{"as_of":"2026-08-10T06:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a93df325141e318a39ad0de5d97c39ca6dc1a9e150fdf09149893a0ee5d78d76","coverage":[{"denominator":120,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T04:12:46.348120Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.03668/citation-record","integrity":"/paper/2502.03668/integrity","json":"/paper/2502.03668/citation-record.json","paper":"/paper/2502.03668"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.788817Z","title":"Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.788817Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0bc4fe32f00a859e22126a0ab2523e5a5720ff1dac5e670b9751cc34397efeef","observation_id":"2093ac3b-396f-4de8-9fcf-7b15f731d028","resolution":{"observed_at":"2026-08-09T04:12:45.788817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.794642Z","title":"Counterfactual Fairness in Synthetic Data Generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.794642Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:5591a66a5993875968d1af997477e7d73fe7ac5f337001a6d324509910956464","observation_id":"1269de77-02c6-43e6-bf18-3cc4d424f414","resolution":{"observed_at":"2026-08-09T04:12:45.794642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.800096Z","title":"Differentially Private Mixture of Generative Neural Networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.800096Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:b718affacfe48e8dbda798595f66cfcd5a01e08e01a593d952aa961728511af1","observation_id":"3550bd46-62bb-4f88-8870-5c17799a036b","resolution":{"observed_at":"2026-08-09T04:12:45.800096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01331","last_updated":"2021-02-22T07:48:49Z","snapshot_observed_at":"2026-08-10T03:56:04.433356Z","submitted_at":"2019-09-03T17:57:07Z","title":"Generalization in Transfer Learning","version":2},"cited_work":{"arxiv_id":"1909.01331","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.01331","snapshot_observed_at":"2026-08-09T04:12:46.630709Z","title":"Generalization in Transfer Learning","venue":"cs.LG","work_id":"5ac17f01-dd52-4273-adcc-2f73cc2c178f","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.805771Z"},"links":{"cited_paper":"/paper/1909.01331","citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:4434f7537b8d8f8ab717e5f06c6810995fb0cd4d23ddd14a429b092879e16a49","observation_id":"cb145171-9abb-4fdc-90b8-c7506219c3ab","resolution":{"observed_at":"2026-08-09T04:12:46.637469Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.812265Z","title":"Differential privacy synthetic data generation using WGANs, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.812265Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:56b164cafd0e2542bd87adf77abf3b498254565da16e2fc533ff1d99b24a4989","observation_id":"cf2e4e7b-5faa-4c2c-ba00-9984c73d4e3e","resolution":{"observed_at":"2026-08-09T04:12:45.812265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.817272Z","title":"Wasserstein Generative Adversarial Networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.817272Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0f11a8efd119d710c48fe3ad49cb9308e6f3fab672d8af8cc5abb7acdbf47887","observation_id":"c6873bbe-efe2-4051-adae-50fb4ad65e93","resolution":{"observed_at":"2026-08-09T04:12:45.817272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.827482Z","title":"Scott Armstrong and Fred Collopy","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.827482Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:051341ecb594c7d57f6fc2ed75599bd9d0f426a5237abb231033825105b5c2b7","observation_id":"fdc68264-6cea-423e-8aea-c4970192c33d","resolution":{"observed_at":"2026-08-09T04:12:45.827482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.833370Z","title":"A White-Box Generator Membership Inference Attack Against Generative Models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.833370Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:53543819ec014f753f17b72373e813836a3bd679eab3331aa9c3226b358b2052","observation_id":"7fccf982-0638-4ff0-b843-950c2e10894e","resolution":{"observed_at":"2026-08-09T04:12:45.833370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.838493Z","title":"Differential Privacy Has Disparate Impact on Model Accuracy","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.838493Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:fee5c6481f559028ba373de05c5df104a9b815b49d346de68048303af602b709","observation_id":"bb18130f-84a0-48e5-9311-e48cc625af68","resolution":{"observed_at":"2026-08-09T04:12:45.838493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.844313Z","title":"Beaulieu-Jones, Zhiwei Steven Wu, Chris Williams, Ran Lee, Sanjeev P","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.844313Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:bca750bc177ca9e5a313366a4f0c961ad77df25e627f0aa0abd6120434e28fff","observation_id":"a79a628b-e313-4cb8-8a68-7bb1b17285f2","resolution":{"observed_at":"2026-08-09T04:12:45.844313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.849302Z","title":"Privacy and synthetic datasets","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.849302Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:3e93c91f109f3be6656e7a31c1f82a83497345d11a61b5d54210ecbe72c04807","observation_id":"559cce25-9324-4164-ac5a-a4141f09a051","resolution":{"observed_at":"2026-08-09T04:12:45.849302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.854323Z","title":"Assessing Differentially Private Variational Autoencoders Under Membership Inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.854323Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:df1c2a30f3b2f4c2cccf80c58e2935cd54bf28dfc5ddfd1fef642a802bf8a893","observation_id":"e5de2e55-c8bc-4f3a-81f4-2d5a04f48c62","resolution":{"observed_at":"2026-08-09T04:12:45.854323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.859086Z","title":"Private