{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CDANHIZHURFPXJLAYQB3MIFOQW","short_pith_number":"pith:CDANHIZH","schema_version":"1.0","canonical_sha256":"10c0d3a327a44afba560c403b620ae85aea62809051413f27ef3894a98a86108","source":{"kind":"arxiv","id":"2501.01785","version":1},"attestation_state":"computed","paper":{"title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"George Siemens, Mohammad Khalil, Oscar Deho, Qinyi Liu, Sam Urmian, Srecko Joksimovic","submitted_at":"2025-01-03T12:35:58Z","abstract_excerpt":"The increasing use of machine learning in learning analytics (LA) has raised significant concerns around algorithmic fairness and privacy. Synthetic data has emerged as a dual-purpose tool, enhancing privacy and improving fairness in LA models. However, prior research suggests an inverse relationship between fairness and privacy, making it challenging to optimize both. This study investigates which synthetic data generators can best balance privacy and fairness, and whether pre-processing fairness algorithms, typically applied to real datasets, are effective on synthetic data. Our results high"},"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":"2501.01785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-03T12:35:58Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"9ad7b78bf94ed3b110718e0d673966d0ac6d0f4587ff42f34d96ae37f05e45f6","abstract_canon_sha256":"aa54b1e6d6dfa10915731fc5f484de5d4e2840963bd932ad16a5b73ba61b5129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T21:03:57.678521Z","signature_b64":"ZewmdlkcJfYXZaTTj9WlRPHakMJyvE4w5dL4eIuP3Tbzb4gZ0avzRyGSWPUpc6cT3KflccQcykZg3vv4RMkSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10c0d3a327a44afba560c403b620ae85aea62809051413f27ef3894a98a86108","last_reissued_at":"2026-05-21T21:03:57.677977Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T21:03:57.677977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"George Siemens, Mohammad Khalil, Oscar Deho, Qinyi Liu, Sam Urmian, Srecko Joksimovic","submitted_at":"2025-01-03T12:35:58Z","abstract_excerpt":"The increasing use of machine learning in learning analytics (LA) has raised significant concerns around algorithmic fairness and privacy. Synthetic data has emerged as a dual-purpose tool, enhancing privacy and improving fairness in LA models. However, prior research suggests an inverse relationship between fairness and privacy, making it challenging to optimize both. This study investigates which synthetic data generators can best balance privacy and fairness, and whether pre-processing fairness algorithms, typically applied to real datasets, are effective on synthetic data. Our results high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01785","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/2501.01785/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":"2501.01785","created_at":"2026-05-21T21:03:57.678046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01785v1","created_at":"2026-05-21T21:03:57.678046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01785","created_at":"2026-05-21T21:03:57.678046+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDANHIZHURFP","created_at":"2026-05-21T21:03:57.678046+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDANHIZHURFPXJLA","created_at":"2026-05-21T21:03:57.678046+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDANHIZH","created_at":"2026-05-21T21:03:57.678046+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/CDANHIZHURFPXJLAYQB3MIFOQW","json":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW.json","graph_json":"https://pith.science/api/pith-number/CDANHIZHURFPXJLAYQB3MIFOQW/graph.json","events_json":"https://pith.science/api/pith-number/CDANHIZHURFPXJLAYQB3MIFOQW/events.json","paper":"https://pith.science/paper/CDANHIZH"},"agent_actions":{"view_html":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW","download_json":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW.json","view_paper":"https://pith.science/paper/CDANHIZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01785&json=true","fetch_graph":"https://pith.science/api/pith-number/CDANHIZHURFPXJLAYQB3MIFOQW/graph.json","fetch_events":"https://pith.science/api/pith-number/CDANHIZHURFPXJLAYQB3MIFOQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW/action/storage_attestation","attest_author":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW/action/author_attestation","sign_citation":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW/action/citation_signature","submit_replication":"https://pith.science/pith/CDANHIZHURFPXJLAYQB3MIFOQW/action/replication_record"}},"created_at":"2026-05-21T21:03:57.678046+00:00","updated_at":"2026-05-21T21:03:57.678046+00:00"}