pith.science/api/pith-number/YM3HSZY4CABD6E5G727QSD6Y2Z/events.json","paper":"https://pith.science/paper/YM3HSZY4"},"agent_actions":{"view_html":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z","download_json":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z.json","view_paper":"https://pith.science/paper/YM3HSZY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07170&json=true","fetch_graph":"https://pith.science/api/pith-number/YM3HSZY4CABD6E5G727QSD6Y2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/YM3HSZY4CABD6E5G727QSD6Y2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z/action/storage_attestation","attest_author":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z/action/author_attestation","sign_citation":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z/action/citation_signature","submit_replication":"https://pith.science/pith/YM3HSZY4CABD6E5G727QSD6Y2Z/action/replication_record"}},"created_at":"2026-07-05T06:19:48.573598+00:00","updated_at":"2026-07-05T06:19:48.573598+00:00"}