GANs, Revisited","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.859086Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:ffc55c31439d9a46f64ddb9349fde6dc4a5d494e1715870c04ffd6f5f44a74bd","observation_id":"badfb361-e315-45c9-b4e0-7022f82999d9","resolution":{"observed_at":"2026-08-09T04:12:45.859086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.863829Z","title":"SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.863829Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:849f52bc4108fdfda6e5551a1eb56e0b74b64550cc4152cc3cb46a7b08595da2","observation_id":"dbeb20ff-6d71-47aa-8f55-21f18a681447","resolution":{"observed_at":"2026-08-09T04:12:45.863829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.868910Z","title":"Generative Adversarial Networks: A Survey Toward Private and Secure Applications","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.868910Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:736b34f76b43e9c9381b0cba7915704f1a4a0c1234e372e994dab601ca32e832","observation_id":"d9445916-dd65-4ca6-9bc8-335ede1e57c8","resolution":{"observed_at":"2026-08-09T04:12:45.868910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.873694Z","title":"GS-WGAN: a gradient-sanitized approach for learning differentially private generators","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.873694Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:9c29f8ac88a22833aa3b829f2ce414a457acb1f5152ddd17b617baadad0ef31e","observation_id":"9b94deb3-bf45-4a74-ba87-058e6056c961","resolution":{"observed_at":"2026-08-09T04:12:45.873694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.878518Z","title":"GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.878518Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:bd3465f21328452f0220cd69326b5e2cfe36da160999faf67989f6b23b0be2d0","observation_id":"0c4ed290-f166-4109-8295-3595910e7731","resolution":{"observed_at":"2026-08-09T04:12:45.878518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.883344Z","title":"Differentially Private Generative Adversarial Networks with Model Inversion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.883344Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:8c9991d5378cb0bb7cc40c52255a2bbeb4383bc4fa928dc6256e5bc068c8bb5e","observation_id":"4d61fba2-f260-4f39-83f2-bc4ab1096393","resolution":{"observed_at":"2026-08-09T04:12:45.883344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.888358Z","title":"Generating a trading strategy in the financial market from sensitive expert data based on the privacy-preserving generative adversarial imitation network","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.888358Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0e8bb7602053b1831af071f6b9d3318cae7cc41888a8226ef0c04f484dfc758d","observation_id":"5320ad18-16d4-464c-b2e0-367f72a0fe47","resolution":{"observed_at":"2026-08-09T04:12:45.888358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.893549Z","title":"VGAN-Based Image Representation Learning for Privacy- Preserving Facial Expression Recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.893549Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:32e28dce8d1eae99e0b07f63e854397f3fc65a5cc98566f9a988971adad69892","observation_id":"6736780c-2fc6-4596-8fc0-c531e5dbfc34","resolution":{"observed_at":"2026-08-09T04:12:45.893549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.900122Z","title":"PAR-GAN: Improving the Generalization of Generative Adversarial Networks Against Membership Inference Attacks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.900122Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:fa516e4d4ec724af83e65c6d55bf4ffc70c4ef24182c4669df5821b67a06eea9","observation_id":"25cfce0f-88de-46ec-a1b6-a1a115f547fb","resolution":{"observed_at":"2026-08-09T04:12:45.900122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.906047Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.906047Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:71d702083f9cef06c153dab167a236d152be037b76173aeae302d107fd08d155","observation_id":"a7697d00-6deb-4362-a16e-31a6e39845a0","resolution":{"observed_at":"2026-08-09T04:12:45.906047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.912634Z","title":"Suriyakumar, Natalie Dullerud, Shalmali Joshi, and Marzyeh Ghassemi","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.912634Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:25bb2780f2e88d36dc1e4d67379a479cac751a36ba8a0385914b0003a37c8ea3","observation_id":"4d060b0d-99ab-49cd-8249-9c0178066e79","resolution":{"observed_at":"2026-08-09T04:12:45.912634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.919199Z","title":"Generating multi-label discrete patient records using generative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.919199Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:2123818038d3218c3d9e0e3b0446654d581849a37bf2da0cb596f2d1391f991f","observation_id":"e56f35c5-d99c-442a-b09f-d54d6bbdde94","resolution":{"observed_at":"2026-08-09T04:12:45.919199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.925096Z","title":"Croft, Jörg-Rüdiger Sack, and Wei Shi","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.925096Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:6938b2204466cc9fec27e53ea1393170c8008e1170d38f172768219af9e2209e","observation_id":"71fa6951-4323-43b3-ba55-bbb381a6c7e0","resolution":{"observed_at":"2026-08-09T04:12:45.925096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.930765Z","title":"ArcFace: Additive Angular Margin Loss for Deep Face Recognition","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.930765Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0805efa80dddd7a0bf1b597987013d51a29c7e08a2d56998d4b89df965e86c26","observation_id":"af3b472f-8838-4364-b16a-3617fed6238b","resolution":{"observed_at":"2026-08-09T04:12:45.930765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.936353Z","title":"A cosine similarity-based negative selection algorithm for time series novelty