{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GRVUFVGWALKRR72YYKGZ653R3T","short_pith_number":"pith:GRVUFVGW","canonical_record":{"source":{"id":"2306.09547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T23:28:45Z","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"title_canon_sha256":"c8670128d1f49a2b423818a14ab418972c3396671d405b0db35fc7c15a1d6509","abstract_canon_sha256":"6b0abe733d4d5b11f79b834edb6eb19260097613914694dac0f6dc6b2c55d2b3"},"schema_version":"1.0"},"canonical_sha256":"346b42d4d602d518ff58c28d9f7771dced1ee34b5b5e162cb630d9033096d10e","source":{"kind":"arxiv","id":"2306.09547","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09547","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09547v2","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09547","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"GRVUFVGWALKR","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"GRVUFVGWALKRR72Y","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"GRVUFVGW","created_at":"2026-07-05T07:50:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GRVUFVGWALKRR72YYKGZ653R3T","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T23:28:45Z","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"title_canon_sha256":"c8670128d1f49a2b423818a14ab418972c3396671d405b0db35fc7c15a1d6509","abstract_canon_sha256":"6b0abe733d4d5b11f79b834edb6eb19260097613914694dac0f6dc6b2c55d2b3"},"schema_version":"1.0"},"canonical_sha256":"346b42d4d602d518ff58c28d9f7771dced1ee34b5b5e162cb630d9033096d10e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:50.705544Z","signature_b64":"s9NfiH5h3oakUOgPSrHk/FRkx1uWZo9/SETWzfr3bL3Qd6qK0KUznJm9q3e27JloBtCeE08ZUfMzR/IyUAS7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"346b42d4d602d518ff58c28d9f7771dced1ee34b5b5e162cb630d9033096d10e","last_reissued_at":"2026-07-05T07:50:50.705089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:50.705089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09547","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sntbte6+Fd8urHg9I4M1kqLz22y7wLCOVFbiU7lS6duwTyzswDe1tHH1Sys9mOZfFO7igPd9cTr6vDKtubVAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:38:44.121072Z"},"content_sha256":"92af554afe9b5b0b7c861332cd654f184e742e9605a995b96fa3fd939bf1b163","schema_version":"1.0","event_id":"sha256:92af554afe9b5b0b7c861332cd654f184e742e9605a995b96fa3fd939bf1b163"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GRVUFVGWALKRR72YYKGZ653R3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training generative models from privatized data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ayfer \\\"Ozg\\\"ur, Daria Reshetova, Wei-Ning Chen","submitted_at":"2023-06-15T23:28:45Z","abstract_excerpt":"Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport - a popular regularization method in the literature that has often been leveraged for its computational benefits - enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09547","kind":"arxiv","version":2},"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/2306.09547/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":"2026-07-05T07:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i0cJt39835mQWfAgt5BB6nUzU3+DlxHrNQdiz0Ebfz7+pU+QnDuzskYYRP49Xn0+z8gF7k3CLxlkbdVCS1NcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:38:44.124151Z"},"content_sha256":"09a7f7e8df80b0048ac78b23318de0129ed950e2e4975e69a00a6ac8f312d4c3","schema_version":"1.0","event_id":"sha256:09a7f7e8df80b0048ac78b23318de0129ed950e2e4975e69a00a6ac8f312d4c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRVUFVGWALKRR72YYKGZ653R3T/bundle.json","state_url":"https://pith.science/pith/GRVUFVGWALKRR72YYKGZ653R3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRVUFVGWALKRR72YYKGZ653R3T/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":"2026-08-14T15:38:44Z","links":{"resolver":"https://pith.science/pith/GRVUFVGWALKRR72YYKGZ653R3T","bundle":"https://pith.science/pith/GRVUFVGWALKRR72YYKGZ653R3T/bundle.json","state":"https://pith.science/pith/GRVUFVGWALKRR72YYKGZ653R3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRVUFVGWALKRR72YYKGZ653R3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GRVUFVGWALKRR72YYKGZ653R3T","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":"6b0abe733d4d5b11f79b834edb6eb19260097613914694dac0f6dc6b2c55d2b3","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T23:28:45Z","title_canon_sha256":"c8670128d1f49a2b423818a14ab418972c3396671d405b0db35fc7c15a1d6509"},"schema_version":"1.0","source":{"id":"2306.09547","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09547","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09547v2","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09547","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"GRVUFVGWALKR","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"GRVUFVGWALKRR72Y","created_at":"2026-07-05T07:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"GRVUFVGW","created_at":"2026-07-05T07:50:50Z"}],"graph_snapshots":[{"event_id":"sha256:09a7f7e8df80b0048ac78b23318de0129ed950e2e4975e69a00a6ac8f312d4c3","target":"graph","created_at":"2026-07-05T07:50:50Z","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/2306.09547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport - a popular regularization method in the literature that has often been leveraged for its computational benefits - enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the paramet","authors_text":"Ayfer \\\"Ozg\\\"ur, Daria Reshetova, Wei-Ning Chen","cross_cats":["cs.CR","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T23:28:45Z","title":"Training generative models from privatized data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09547","kind":"arxiv","version":2},"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":"sha256:92af554afe9b5b0b7c861332cd654f184e742e9605a995b96fa3fd939bf1b163","target":"record","created_at":"2026-07-05T07:50:50Z","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":"6b0abe733d4d5b11f79b834edb6eb19260097613914694dac0f6dc6b2c55d2b3","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T23:28:45Z","title_canon_sha256":"c8670128d1f49a2b423818a14ab418972c3396671d405b0db35fc7c15a1d6509"},"schema_version":"1.0","source":{"id":"2306.09547","kind":"arxiv","version":2}},"canonical_sha256":"346b42d4d602d518ff58c28d9f7771dced1ee34b5b5e162cb630d9033096d10e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"346b42d4d602d518ff58c28d9f7771dced1ee34b5b5e162cb630d9033096d10e","first_computed_at":"2026-07-05T07:50:50.705089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:50.705089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s9NfiH5h3oakUOgPSrHk/FRkx1uWZo9/SETWzfr3bL3Qd6qK0KUznJm9q3e27JloBtCeE08ZUfMzR/IyUAS7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:50.705544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09547","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92af554afe9b5b0b7c861332cd654f184e742e9605a995b96fa3fd939bf1b163","sha256:09a7f7e8df80b0048ac78b23318de0129ed950e2e4975e69a00a6ac8f312d4c3"],"state_sha256":"e5b4f3227e97e66b4ff9e871cac7958d1e08a8fec89c83d383d19bd50918b5cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GkqzMBILpJF0XbWzvlOCGoVC4mat1fU2U9G26a1nXuTbniVCtCV2GIZ5e/+GYz678S3Ed/wRTmxp25O7/4+vCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:38:44.135177Z","bundle_sha256":"0869c91590a026c102400c2694687145f40f3df10a4d0f4f5b9df0040d5c094f"}}