{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UULOCPBMH5U4CLWB44UO5T7BO6","short_pith_number":"pith:UULOCPBM","schema_version":"1.0","canonical_sha256":"a516e13c2c3f69c12ec1e728eecfe1778312163631edc52b7f4d7e9d1996426b","source":{"kind":"arxiv","id":"2404.00826","version":2},"attestation_state":"computed","paper":{"title":"Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abby R. Rosenberg, Fei Xia, Giridhar Kaushik Ramachandran, Kevin Lybarger, Meliha Yetisgen, Michael Leu, Namu Park, Nicholas J Dobbins, Ozlem Uzuner, Yujuan Fu","submitted_at":"2024-03-31T23:37:18Z","abstract_excerpt":"Social determinants of health (SDoH) play a critical role in shaping health outcomes, particularly in pediatric populations where interventions can have long-term implications. SDoH are frequently studied in the Electronic Health Record (EHR), which provides a rich repository for diverse patient data. In this work, we present a novel annotated corpus, the Pediatric Social History Annotation Corpus (PedSHAC), and evaluate the automatic extraction of detailed SDoH representations using fine-tuned and in-context learning methods with Large Language Models (LLMs). PedSHAC comprises annotated socia"},"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":"2404.00826","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T23:37:18Z","cross_cats_sorted":[],"title_canon_sha256":"406c06734b85f0448d2bf26f472d9cdd12b313a47d6ac35b62300b7561fb7680","abstract_canon_sha256":"0c7eeb5c29659b04b6f0676aa5b224c528feff3ad0b467de23cf4b4fead23210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:19.717238Z","signature_b64":"R04DQVGRfH4JwQW9nzeRbZX6oZrfcoxw5A6xLS/AVgihspIJ2BC1au6zqbKdAIKHQujSjVvRLZZnu9eDdiWtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a516e13c2c3f69c12ec1e728eecfe1778312163631edc52b7f4d7e9d1996426b","last_reissued_at":"2026-07-05T08:04:19.716677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:19.716677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abby R. Rosenberg, Fei Xia, Giridhar Kaushik Ramachandran, Kevin Lybarger, Meliha Yetisgen, Michael Leu, Namu Park, Nicholas J Dobbins, Ozlem Uzuner, Yujuan Fu","submitted_at":"2024-03-31T23:37:18Z","abstract_excerpt":"Social determinants of health (SDoH) play a critical role in shaping health outcomes, particularly in pediatric populations where interventions can have long-term implications. SDoH are frequently studied in the Electronic Health Record (EHR), which provides a rich repository for diverse patient data. In this work, we present a novel annotated corpus, the Pediatric Social History Annotation Corpus (PedSHAC), and evaluate the automatic extraction of detailed SDoH representations using fine-tuned and in-context learning methods with Large Language Models (LLMs). PedSHAC comprises annotated socia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00826","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/2404.00826/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":"2404.00826","created_at":"2026-07-05T08:04:19.716747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00826v2","created_at":"2026-07-05T08:04:19.716747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00826","created_at":"2026-07-05T08:04:19.716747+00:00"},{"alias_kind":"pith_short_12","alias_value":"UULOCPBMH5U4","created_at":"2026-07-05T08:04:19.716747+00:00"},{"alias_kind":"pith_short_16","alias_value":"UULOCPBMH5U4CLWB","created_at":"2026-07-05T08:04:19.716747+00:00"},{"alias_kind":"pith_short_8","alias_value":"UULOCPBM","created_at":"2026-07-05T08:04:19.716747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11478","citing_title":"ImmunoFOMO: Are Language Models missing what oncologists see?","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6","json":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6.json","graph_json":"https://pith.science/api/pith-number/UULOCPBMH5U4CLWB44UO5T7BO6/graph.json","events_json":"https://pith.science/api/pith-number/UULOCPBMH5U4CLWB44UO5T7BO6/events.json","paper":"https://pith.science/paper/UULOCPBM"},"agent_actions":{"view_html":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6","download_json":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6.json","view_paper":"https://pith.science/paper/UULOCPBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00826&json=true","fetch_graph":"https://pith.science/api/pith-number/UULOCPBMH5U4CLWB44UO5T7BO6/graph.json","fetch_events":"https://pith.science/api/pith-number/UULOCPBMH5U4CLWB44UO5T7BO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6/action/storage_attestation","attest_author":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6/action/author_attestation","sign_citation":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6/action/citation_signature","submit_replication":"https://pith.science/pith/UULOCPBMH5U4CLWB44UO5T7BO6/action/replication_record"}},"created_at":"2026-07-05T08:04:19.716747+00:00","updated_at":"2026-07-05T08:04:19.716747+00:00"}