detection","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.936353Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:b8ed90718c657ced221b921986264f64e01db5e530ab4be6ee54dcc002a2cb35","observation_id":"8bf291ef-cbe8-43bb-ae4c-7868053e80ef","resolution":{"observed_at":"2026-08-09T04:12:45.936353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.941289Z","title":"Identifying and handling data bias within primary healthcare data using synthetic data generators","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.941289Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:024fc3cd0b99d5b735981730265a92af41a0f62219fdbd870fc3b2e6dfec737a","observation_id":"259673cd-9b3f-400f-9671-e3dd850fedba","resolution":{"observed_at":"2026-08-09T04:12:45.941289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.946194Z","title":"Differential Privacy: A Survey of Results","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.946194Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:71cde5bd4b30f9ec836f9c1080c91540ce892160b8242d76fae2c602aaa08696","observation_id":"37e89e1d-c0f0-4692-a8f3-2784b3b1d585","resolution":{"observed_at":"2026-08-09T04:12:45.946194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.951395Z","title":"A survey of differentially private generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.951395Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0d70f35438f4db4c062d69c325b8ce650af04f5e6230c705604b873731adf69c","observation_id":"55f02c1d-bb12-47e8-aa4f-1fee96e147b2","resolution":{"observed_at":"2026-08-09T04:12:45.951395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.956306Z","title":null,"venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.956306Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:5fe8d6afe3bd01435d3ecab5d2ca6103e12bacab022432d4892d00c6e032be99","observation_id":"6e4aca64-a4ca-48a4-a224-446ef614e693","resolution":{"observed_at":"2026-08-09T04:12:45.956306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.961636Z","title":"Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.961636Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:c2dfc7c980ef247e61ff85c6d22ce7657a4681eb02073f9799ba5f5534dbc494","observation_id":"3ed5dddb-1f11-4879-b28f-0f3b190c8816","resolution":{"observed_at":"2026-08-09T04:12:45.961636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.967938Z","title":"Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.967938Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:01eff7ad87ef205e96e346387ebaa320f8e1425216967c469240c18689cdb1b0","observation_id":"212d37d5-4b57-4101-8292-3dbd507dbac0","resolution":{"observed_at":"2026-08-09T04:12:45.967938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.973775Z","title":"Live Face De-Identification in Video","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.973775Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:c5d99fb82e51553a1d3fb5d1ecea06f6aba75d0278d63d6da89b227582c960d4","observation_id":"12a5315f-2c44-4ac7-9ca3-e848b2e23d5b","resolution":{"observed_at":"2026-08-09T04:12:45.973775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.978908Z","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?, November 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.978908Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:82812ac4e5d5e4d2738092ba5f46836bc90e92e0bc5003de05c82bda7c7edb9e","observation_id":"870c6a5c-52f1-47eb-86d0-1ccef38b5f43","resolution":{"observed_at":"2026-08-09T04:12:45.978908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.983833Z","title":"Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.983833Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:dac6af16e437270c51b2ebada4ddcab30344672dac7b8a06f13a4cc58ebaf7b8","observation_id":"25f2bc3b-bfb2-4f5b-b98f-9f0b43fa3670","resolution":{"observed_at":"2026-08-09T04:12:45.983833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.988919Z","title":"Graphical vs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.988919Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:9142497b60afe4c3655ab01c63014f2f05ab62a54e32bac8e43eb6f46977fb58","observation_id":"5060f4aa-f084-42b6-ab36-e1cd776f1c1f","resolution":{"observed_at":"2026-08-09T04:12:45.988919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.993856Z","title":"A Unified Framework for Quantifying Privacy Risk in Synthetic Data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.993856Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:88fe4f0ddbc330ec486eeaf0aff77014961e732b5e1ef731197f36fbe8456517","observation_id":"d950025d-a378-4033-957d-765c40e6eb54","resolution":{"observed_at":"2026-08-09T04:12:45.993856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:45.999036Z","title":"Generation and evaluation of synthetic patient data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:45.999036Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:e96afc371622c4ebcd64142352b4795466a40c913750644792dd37147ae86545","observation_id":"110b3b82-548b-439e-91c8-a612108b505d","resolution":{"observed_at":"2026-08-09T04:12:45.999036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.004965Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.004965Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:46a4e770e84dbd25f15290570b3d14b5e7437c39c60dd7626c9bc13987366952","observation_id":"04c60dcc-e850-4411-82b3-6105b5af0478","resolution":{"observed_at":"2026-08-09T04:12:46.004965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.010466Z","title":"Improved training of wasserstein gans","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.010466Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:a68e1850c6d38ef8996719eb2a65e8ec9d1f51433fa758459266535ffa14dc2b","observation_id":"58037375-2cae-4f5a-8a25-e3815a51db19","resolution":{"observed_at":"2026-08-09T04:12:46.010466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:48.079341Z","title":"Utility-Aware Synthesis of Differentially Private and Attack-Resilient Location