{"as_of":"2026-08-23T16:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:518708c0fcbdab56cc30ea7fb06bbd0992a975f4bb70ffa7057e981b786b5935","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T05:48:12.273148Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2602.01607/citation-record","integrity":"/paper/2602.01607/integrity","json":"/paper/2602.01607/citation-record.json","paper":"/paper/2602.01607"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T05:48:06.614581Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.614581Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:ae3204f2606ea8ab31bbb53f7e3c61e40b6244f8bef96eb93e9bda5fa9eb2eb3","observation_id":"b41466ab-5ebd-4249-8bf8-b9bc9e31512f","resolution":{"observed_at":"2026-08-03T05:48:06.614581Z","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":"2026-08-03T05:48:06.667508Z","title":"Census topdown: Differentially private data, in- cremental schemas, and consistency with public knowledge.US Census Bureau, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.667508Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:bb5d71c71853b86e2f5f4578e796e93b1c270782b075242d15bb39481f9dc1fc","observation_id":"fb6bdddd-ffdc-4474-a7c1-4085100db0f5","resolution":{"observed_at":"2026-08-03T05:48:06.667508Z","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":"2026-08-03T05:48:06.749239Z","title":"Differentially private assouad, fano, and le cam","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.749239Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:7fcce020d2f0d5efa067f536b2ce272d7db97af744680afc51cbcafa99ff6e14","observation_id":"acedc5f9-f11e-41b5-be29-ea51ed26c1db","resolution":{"observed_at":"2026-08-03T05:48:06.749239Z","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":"2026-08-03T05:48:06.805292Z","title":"Differ- entially private covariance estimation.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.805292Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:322f37cb56e957cfb50acdfa526ead8adef70ee73dcbad5fed54eabb914cd92c","observation_id":"d7776ba9-6844-466e-8d6d-9dab8dbecfc1","resolution":{"observed_at":"2026-08-03T05:48:06.805292Z","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":"2026-08-03T05:48:06.873464Z","title":"Wasserstein concentration of empirical measures for dependent data via the method of moments.arXiv preprint arXiv:2601.07228, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.873464Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:3ae9d70f811dafd17c6d7e9992969cd1d15756d71055fe001e9f725e4e334608","observation_id":"4ae470cb-3af5-4c34-b4f6-305808349b77","resolution":{"observed_at":"2026-08-03T05:48:06.873464Z","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":"2026-08-03T05:48:06.937672Z","title":"On the Gibbs exponential mechanism and private synthetic data generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:06.937672Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:3238269e12393c78ddac098ee82f2382f42e8ae8dd3759dd6528031a6d880e29","observation_id":"a663c366-04a7-4878-be3e-69dc45f64cca","resolution":{"observed_at":"2026-08-03T05:48:06.937672Z","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":"2026-08-03T05:48:07.034068Z","title":"Improving the gaussian mechanism for differential pri- vacy: Analytical calibration and optimal denoising","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.034068Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:0ed1778e45364f44f2b4adb555d46ff2a0e5ab3f5b12d7ac2914bb541a764588","observation_id":"68554cb0-a09e-425e-9565-4720ded816a5","resolution":{"observed_at":"2026-08-03T05:48:07.034068Z","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":"2026-08-03T05:48:07.112678Z","title":"Privacy, accuracy, and consistency too: a holistic solution to contingency table release","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.112678Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:1446a7533b1989ab287579a1620bdf085544f814af8103c5bc00889c2db776b8","observation_id":"0c4b0252-c76a-473b-b7bb-f161c2263138","resolution":{"observed_at":"2026-08-03T05:48:07.112678Z","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":"2026-08-03T05:48:07.234897Z","title":"Privacy and synthetic