{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T5RFBKWYJI2MRGHEYD2IXZO2U5","short_pith_number":"pith:T5RFBKWY","schema_version":"1.0","canonical_sha256":"9f6250aad84a34c898e4c0f48be5daa764fe63cb101c83aeb39fee9af8d86316","source":{"kind":"arxiv","id":"2506.19082","version":1},"attestation_state":"computed","paper":{"title":"FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amir M. Rahmani, Nitish Nagesh, Ziyu Wang","submitted_at":"2025-06-23T19:59:26Z","abstract_excerpt":"Synthetic data generation creates data based on real-world data using generative models. In health applications, generating high-quality data while maintaining fairness for sensitive attributes is essential for equitable outcomes. Existing GAN-based and LLM-based methods focus on counterfactual fairness and are primarily applied in finance and legal domains. Causal fairness provides a more comprehensive evaluation framework by preserving causal structure, but current synthetic data generation methods do not address it in health settings. To fill this gap, we develop the first LLM-augmented syn"},"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":"2506.19082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T19:59:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c63768b93233bdc8ced5ac66f0394f89d4121455d9f4ca7765848a9766084eb2","abstract_canon_sha256":"d1dbb6f5b6fe97e5961726a496c47740652aa02e00895e86aa49f03881ca5601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:09.091882Z","signature_b64":"7PL3oYGeJEOouH8Nt08BJ/F1i4ZrYR8f01u/COKMXihTFMGiHrCzgPLuLwj5kphgLa7kXlGHsAt/p9dBP3RnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6250aad84a34c898e4c0f48be5daa764fe63cb101c83aeb39fee9af8d86316","last_reissued_at":"2026-07-05T11:26:09.091355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:09.091355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amir M. Rahmani, Nitish Nagesh, Ziyu Wang","submitted_at":"2025-06-23T19:59:26Z","abstract_excerpt":"Synthetic data generation creates data based on real-world data using generative models. In health applications, generating high-quality data while maintaining fairness for sensitive attributes is essential for equitable outcomes. Existing GAN-based and LLM-based methods focus on counterfactual fairness and are primarily applied in finance and legal domains. Causal fairness provides a more comprehensive evaluation framework by preserving causal structure, but current synthetic data generation methods do not address it in health settings. To fill this gap, we develop the first LLM-augmented syn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19082","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/2506.19082/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":"2506.19082","created_at":"2026-07-05T11:26:09.091427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19082v1","created_at":"2026-07-05T11:26:09.091427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19082","created_at":"2026-07-05T11:26:09.091427+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5RFBKWYJI2M","created_at":"2026-07-05T11:26:09.091427+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5RFBKWYJI2MRGHE","created_at":"2026-07-05T11:26:09.091427+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5RFBKWY","created_at":"2026-07-05T11:26:09.091427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17758","citing_title":"Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5","json":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5.json","graph_json":"https://pith.science/api/pith-number/T5RFBKWYJI2MRGHEYD2IXZO2U5/graph.json","events_json":"https://pith.science/api/pith-number/T5RFBKWYJI2MRGHEYD2IXZO2U5/events.json","paper":"https://pith.science/paper/T5RFBKWY"},"agent_actions":{"view_html":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5","download_json":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5.json","view_paper":"https://pith.science/paper/T5RFBKWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19082&json=true","fetch_graph":"https://pith.science/api/pith-number/T5RFBKWYJI2MRGHEYD2IXZO2U5/graph.json","fetch_events":"https://pith.science/api/pith-number/T5RFBKWYJI2MRGHEYD2IXZO2U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5/action/storage_attestation","attest_author":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5/action/author_attestation","sign_citation":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5/action/citation_signature","submit_replication":"https://pith.science/pith/T5RFBKWYJI2MRGHEYD2IXZO2U5/action/replication_record"}},"created_at":"2026-07-05T11:26:09.091427+00:00","updated_at":"2026-07-05T11:26:09.091427+00:00"}