Traces","venue":null,"work_id":"b7c2fd10-bf7c-45b8-a3a0-150c0e8ae020","year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.016923Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:d023f68309e0202eb006dde441b7921c68d3c53d48feac5dbcc9bdd54c28b30d","observation_id":"5248c4e1-1078-4f3b-bf9c-965758cc3517","resolution":{"observed_at":"2026-08-09T04:12:48.085403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:48.060844Z","title":"Differentially private GANs by adding noise to Discriminator’s loss","venue":null,"work_id":"7f740e59-16b1-4b39-a0d9-990d95efe4a8","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.022540Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:7d61f349be4ad11d9f29c63ce83f932e8c41fab927ad16e92f579978eb70c36d","observation_id":"68af2541-c019-47bd-a980-1e552d232be3","resolution":{"observed_at":"2026-08-09T04:12:48.067379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:48.040713Z","title":"LOGAN: Membership Inference Attacks Against Generative Models","venue":null,"work_id":"7b9ba1ef-2bb7-4c0a-ae35-5d3e1fd50934","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.027511Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:19c0cf609fe558b3d5bda36cc495b6d818fdd1ce8ce79e838a16c7053be6b1ce","observation_id":"da4639e2-04a6-4e18-bf80-954d011966c5","resolution":{"observed_at":"2026-08-09T04:12:48.048087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.08500","last_updated":"2018-01-12T14:05:44Z","snapshot_observed_at":"2026-07-06T05:48:30.254634Z","submitted_at":"2017-06-26T17:45:23Z","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.08500","snapshot_observed_at":"2026-08-09T04:12:46.033701Z","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, January 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.033701Z"},"links":{"cited_paper":"/paper/1706.08500","citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0cdf0b4ba8cdae0b246fc15354a4bcfbd5c78b4ebfe29ccc63bd5102f7476549","observation_id":"53db047a-414c-401e-8d5e-0225335610cb","resolution":{"observed_at":"2026-08-09T04:12:46.033701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:48.019336Z","title":"Monte carlo and reconstruction membership inference attacks against generative models","venue":null,"work_id":"012f7f34-1d0f-4ed3-b63f-6b5a7bb1c1ae","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.039424Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:a77d8d6101a039b3cf526e555a2b765e24a1df984ef5250580e99f6c09eff616","observation_id":"a7dd6db3-b654-4ac2-8a6d-87b69bf7e35d","resolution":{"observed_at":"2026-08-09T04:12:48.026219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.993559Z","title":"DP-GAN: Differentially private consecutive data publishing using generative adversarial nets","venue":null,"work_id":"5f066dc8-5fd9-4feb-a376-b2bc05d30f08","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.044736Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0650ff3ee48386517a9f4be7fe6acf149f19ee29dbab5f7d4525905d00284ae0","observation_id":"971c67a1-f4dd-46fa-899e-5ea196258da7","resolution":{"observed_at":"2026-08-09T04:12:48.001444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.971722Z","title":"Cohen, Owen Daniel, Andrew Elliott, James Geddes, Callum Mole, Camila Rangel-Smith, and Lukasz Szpruch","venue":null,"work_id":"0e7af53c-1f75-4764-85a9-d343115df217","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.049605Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:1a583663df2b2c21b298c1ea7300473fa226c00636f1b90184b629b192cf6b5e","observation_id":"a2941850-272c-4640-86c6-f68b1fca0957","resolution":{"observed_at":"2026-08-09T04:12:47.977913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.950613Z","title":"TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing","venue":null,"work_id":"b57023cf-af4a-40a4-ae7d-0afb0ac333d1","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.054779Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:cc930c505e5c83a61b8427363ab6425d6a5d8fcc23f05a772f1620d5142ffaae","observation_id":"b4440430-367c-47aa-99f9-eefde2cd8e72","resolution":{"observed_at":"2026-08-09T04:12:47.957564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.925808Z","title":"Model Extraction and Defenses on Generative Adversarial Networks, January 2021","venue":null,"work_id":"3373a05e-50b3-4652-8ead-d6f27955cd12","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.059879Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:3ce905f72683c30b3b83fcde0aa419b95bbd278d5d7d851c82e21e3ba9780d03","observation_id":"430c0bad-6ee7-4512-9edd-6aa04d596211","resolution":{"observed_at":"2026-08-09T04:12:47.935457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.879479Z","title":"An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models","venue":null,"work_id":"3d0a59bc-38f5-40a0-95fc-6aa9af62d9b7","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.064729Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f872f8e2e61fd9e69452c13c90caba6957b733401431eb97fe89e8c465468159","observation_id":"8dba90c9-faf6-465b-a947-1680adc473a3","resolution":{"observed_at":"2026-08-09T04:12:47.897814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.860668Z","title":"Synthetic and Private Smart Health Care Data Generation using GANs","venue":null,"work_id":"49cb733d-b5f5-4128-83f0-17efb270ec32","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.069563Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f4431d780f3f1fb7f1b243ed6afd8ad5d982c0ba774f9439468b5dadd2c5b6ad","observation_id":"6d786280-33e8-4a26-ac69-2d9b1ac4f85b","resolution":{"observed_at":"2026-08-09T04:12:47.866708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.839633Z","title":"DP$^2$-V AE: Differentially Private Pre-trained Variational Autoencoders, August 2022","venue":null,"work_id":"893d66e5-cbbf-47ca-8fea-fa695ed7d5df","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.074551Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:9512d46ae4636d9647eb370c976760d157aef4c30e903c411a9bfee647d733db","observation_id":"8e20d01e-29c1-4c15-a37f-da2297a64fc5","resolution":{"observed_at":"2026-08-09T04:12:47.845940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.816369Z","title":"Pruning’s Effect on Generalization Through the