datasets.Stan","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.234897Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:cb55bfd67caca0ea32d68e7113a4b04c791d0d01446f9f9ffa5ff63b5cbc822e","observation_id":"30e2bd5c-806b-492b-b543-71b329c4fbab","resolution":{"observed_at":"2026-08-03T05:48:07.234897Z","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":"2026-08-03T05:48:07.314375Z","title":"A learning theory approach to noninterac- tive database privacy.Journal of the ACM (JACM), 60(2):1–25, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.314375Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:3e3b30ea0605372a2a7c865685129f882ab5fc00b046a3bb403d253d06996d93","observation_id":"1446647c-b194-494b-b74a-09bfecb12e67","resolution":{"observed_at":"2026-08-03T05:48:07.314375Z","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":"2026-08-03T05:48:07.412979Z","title":"Private measures, random walks, and synthetic data.Probability theory and related fields, 189(1):569–611, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.412979Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:8b7d5e94aa45e70722f61df623246fa218ec29b8336097842ad4befc781153e7","observation_id":"6a93abb4-57d5-426b-81c6-f8754af495af","resolution":{"observed_at":"2026-08-03T05:48:07.412979Z","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":"2026-08-03T05:48:07.521003Z","title":"Synthetic data generators–sequential and private.Advances in Neural Information Processing Systems, 33:7114–7124, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.521003Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:7c39fb9bc052225e41ef42b3a4686e4f052d5ac0fffbba2f9fa1e1c63fa5887e","observation_id":"785864da-328c-4d3a-9465-f273d26fa0bb","resolution":{"observed_at":"2026-08-03T05:48:07.521003Z","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":"2026-08-03T05:48:07.630236Z","title":"A universal law of robustness via isoperimetry.Advances in Neural Information Processing Systems, 34:28811–28822, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.630236Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:787ee1b7ed84158001a2140ef57fc04b2accba37c967cc429c6b865e26013d20","observation_id":"1447fd8c-5860-4347-889f-e7aeb6f0d591","resolution":{"observed_at":"2026-08-03T05:48:07.630236Z","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":"2026-08-03T05:48:07.701075Z","title":"Continual release of differentially private synthetic data from longitudinal data collections.Proceedings of the ACM on Management of Data, 2(2):1–26, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.701075Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:53ac00683adfe786637ae3ef10be96679f8c60ed988f27e0a13bb3d131686796","observation_id":"391eb54b-bac1-423c-87be-4e38b3b1c6b7","resolution":{"observed_at":"2026-08-03T05:48:07.701075Z","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":"2026-08-03T05:48:07.807008Z","title":"Make up your mind: The price of online queries in differential privacy","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.807008Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:574ea469a46a97f65d02dd7b228789c627a98ce13098050ac101e2c6ee51b471","observation_id":"17ff9afb-1dbf-4771-858e-850d9ca2df36","resolution":{"observed_at":"2026-08-03T05:48:07.807008Z","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":"2026-08-03T05:48:07.909057Z","title":"Fingerprinting codes and the price of approximate differential privacy","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.909057Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:746e00b959432ff1312c527ef9bbc91f83f499d0f8c4ae8b6f3092ef6196a1ea","observation_id":"a9e826e7-7714-4f82-ac0b-1eeb54c00373","resolution":{"observed_at":"2026-08-03T05:48:07.909057Z","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":"2026-08-03T05:48:07.979132Z","title":"The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy.The Annals of Statistics, 49(5):2825–2850, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:07.979132Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:075ce92d01c96fe56552a63579c8be175231340bf295c727582fb33a5bf7b28c","observation_id":"dc1d4895-54a1-42a0-a0b6-9becfae693fd","resolution":{"observed_at":"2026-08-03T05:48:07.979132Z","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":"2026-08-03T05:48:08.046738Z","title":"Differentially private histogram with valid statistics.Statistics & Probability Letters, 