{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E2HC4IYUWM5WFRUGJP2UIPZ6KW","short_pith_number":"pith:E2HC4IYU","schema_version":"1.0","canonical_sha256":"268e2e2314b33b62c6864bf5443f3e55bec671414fa13c24a8e7acb1482d87ac","source":{"kind":"arxiv","id":"2406.06056","version":3},"attestation_state":"computed","paper":{"title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avijit Mitra, Emily Druhl, Hong Yu, Raelene Goodwin, Zhichao Yang","submitted_at":"2024-06-10T07:03:36Z","abstract_excerpt":"Social and behavioral determinants of health (SBDH) play a crucial role in health outcomes and are frequently documented in clinical text. Automatically extracting SBDH information from clinical text relies on publicly available good-quality datasets. However, existing SBDH datasets exhibit substantial limitations in their availability and coverage. In this study, we introduce Synth-SBDH, a novel synthetic dataset with detailed SBDH annotations, encompassing status, temporal information, and rationale across 15 SBDH categories. We showcase the utility of Synth-SBDH on three tasks using real-wo"},"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":"2406.06056","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T07:03:36Z","cross_cats_sorted":[],"title_canon_sha256":"90ac21c30a536985cb968a9624c3a92eb3aadc80461aa5ee36101f5640d361ca","abstract_canon_sha256":"2b63ead3204ceac5093b695bcab5707dce28eddee8f3ddd444eca002a7be4bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:00.211092Z","signature_b64":"+i+Lqn1j7kw/Zh0KnOBeoZ7OjmL7W2tnmrJbQIirhTxVV0+ae2x+z9MfQqN8WM6q++VMFzXUHpBjYELCvCS3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"268e2e2314b33b62c6864bf5443f3e55bec671414fa13c24a8e7acb1482d87ac","last_reissued_at":"2026-07-05T12:06:00.210617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:00.210617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avijit Mitra, Emily Druhl, Hong Yu, Raelene Goodwin, Zhichao Yang","submitted_at":"2024-06-10T07:03:36Z","abstract_excerpt":"Social and behavioral determinants of health (SBDH) play a crucial role in health outcomes and are frequently documented in clinical text. Automatically extracting SBDH information from clinical text relies on publicly available good-quality datasets. However, existing SBDH datasets exhibit substantial limitations in their availability and coverage. In this study, we introduce Synth-SBDH, a novel synthetic dataset with detailed SBDH annotations, encompassing status, temporal information, and rationale across 15 SBDH categories. We showcase the utility of Synth-SBDH on three tasks using real-wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06056","kind":"arxiv","version":3},"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/2406.06056/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":"2406.06056","created_at":"2026-07-05T12:06:00.210680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06056v3","created_at":"2026-07-05T12:06:00.210680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06056","created_at":"2026-07-05T12:06:00.210680+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2HC4IYUWM5W","created_at":"2026-07-05T12:06:00.210680+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2HC4IYUWM5WFRUG","created_at":"2026-07-05T12:06:00.210680+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2HC4IYU","created_at":"2026-07-05T12:06:00.210680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05993","citing_title":"Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW","json":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW.json","graph_json":"https://pith.science/api/pith-number/E2HC4IYUWM5WFRUGJP2UIPZ6KW/graph.json","events_json":"https://pith.science/api/pith-number/E2HC4IYUWM5WFRUGJP2UIPZ6KW/events.json","paper":"https://pith.science/paper/E2HC4IYU"},"agent_actions":{"view_html":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW","download_json":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW.json","view_paper":"https://pith.science/paper/E2HC4IYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06056&json=true","fetch_graph":"https://pith.science/api/pith-number/E2HC4IYUWM5WFRUGJP2UIPZ6KW/graph.json","fetch_events":"https://pith.science/api/pith-number/E2HC4IYUWM5WFRUGJP2UIPZ6KW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW/action/storage_attestation","attest_author":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW/action/author_attestation","sign_citation":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW/action/citation_signature","submit_replication":"https://pith.science/pith/E2HC4IYUWM5WFRUGJP2UIPZ6KW/action/replication_record"}},"created_at":"2026-07-05T12:06:00.210680+00:00","updated_at":"2026-07-05T12:06:00.210680+00:00"}