Lens of Training and Regularization","venue":null,"work_id":"6f0844c6-d65d-4cd0-932e-1a2ba66e0281","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.079900Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:67e8e88cf448dc5b36825e57bf131b49f4a09f0f4df88ad3ab317954a1b87e42","observation_id":"9461d8f3-900c-4bc5-8fd8-410e46829e9e","resolution":{"observed_at":"2026-08-09T04:12:47.826494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.792815Z","title":"PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees","venue":null,"work_id":"5e70c458-f8ee-4e0e-8085-67bd9894e2b8","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.084669Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:344903e6b22f1dd53a80bde3af11ebeece79e9609f4979328b70c1ef10b39bc9","observation_id":"05bcb1d2-8316-4915-958c-fa8f34bfe98c","resolution":{"observed_at":"2026-08-09T04:12:47.799340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10196","last_updated":"2018-02-26T15:33:34Z","snapshot_observed_at":"2026-07-06T06:06:26.276752Z","submitted_at":"2017-10-27T15:28:35Z","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10196","snapshot_observed_at":"2026-08-09T04:12:46.089734Z","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation, February 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.089734Z"},"links":{"cited_paper":"/paper/1710.10196","citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f64d4e90ac47ee0e8739872371e7cd8ad9a160c334a0b00476b47499e7434951","observation_id":"a43e63a6-86af-4e3a-8326-37a5b6fff870","resolution":{"observed_at":"2026-08-09T04:12:46.089734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.771295Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"16ded3f9-3a91-4ecd-bb76-042add0de56e","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.095159Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:aba5fb261cde2974acae57642c7d66862bbebe9e221f68afddddae80dbbed6ff","observation_id":"282ed6b2-96c7-42b0-b429-39b44815e87b","resolution":{"observed_at":"2026-08-09T04:12:47.778661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.748085Z","title":"OCT-GAN: Neural ODE-based Conditional Tabular GANs","venue":null,"work_id":"e95db59c-f205-4681-acc1-b8f989658dcf","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.100222Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:a1590b155fb7197adb5cd0c1bddf34d64f2ae52f8d5367f3664aeff232f741f3","observation_id":"a9dae688-ace1-4488-a71a-cc5bafc07c5e","resolution":{"observed_at":"2026-08-09T04:12:47.755103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.725374Z","title":"Stochastic gradient vb and the variational auto-encoder","venue":null,"work_id":"9a256ae4-ddbe-48d9-9568-4c08833c46c5","year":2014},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.105033Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:65caae13230ea818f241393f884d557a3ae08ec271d2e2165930e52b12394216","observation_id":"5de07715-22ce-4270-9307-4774ea7bba7a","resolution":{"observed_at":"2026-08-09T04:12:47.731527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.700842Z","title":"PriveTAB: Secure and Privacy- Preserving sharing of Tabular Data","venue":null,"work_id":"9464dd91-df1f-4291-b226-6f3456d0b7cc","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.110675Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:50949c3cab10cedbae7b6bf62c7ae44b9523a4385231e4d0175bb70ddad494e5","observation_id":"4ae29235-e43f-4662-b832-96f8a1eb3651","resolution":{"observed_at":"2026-08-09T04:12:47.707403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.682806Z","title":"Unnoticeable synthetic face replacement for image privacy protection","venue":null,"work_id":"792b38ff-50dd-4182-99d6-452c41f826c9","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.115976Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:20cf3d78fd0917a669e773fbb73edb9af232d72a2a774ec0e1c9b8342c35611e","observation_id":"bed95510-02ef-4976-bb19-76dde8958f84","resolution":{"observed_at":"2026-08-09T04:12:47.688206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.660308Z","title":"DTGAN: Differential Private Training for Tabular GANs, July 2021","venue":null,"work_id":"6ea5149e-826a-489f-9475-51dab5662e03","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.121387Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:40e78aa696a1fd707f6ca7d6fa763ab250b4322c2012219c6d48adae0a7002e3","observation_id":"785ca172-1d2c-4682-88d6-8634e76650b2","resolution":{"observed_at":"2026-08-09T04:12:47.666667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.637345Z","title":"Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis","venue":null,"work_id":"1f8984ad-25f2-40b9-ae0e-4131a249c86b","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.126431Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:a46ed3073dfc88ea996adac1119bbd57c642d5801da8b458038e203bc8b75932","observation_id":"863aca46-cdae-4947-8346-f86c9542572e","resolution":{"observed_at":"2026-08-09T04:12:47.643912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.611274Z","title":"Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median","venue":null,"work_id":"8247f6b7-4d2a-42fe-977e-710d6fb1fe17","year":2013},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.131225Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:dacf53997cd95c076009d1aa642bcbd4faeebd78b45c2f2193a887b59dfc0a29","observation_id":"8d74932c-0a0e-45ba-8e43-a42b334e5807","resolution":{"observed_at":"2026-08-09T04:12:47.618535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.585908Z","title":"Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what? PLOS ONE, 12(8):e0183250, August 2017","venue":null,"work_id":"5c7aa2ce-020e-49d7-b4c2-77eef8e83b0b","year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.136168Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:b8d0a9e2833154d229f7553feade23555f05b33af22454dcfca5dd991f13411c","observation_id":"3e9cb5ad-ce79-4791-af1f-89e637075194","resolution":{"observed_at":"2026-08-09T04:12:47.597682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.557554Z","title":"Privacy-preserving