{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2VBNAESYNZSMK2AFAJSXP3DOE7","short_pith_number":"pith:2VBNAESY","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"},"canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","source":{"kind":"arxiv","id":"2412.16335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16335","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16335v1","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16335","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"2VBNAESYNZSM","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"2VBNAESYNZSMK2AF","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"2VBNAESY","created_at":"2026-07-05T09:53:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2VBNAESYNZSMK2AFAJSXP3DOE7","target":"record","payload":{"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"},"canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","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"},"source_kind":"arxiv","source_id":"2412.16335","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxIN83Ac7Vfto91Ilpgctla8dUFEQSsfxVuU6FJD8XHCwZPOuEK6qm4G/3xJmCPY/9bR8KEbK1eQGpDgntRBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:12:00.685541Z"},"content_sha256":"651ec510da54b287271ac2c18ac1635325f07ec39f9df900e92b1ae6711ca052","schema_version":"1.0","event_id":"sha256:651ec510da54b287271ac2c18ac1635325f07ec39f9df900e92b1ae6711ca052"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2VBNAESYNZSMK2AFAJSXP3DOE7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfJGNPJDpIoqSyLjf1GtIsccUDQyo/Yx/P0jOqtycs7zyokDovfgMh6snd+Np1wUJeO4Xz+IijlBkSItw/acBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:12:00.686202Z"},"content_sha256":"7f6f66e021871b3d758f5dfb3eced99ff1e196552e6445e7d9b4a49da29d7406","schema_version":"1.0","event_id":"sha256:7f6f66e021871b3d758f5dfb3eced99ff1e196552e6445e7d9b4a49da29d7406"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/bundle.json","state_url":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T17:12:00Z","links":{"resolver":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7","bundle":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/bundle.json","state":"https://pith.science/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VBNAESYNZSMK2AFAJSXP3DOE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2VBNAESYNZSMK2AFAJSXP3DOE7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4fc0a88b14b988e8bbd2d15357763a16a67ae48a24c8ba6afb85f64ec319726c","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T20:49:17Z","title_canon_sha256":"8ae8113813c67099c21ed6f2fbdc4f0f896cef362e8f7557247d98a6e06c0a67"},"schema_version":"1.0","source":{"id":"2412.16335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16335","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16335v1","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16335","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"2VBNAESYNZSM","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"2VBNAESYNZSMK2AF","created_at":"2026-07-05T09:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"2VBNAESY","created_at":"2026-07-05T09:53:10Z"}],"graph_snapshots":[{"event_id":"sha256:7f6f66e021871b3d758f5dfb3eced99ff1e196552e6445e7d9b4a49da29d7406","target":"graph","created_at":"2026-07-05T09:53:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.16335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arshana Welivita, Daniel Smolyak, Margr\\'et V. Bjarnad\\'ottir, Ritu Agarwal","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T20:49:17Z","title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16335","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:651ec510da54b287271ac2c18ac1635325f07ec39f9df900e92b1ae6711ca052","target":"record","created_at":"2026-07-05T09:53:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4fc0a88b14b988e8bbd2d15357763a16a67ae48a24c8ba6afb85f64ec319726c","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T20:49:17Z","title_canon_sha256":"8ae8113813c67099c21ed6f2fbdc4f0f896cef362e8f7557247d98a6e06c0a67"},"schema_version":"1.0","source":{"id":"2412.16335","kind":"arxiv","version":1}},"canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d542d012586e64c56805026577ec6e27e4ab743e4364a4ca1bb42b498a72b628","first_computed_at":"2026-07-05T09:53:10.208907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:10.208907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMLmohUBCJ0RORv+GW/NNf++7rpHk5IhxfRSKHs8cFGgnUUWV26YbzJfDlODlbh+fwY3MyfVpFQNz6NLG6wfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:10.209308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:651ec510da54b287271ac2c18ac1635325f07ec39f9df900e92b1ae6711ca052","sha256:7f6f66e021871b3d758f5dfb3eced99ff1e196552e6445e7d9b4a49da29d7406"],"state_sha256":"4740e00948be225f6b1d62cb135765eb930a48babd82bfefc3cac27a8e1a0d56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oRQ/bS/PKlzQP8fes+7Ti0AAmXTB5L0tv88rU1y2mOa8da/+aiLWlrWgMNGpJR/kxm7jdRWxUo90bNkK/WtNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:12:00.691548Z","bundle_sha256":"814ec4d025fbf72d9c4e843311e1cf263c4d3be3e6a40d439d257ead95b422f4"}}