{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5VRW2U2KRUVRIOPMPAHQSIDFPV","short_pith_number":"pith:5VRW2U2K","schema_version":"1.0","canonical_sha256":"ed636d534a8d2b1439ec780f0920657d65f5904650ac855e2a234843a9d2e196","source":{"kind":"arxiv","id":"2503.20846","version":1},"attestation_state":"computed","paper":{"title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.CR","authors_text":"Anil A Bharath, Kevin Yee, Viktor Schlegel, Zilong Zhao","submitted_at":"2025-03-26T16:06:33Z","abstract_excerpt":"Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or institutional reasons. This survey provides a comprehensive framework for understanding the landscape of privacy-preserving synthetic data, presenting the theoretical foundations of generative models and differential privacy followed by a review of state-of-the-art methods across tabular data, images, and text. Our synthesis of evaluation approaches highlights the fundamental trade-off between utility for down-stream "},"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":"2503.20846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-26T16:06:33Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"fd4862cb5cf848575175d8add9bd41b7782659297a58a1ddbbeaffd495ac9ac1","abstract_canon_sha256":"e4e0fc693947a86c6f686f39fbf6336418df575c825f26f1f9c4573e2f88c79f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:49.102792Z","signature_b64":"VFE9xE/DWz3yAiF+zt1sp0g30TVFHaUCr2pbHNpLnTVtfoOo5jD8klRJPFkaF7VyqnRhaV0EqMLZ1PGAuGzADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed636d534a8d2b1439ec780f0920657d65f5904650ac855e2a234843a9d2e196","last_reissued_at":"2026-07-05T10:39:49.102335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:49.102335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.CR","authors_text":"Anil A Bharath, Kevin Yee, Viktor Schlegel, Zilong Zhao","submitted_at":"2025-03-26T16:06:33Z","abstract_excerpt":"Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or institutional reasons. This survey provides a comprehensive framework for understanding the landscape of privacy-preserving synthetic data, presenting the theoretical foundations of generative models and differential privacy followed by a review of state-of-the-art methods across tabular data, images, and text. Our synthesis of evaluation approaches highlights the fundamental trade-off between utility for down-stream "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20846","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/2503.20846/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":"2503.20846","created_at":"2026-07-05T10:39:49.102392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20846v1","created_at":"2026-07-05T10:39:49.102392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20846","created_at":"2026-07-05T10:39:49.102392+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VRW2U2KRUVR","created_at":"2026-07-05T10:39:49.102392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VRW2U2KRUVRIOPM","created_at":"2026-07-05T10:39:49.102392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VRW2U2K","created_at":"2026-07-05T10:39:49.102392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.14594","citing_title":"SynBench: A Benchmark for Differentially Private Text Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02390","citing_title":"Differentially Private Synthetic Voltage Phasor Release for Distribution Grids","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV","json":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV.json","graph_json":"https://pith.science/api/pith-number/5VRW2U2KRUVRIOPMPAHQSIDFPV/graph.json","events_json":"https://pith.science/api/pith-number/5VRW2U2KRUVRIOPMPAHQSIDFPV/events.json","paper":"https://pith.science/paper/5VRW2U2K"},"agent_actions":{"view_html":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV","download_json":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV.json","view_paper":"https://pith.science/paper/5VRW2U2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20846&json=true","fetch_graph":"https://pith.science/api/pith-number/5VRW2U2KRUVRIOPMPAHQSIDFPV/graph.json","fetch_events":"https://pith.science/api/pith-number/5VRW2U2KRUVRIOPMPAHQSIDFPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV/action/storage_attestation","attest_author":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV/action/author_attestation","sign_citation":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV/action/citation_signature","submit_replication":"https://pith.science/pith/5VRW2U2KRUVRIOPMPAHQSIDFPV/action/replication_record"}},"created_at":"2026-07-05T10:39:49.102392+00:00","updated_at":"2026-07-05T10:39:49.102392+00:00"}