lightweight face recognition.Neurocomputing, 363(C):212–222, October 2019","venue":null,"work_id":"6e5ed5dc-f9ee-40a4-84b6-f20f138f346b","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.141560Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:5f8abfd3bbe58f35329840e7ebc07fa6b180f3d59a4d6cc45a9d6d11cf78cb4d","observation_id":"dee6b449-09c6-434d-a780-1bd126069650","resolution":{"observed_at":"2026-08-09T04:12:47.564631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.529055Z","title":"Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images","venue":null,"work_id":"83215bd8-bac7-4159-b4e9-080f689f211d","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.146669Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:dbd168a84f8107898a6e146187d33e683f859b4a1a024d5b5ebb735802e117c8","observation_id":"a3735fc8-6242-4250-a860-29aa947fc3c1","resolution":{"observed_at":"2026-08-09T04:12:47.537332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.508303Z","title":"Performing Co-membership Attacks Against Deep Generative Models","venue":null,"work_id":"4cd12bcf-4687-4da2-b576-e06b9a54270e","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.151850Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:21e7066f29c2f6aa6fe6d07bb4ffca0346627cc0e7f299261b3808880f1e0e74","observation_id":"3900782f-0d4f-48ec-8fc8-192fa0aa44a9","resolution":{"observed_at":"2026-08-09T04:12:47.515389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.488134Z","title":"Yu, and Yi Wu","venue":null,"work_id":"f4a2395c-f4c6-4c45-b24e-14f1b827bbbd","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.156663Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:997ea7c783f3945e4b28e78eab8f71ed76e72dd15c82d08a2dfe909e917ca2ea","observation_id":"f3ca9385-b058-47e0-939f-d56fb08c1618","resolution":{"observed_at":"2026-08-09T04:12:47.493574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.469345Z","title":"G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators","venue":null,"work_id":"fd71ae47-46c5-495c-be0b-4bd4875c7f86","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.161722Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:4f2580b537bc4a7510bd58e52a4156eeefea2fdf1eab991e9ad0c7bd2c6f101e","observation_id":"904fc5f8-2505-4dcd-bf38-ba2a737a7a41","resolution":{"observed_at":"2026-08-09T04:12:47.475586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.441780Z","title":"POSTER: A Unified Framework of Differentially Private Synthetic Data Release with Generative Adversarial Network","venue":null,"work_id":"30dc4517-0328-4829-9be0-3e13f2f4b934","year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.166637Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:e070c0e21e49dadcfbb2bc46af7ff7af1abed94aacd56555dc1e814223d29610","observation_id":"01f0008f-6b83-4205-afaa-a389637154ab","resolution":{"observed_at":"2026-08-09T04:12:47.455737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04062","last_updated":"2025-04-04T09:34:37Z","snapshot_observed_at":"2026-07-06T14:49:41.442616Z","submitted_at":"2023-02-08T13:59:31Z","title":"Machine Learning for Synthetic Data Generation: A Review","version":10},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04062","snapshot_observed_at":"2026-08-09T04:12:46.171445Z","title":"Machine Learning for Synthetic Data Generation: A Review, May 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.171445Z"},"links":{"cited_paper":"/paper/2302.04062","citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:1e49aa0fe045591d8b32be07e6f2b6663a71466f00ea4abf9ed95d27839297db","observation_id":"e099504f-46a5-4577-a4ca-9ed90b776ddc","resolution":{"observed_at":"2026-08-09T04:12:46.171445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.415451Z","title":"Vincent Poor","venue":null,"work_id":"429e3735-3034-488e-a901-6dd87053d8d2","year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.176895Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:e7afd8db50c13bda39ef5ee4a5734866949f57b877f32bfa8132d02b7e032ccb","observation_id":"5df3aafd-f503-4d6a-bac9-d2f530fb64cf","resolution":{"observed_at":"2026-08-09T04:12:47.426521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.395343Z","title":"CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks","venue":null,"work_id":"3ff8875b-69fb-4646-a7db-d9dd7a8e4505","year":2020},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.182483Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:8218d5ec465a43dea6d0a3cd8f75cf3b45be6f2f7603cb6c2af3d505c2f4fc7d","observation_id":"bdce4ad5-8f59-4f84-b1fb-8f1446b59a4a","resolution":{"observed_at":"2026-08-09T04:12:47.400768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.378348Z","title":"Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy","venue":null,"work_id":"4c9bacac-f66f-4b83-b217-173e9105d208","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.187601Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:90d1fde4fe4a2b1305a751c495856dcef7f85e33938fb566b9783fcc9fe47bd0","observation_id":"6a4e63c4-6c2f-4282-a39a-4fdcd6b6c84e","resolution":{"observed_at":"2026-08-09T04:12:47.383873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.361813Z","title":"A Probe Towards Understanding GAN and V AE Models, December","venue":null,"work_id":"f270096a-6c37-4949-b773-d47973de226b","year":null},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.192588Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:88c6d659c3cdf18db80c1708af187b6d97c4d31433730f406bbc3b6c8768dba8","observation_id":"ed4a9321-6ca4-4ffb-a112-8a535fc9175c","resolution":{"observed_at":"2026-08-09T04:12:47.367196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.343803Z","title":"Rényi Differential Privacy","venue":null,"work_id":"652af8d0-4a33-40b9-8581-fcd558a3696b","year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.203402Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:7fca2099cbf8856b502114df40d6d36620380fbd22b1c95bfc664e1783af2fa9","observation_id":"c037f2fa-6b77-4bc6-b7b7-0329c9dbaecb","resolution":{"observed_at":"2026-08-09T04:12:47.349075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1411.1784","last_updated":"2014-11-06T22:33:22Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-11-06T22:33:22Z","title":"Conditional