219:110354, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.046738Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:2101e5cb525522df96d19908515a98310a941cc8b32ce3f661265732742f5c8d","observation_id":"fd0710a9-e430-47f0-87e3-b53594f31799","resolution":{"observed_at":"2026-08-03T05:48:08.046738Z","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":"2026-08-03T05:48:08.154237Z","title":"A short course on approximation theory.Bowling Green State University, Bowling Green, OH, 38, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.154237Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:19ca99105592f355254d80074335f242862af51919f6e2ff55a480b93b9ca201","observation_id":"01b4571c-3a92-4ff7-a891-2a559d51417e","resolution":{"observed_at":"2026-08-03T05:48:08.154237Z","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":"2026-08-03T05:48:08.252662Z","title":"Privacy-preserving logistic regression.Ad- vances in neural information processing systems, 21, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.252662Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:843c167bc0b0d544129c33daa95dfb0399a492c2191c27ca5718ba7dd14b97ef","observation_id":"46563ba8-0750-433a-b5e5-80e4f6f3a005","resolution":{"observed_at":"2026-08-03T05:48:08.252662Z","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":"2026-08-03T05:48:08.327679Z","title":"Differentially private empirical risk minimization.Journal of Machine Learning Research, 12(3), 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.327679Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:39d541d63fbdf97756bb0a5d4ca093ba9e7525aed11400263c44591b92514c5d","observation_id":"28f2de85-4a29-4a4b-a35e-4449481856c7","resolution":{"observed_at":"2026-08-03T05:48:08.327679Z","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":"2026-08-03T05:48:08.428075Z","title":"Privacy at scale: Local differential privacy in practice","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.428075Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:5239a91222f03edac7d03e8d06b62c07604b1a396f95489051e8bfda0c821481","observation_id":"0f0cba7d-1ed7-4d40-83b2-2193c4d4a31e","resolution":{"observed_at":"2026-08-03T05:48:08.428075Z","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":"2026-08-03T05:48:08.587851Z","title":"Certified private data release for sparse lipschitz functions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.587851Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:9dc920532926c856aade6c10db75822a2c4cca4ad1f11473a65de1e9e7da95c3","observation_id":"89d7ccb3-832a-4606-b50f-e3c3901aadbf","resolution":{"observed_at":"2026-08-03T05:48:08.587851Z","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":"2026-08-03T05:48:08.749748Z","title":"Minimax optimal proce- dures for locally private estimation.Journal of the American Statistical Association, 113(521):182–201, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.749748Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:c108446d7e96fafb97d75ced83e084a793f6723637ebc43315ee37cea87ab9fa","observation_id":"88dbb27e-7589-4820-8f4a-e2a888467bc6","resolution":{"observed_at":"2026-08-03T05:48:08.749748Z","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":"2026-08-03T05:48:08.861899Z","title":"Differential privacy in practice: Expose your epsilons!Journal of Privacy and Confidentiality, 9(2), 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.861899Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:6c8e223026d3e4665fb69e13a2a001f573d451f33a7c142455460dd999717229","observation_id":"8381aca4-e2b1-4544-a304-7dbffc5fdf12","resolution":{"observed_at":"2026-08-03T05:48:08.861899Z","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":"2026-08-03T05:48:08.952638Z","title":"The algorithmic foundations of differential privacy.Foun- dations and Trends®in Theoretical Computer Science, 9(3–4):211–407, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:08.952638Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:23959103ba086bce78f1d05112fa3e6de67e8c78ee94f640cecf7213a79aa314","observation_id":"c99085d1-20d3-4fbc-b339-d441117c3592","resolution":{"observed_at":"2026-08-03T05:48:08.952638Z","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":"2026-08-03T05:48:09.066470Z","title":"Instance-optimal private density estimation in the wasserstein distance.Advances in Neural Information Processing Systems, 37:90061–90131, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.066470Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:2ce7fe8b69fd38740fa2bc451e38d108c831b837a2682d98f9497a38cd1fdc26","observation_id":"b7892826-8b88-4bfc-9d3f-a876a5461d01","resolution":{"observed_at":"2026-08-03T05:48:09.066470Z","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":"2026-08-03T05:48:09.156867Z","title":"JHU press, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.156867Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:02d60aa9eff63b42b8eae7b448dbba6efbd221dfba117ec0dbee19159c6c2d16","observation_id":"5fa5bd8c-6d14-428d-b5cc-f30071e81a89","resolution":{"observed_at":"2026-08-03T05:48:09.156867Z","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":"2026-08-03T05:48:09.224500Z","title":"Private evolution converges.arXiv preprint arXiv:2506.08312, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.224500Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:316779e9c60b194c4342c519ccaf30b8373c9bb0811ccfc3ccf5edabe4909dfc","observation_id":"110e5822-99c2-4f8d-b32e-89b5f1f175d8","resolution":{"observed_at":"2026-08-03T05:48:09.224500Z","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":"2026-08-03T05:48:09.298995Z","title":"Mirror descent algorithms with nearly dimension-independent rates for differentially-private stochastic saddle-point problems.arXiv preprint arXiv:2403.02912, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.298995Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:5abfba5f173c59b1139cb5e252332c6e6285ad4984e76984bfea0608814e43ad","observation_id":"6c572e82-f0dd-46fa-b7da-8be34759f23b","resolution":{"observed_at":"2026-08-03T05:48:09.298995Z","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":"2026-08-03T05:48:09.382945Z","title":"Differentially private wasserstein barycenters.arXiv preprint arXiv:2510.03021, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.382945Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:e473b92d47196b5f8883231a5dcad090f176d074b8320c7d80327760735a6410","observation_id":"a9f454c5-a4da-4e9e-8d13-a22f45f658ae","resolution":{"observed_at":"2026-08-03T05:48:09.382945Z","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":"2026-08-03T05:48:09.446857Z","title":"A simple and practical algorithm for differentially private data release.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.446857Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:f55aff8af2e206c378ae157745f44ebd561d315aeb4d7f11e7f6e1878edee382","observation_id":"27caa697-1177-4c44-98ba-db7207c973ed","resolution":{"observed_at":"2026-08-03T05:48:09.446857Z","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":"2026-08-03T05:48:09.536537Z","title":"A multiplicative weights mechanism for privacy- preserving data analysis","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.536537Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:b5d44f7ea5e69f5da5d011a80ea9bfaa5b3933470fc96159c61fe473f0361cf0","observation_id":"db2245c6-1cc9-48f4-b0f7-3871d4535c12","resolution":{"observed_at":"2026-08-03T05:48:09.536537Z","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":"2026-08-03T05:48:09.622128Z","title":"Differential privacy in the 2020 census will distort covid-19 rates.Socius, 7:2378023121994014, 2021","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.622128Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:a52b7e4f8b4062b5bea182ecf2862ac626f33056a40b6dcb83cab35a7cfb0802","observation_id":"f9d4b511-ab59-4930-8ffe-2b84b4e3adce","resolution":{"observed_at":"2026-08-03T05:48:09.622128Z","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":"2026-08-03T05:48:09.706597Z","title":"Implementing differential privacy: Seven lessons from the 2020 United States Census.Harvard Data Science Review, 2(2), 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.706597Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:5dfcbc5358140548e2f35d04bd50563374a587405d8adaae9c65b81f24b1facd","observation_id":"cc9c69df-cf40-493f-af87-33199bb10689","resolution":{"observed_at":"2026-08-03T05:48:09.706597Z","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":"2026-08-03T05:48:09.794608Z","title":"Differentially private low- dimensional synthetic data from high-dimensional datasets.Information and Inference: A Journal of the IMA, 14(1):iaae034, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.794608Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:414c4bfe330718ad1c90733e180f6d0b54d69f99b0bbd64960a9e7839e44c6a2","observation_id":"6624ab23-6993-41ed-98f2-b5f25f83cd3b","resolution":{"observed_at":"2026-08-03T05:48:09.794608Z","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":"2026-08-03T05:48:09.858406Z","title":"Algorithmically