{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VBNAESYNZSMK2AFAJSXP3DOE7","short_pith_number":"pith:2VBNAESY","schema_version":"1.0","canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","source":{"kind":"arxiv","id":"2412.16335","version":1},"attestation_state":"computed","paper":{"title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Arshana Welivita, Daniel Smolyak, Margr\\'et V. Bjarnad\\'ottir, Ritu Agarwal","submitted_at":"2024-12-20T20:49:17Z","abstract_excerpt":"Objective. Demographic groups are often represented at different rates in medical datasets. These differences can create bias in machine learning algorithms, with higher levels of performance for better-represented groups. One promising solution to this problem is to generate synthetic data to mitigate potential adverse effects of non-representative data sets.\n  Methods. We build on recent advances in LLM-based synthetic data generation to create a pipeline where the synthetic data is generated separately for each demographic group. We conduct our study using MIMIC-IV and Framingham \"Offspring"},"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":"2412.16335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T20:49:17Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"8ae8113813c67099c21ed6f2fbdc4f0f896cef362e8f7557247d98a6e06c0a67","abstract_canon_sha256":"4fc0a88b14b988e8bbd2d15357763a16a67ae48a24c8ba6afb85f64ec319726c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:10.209308Z","signature_b64":"aMLmohUBCJ0RORv+GW/NNf++7rpHk5IhxfRSKHs8cFGgnUUWV26YbzJfDlODlbh+fwY3MyfVpFQNz6NLG6wfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","last_reissued_at":"2026-07-05T09:53:10.208907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:10.208907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Arshana Welivita, Daniel Smolyak, Margr\\'et V. Bjarnad\\'ottir, Ritu Agarwal","submitted_at":"2024-12-20T20:49:17Z","abstract_excerpt":"Objective. Demographic groups are often represented at different rates in medical datasets. These differences can create bias in machine learning algorithms, with higher levels of performance for better-represented groups. One promising solution to this problem is to generate synthetic data to mitigate potential adverse effects of non-representative data sets.\n  Methods. We build on recent advances in LLM-based synthetic data generation to create a pipeline where the synthetic data is generated separately for each demographic group. We conduct our study using MIMIC-IV and Framingham \"Offspring"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16335","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/2412.16335/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":"2412.16335","created_at":"2026-07-05T09:53:10.208958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16335v1","created_at":"2026-07-05T09:53:10.208958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16335","created_at":"2026-07-05T09:53:10.208958+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VBNAESYNZSM","created_at":"2026-07-05T09:53:10.208958+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VBNAESYNZSMK2AF","created_at":"2026-07-05T09:53:10.208958+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VBNAESY","created_at":"2026-07-05T09:53:10.208958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7","json":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7.json","graph_json":"https://pith.science/api/pith-number/2VBNAESYNZSMK2AFAJSXP3DOE7/graph.json","events_json":"https://pith.science/api/pith-number/2VBNAESYNZSMK2AFAJSXP3DOE7/events.json","paper":"https://pith.science/paper/2VBNAESY"},"agent_actions":{"view_html":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7","download_json":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7.json","view_paper":"https://pith.science/paper/2VBNAESY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16335&json=true","fetch_graph":"https://pith.science/api/pith-number/2VBNAESYNZSMK2AFAJSXP3DOE7/graph.json","fetch_events":"https://pith.science/api/pith-number/2VBNAESYNZSMK2AFAJSXP3DOE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/action/storage_attestation","attest_author":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/action/author_attestation","sign_citation":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/action/citation_signature","submit_replication":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/action/replication_record"}},"created_at":"2026-07-05T09:53:10.208958+00:00","updated_at":"2026-07-05T09:53:10.208958+00:00"}