Generative Adversarial Nets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.1784","snapshot_observed_at":"2026-08-09T04:12:46.208134Z","title":"Conditional Generative Adversarial Nets, November 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.208134Z"},"links":{"cited_paper":"/paper/1411.1784","citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:32804775804e8acd6a489c939edc0393a341ff4e67b4d72a79ab1e3166d16e25","observation_id":"f68af20f-66ab-4b86-b767-e31507c8684d","resolution":{"observed_at":"2026-08-09T04:12:46.208134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.327066Z","title":"Spectral Normalization for Generative Adversarial Networks","venue":null,"work_id":"84e19b5e-ca81-4de1-ac2d-0363945dac79","year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.213403Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:9f3f719cb4146ef4b7b96b9fe3accfadf9567e33f0a3ddddd7bdcfd4b9aa20bd","observation_id":"192dd9f7-57b8-4ff2-b6f1-e2899cdbe936","resolution":{"observed_at":"2026-08-09T04:12:47.332582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.308018Z","title":null,"venue":null,"work_id":"2543f5a1-16f0-43ab-8796-ae6989adb30f","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.218316Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:350eb42c9169ab5fd5048fb928db33cf1f2fe337806fb98119e3d81d8bb482d6","observation_id":"ed92e88c-2670-4c68-8a24-4943a2917508","resolution":{"observed_at":"2026-08-09T04:12:47.313755Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.289592Z","title":"DPD-InfoGAN: Differentially Private Distributed InfoGAN","venue":null,"work_id":"af7cb18c-5b2e-42d5-b0e5-0f0937103b3c","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.223491Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:3edfc87783e2b0b32339e5cb84dbb0d4880350852d9b2dfc8bddce2e19b7a2ce","observation_id":"1090a130-d3c5-4291-b9ee-a6a6e227756b","resolution":{"observed_at":"2026-08-09T04:12:47.294966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.272384Z","title":null,"venue":null,"work_id":"c3ce7022-0d9b-4611-8c14-2dcf4d33d2b7","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.231059Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:cd59692819b954ee92dcfd4a0cf6ce1d8451a583be718fa23d6c376464f82e0f","observation_id":"e0d74ef7-6a89-4417-bbf2-147132e90dbf","resolution":{"observed_at":"2026-08-09T04:12:47.277432Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.253703Z","title":"Automatic detection of outliers and the number of clusters in k-means clustering via Chebyshev-type inequalities","venue":null,"work_id":"811f1317-44f3-4f23-86ce-0264fe2300a5","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.236778Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:63fef7dc9f110b49d9a58414428cf578feeecc6dda4efddebd641c99aa3905a4","observation_id":"24e1758d-d1f1-436e-afdf-7500b06f9650","resolution":{"observed_at":"2026-08-09T04:12:47.259811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.231574Z","title":"On Utility and Privacy in Synthetic Genomic Data","venue":null,"work_id":"0c00217b-d0aa-4584-8b4b-e6a3da50ee50","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.242348Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:df19ac23e24bb70f0500f02b0cc94902d5fcf638e1ef3884e13801ac9123bae7","observation_id":"e6b904dc-a64c-400d-8e53-defb9f966a81","resolution":{"observed_at":"2026-08-09T04:12:47.239184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.212270Z","title":"Privacy-enhanced generative adversarial network with adaptive noise allocation","venue":null,"work_id":"51551548-b153-4113-ac92-66c37f817c97","year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.247621Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:3996301f548437f5e392e4b0a0434ce4dea1e6781f81c35dff32b2c992b503bb","observation_id":"f76f07f6-c9a3-44bf-a4da-7adcc592b721","resolution":{"observed_at":"2026-08-09T04:12:47.219540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.194591Z","title":"Scalable Private Learning with PATE","venue":null,"work_id":"fcf5f2c5-1d3c-4d2a-8bda-e26ded901bda","year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.254739Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:0ff07810125604bf44ab8e93e5f7fe1d7b518b9ee371dc42a61f643b50e577f8","observation_id":"c15464a5-ffd3-4266-afa4-b4152a7943ac","resolution":{"observed_at":"2026-08-09T04:12:47.200159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.176593Z","title":"Evaluating Differentially Private Generative Adversarial Networks Over Membership Inference Attack","venue":null,"work_id":"f107f521-e858-4b2d-b710-c780af44a94d","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.260181Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:6633ced0a6c7e223a1d8dd681be1047e469be740f612b061b062592dee5ad821","observation_id":"2b0ebfb0-d403-41fb-bd9a-c6c3d005920d","resolution":{"observed_at":"2026-08-09T04:12:47.182091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.157796Z","title":"Data synthesis based on generative adversarial networks","venue":null,"work_id":"d0c434b2-d0e2-4159-9daf-cdb8e06ce220","year":2018},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.266694Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f6375399da50bc39d5adf6a5eb110ef69d046967138be1c5218024c6cbc2f3b4","observation_id":"9d6c98ca-e55c-47e3-a806-f72164f117cb","resolution":{"observed_at":"2026-08-09T04:12:47.164122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.272489Z","title":"Unsupervised representation learning with deep convolutional generative adversarial networks, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.272489Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f68bc1907a413e302e685da1d1831100800c0e56fd3cf609acf965713d53df26","observation_id":"cf7d2506-91fb-41db-b11f-e600f10cda0e","resolution":{"observed_at":"2026-08-09T04:12:46.272489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.128893Z","title":"Improved Techniques for Training GANs","venue":null,"work_id":"3dfacd21-a14e-40f2-abb9-ae556a574ad8","year":2016},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.279234Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:e78204e9d9d6ae69a6755f6b513a2fcf163e85e5ae4e9028215c243d3860f2c3","observation_id":"cdc5cd49-7951-4f28-8e03-baf0d1e1a4e1","resolution":{"observed_at":"2026-08-09T04:12:47.134356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.111246Z","title":"Differentially-Private Text Generation via Text Preprocessing to Reduce Utility Loss","venue":null,"work_id":"f0213691-e8fd-4148-b07b-f613a8ae71c1","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.284542Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:7a078f7809d0846ac4fb870d5a8ca798fbb4dad989d920261edd83d47431e3a9","observation_id":"fd3292e4-9025-489e-a502-c6cd518f71db","resolution":{"observed_at":"2026-08-09T04:12:47.117977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.094625Z","title":"FaceNet: A unified embedding for face recognition and clustering","venue":null,"work_id":"7a5c41ec-8a38-4ddc-8814-e3c2ae567313","year":2015},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.289969Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:61fa617c376f1a4c4c184f1639c29adc55f25ccc035a10c7556815410e2cf8f7","observation_id":"fe32b96d-0450-4d4d-b3e8-b67d7df44c53","resolution":{"observed_at":"2026-08-09T04:12:47.099682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.078482Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"2d5434d1-ba35-4968-bdb2-ea929be3b5fc","year":2017},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.296182Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:f71def30dedb9bb46ede852d25c7c1c09538aca90e2103b2be0c10bcc33fbacc","observation_id":"741cc6a8-92d2-43a2-b242-6f34c8a7902f","resolution":{"observed_at":"2026-08-09T04:12:47.083591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.061598Z","title":"Synthetic Data – Anonymisation Groundhog Day","venue":null,"work_id":"8bb7e124-b410-4665-aa58-ff905532c28b","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.303796Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:428d1f1c4a8937ef567002d6d7e1af1a0ba133bc5f9f9dee218a80513d7b0f63","observation_id":"3afdc648-d930-45f0-b9df-a9996d2faa4f","resolution":{"observed_at":"2026-08-09T04:12:47.066627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.045554Z","title":"Adversarial Attacks Against Deep Generative Models on Data: A Survey","venue":null,"work_id":"95c84138-b170-463e-86f6-26613254c365","year":2023},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.313175Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:494957ddbe965574ca5fa4b709d73955c742d614d5d8bc771c5f32fc36357d63","observation_id":"c07a2c61-8fc1-44bf-87f0-327e614d1df6","resolution":{"observed_at":"2026-08-09T04:12:47.050839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.027421Z","title":"P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model","venue":null,"work_id":"a265b5a6-8963-4131-a5c2-1f09c8f45d64","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.320069Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:03785abaf529d23f9729afc7055184e4bb5a2b1875b7a47b1df4c9b1cab243af","observation_id":"ac5f680e-9404-41a1-9489-581ba229c88b","resolution":{"observed_at":"2026-08-09T04:12:47.033351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:47.010391Z","title":"Differ- entially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning","venue":null,"work_id":"1346345b-3946-4031-869d-ddc450d50cc1","year":2021},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.326936Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:23290028fb8598b46c302f6e644082024c6c32d8e13ed8cb915bcb06975c942c","observation_id":"d744297e-a9a1-42b4-9d3e-ba700fabfb8a","resolution":{"observed_at":"2026-08-09T04:12:47.015452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.993271Z","title":"Fairness and privacy preservation for facial images: GAN-based methods","venue":null,"work_id":"2ea222d9-04cc-4368-bf26-1960b0e9fb11","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.335164Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:413cc809b3abba26f0d178b97fab14a6c6c217906f9e30b39ce776ed5d3195cb","observation_id":"e41abc14-e553-4641-b48f-5bbe48156ae6","resolution":{"observed_at":"2026-08-09T04:12:46.998569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.976578Z","title":"Fox, and Chandan K","venue":null,"work_id":"0e901f71-38d6-4176-916e-21d56a8580f4","year":2022},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.341956Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:10a2a941e8f409058c9366265f9a248f0aa18cc3caf17361413e510eeb589aed","observation_id":"5187e263-704f-4fe2-9064-4bfcc491eaba","resolution":{"observed_at":"2026-08-09T04:12:46.982182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T04:12:46.960227Z","title":"DP-CGAN: Differentially Private Synthetic Data and Label Generation","venue":null,"work_id":"2a644dd1-51a5-4c24-b15e-d6da50908e3d","year":2019},"citing_paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-09T04:12:46.348120Z"},"links":{"citing_paper":"/paper/2502.03668"},"observation_digest":"sha256:dee6ae8a11ee7215e77c2cbc4008f0528d3a522bbfca6014adf0f366c2ff8214","observation_id":"5fb31851-163f-480e-8a8c-61f364b9c261","resolution":{"observed_at":"2026-08-09T04:12:46.965475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03668","last_updated":"2025-02-05T23:24:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:07:41.011260Z","submitted_at":"2025-02-05T23:24:43Z","title":"Privacy-Preserving Generative Models: A Comprehensive Survey"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":1,"verified_fuzzy":52},"total_outbound_references":120},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 120 outbound references and 0 inbound Pith citation observations for arXiv:2502.03668."}