effective differentially private synthetic data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.858406Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:88aae14a435687e862bd0bbccabac80a093c38da0862ac526e4a4657b71f08d6","observation_id":"118c56a1-c4f6-4dd1-aa4d-ebd5321f5090","resolution":{"observed_at":"2026-08-03T05:48:09.858406Z","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":"2026-08-03T05:48:09.946454Z","title":"Online differentially private synthetic data generation.IEEE Transactions on Privacy, (01):1–12, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:09.946454Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:030c8e9fa761a16100843598b205bd2dae7d1db958448bb9814765d878927482","observation_id":"0df35be5-1997-4099-b6c2-61bf61df8f89","resolution":{"observed_at":"2026-08-03T05:48:09.946454Z","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":"2026-08-03T05:48:10.003886Z","title":"Private synthetic data generation in bounded memory.Proceedings of the ACM on Management of Data, 3(2):1– 25, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.003886Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:44183bc248f53af4093e9532f44f97a3212a213650951b509a2387646adc54a0","observation_id":"f1b0e177-af77-439c-a603-9b954f1126ad","resolution":{"observed_at":"2026-08-03T05:48:10.003886Z","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":"2026-08-03T05:48:10.094449Z","title":"On approximation by trigonometric sums and polynomials.Transactions of the American Mathematical society, 13(4):491–515, 1912","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.094449Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:21b7149c27400fcb61dc00773977c17ad57456333a35d5d37bc5682eb8492a67","observation_id":"3cd3dc78-4769-4f55-a242-f2e44281a967","resolution":{"observed_at":"2026-08-03T05:48:10.094449Z","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":"2026-08-03T05:48:10.166225Z","title":"American Mathematical Soc., 1930","venue":null,"work_id":null,"year":1930},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.166225Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:f59e9a9a032480b86e8bf915228344b33b61669f3eed59b9bd9cc3d1c6b00c3b","observation_id":"2f238896-952a-4e9e-a430-eced6f45a070","resolution":{"observed_at":"2026-08-03T05:48:10.166225Z","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":"2026-08-03T05:48:10.241577Z","title":"New lower bounds for private estimation and a generalized fingerprinting lemma.Advances in neural information pro- cessing systems, 35:24405–24418, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.241577Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:378d6d09044092294ee1e29b344e7a5c76831e86406d2a510f025288db8ed5fd","observation_id":"85c0e835-0c9d-4962-b7d8-54f8a70e0cec","resolution":{"observed_at":"2026-08-03T05:48:10.241577Z","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":"2026-08-03T05:48:10.302931Z","title":"Cambridge Mathematical Library","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.302931Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:12eb03ded180c2ecabc84078f50e559a0e123012f710b96d76d77a01b1574e08","observation_id":"c90b5698-5d02-4dae-a566-a5114deeada5","resolution":{"observed_at":"2026-08-03T05:48:10.302931Z","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":"2026-08-03T05:48:10.381889Z","title":"Lipschitz clustering in metric spaces.The Journal of Geometric Anal- ysis, 32(7):188, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.381889Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:fa1f85f8d827103995c2f1e9e13dc197e7ecc2680164a39b5ed604aa8b01793e","observation_id":"2ff0488e-e5e1-4b54-b8f8-f44c7e620bee","resolution":{"observed_at":"2026-08-03T05:48:10.381889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15560","last_updated":"2025-05-17T15:12:18Z","snapshot_observed_at":"2026-08-16T17:12:33.591572Z","submitted_at":"2023-05-24T23:47:26Z","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15560","snapshot_observed_at":"2026-08-03T05:48:10.499227Z","title":"Dif- ferentially private synthetic data via foundation model apis 1: Images.arXiv preprint arXiv:2305.15560, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.499227Z"},"links":{"cited_paper":"/paper/2305.15560","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:63e42b8ffa6e909da537ed99b0e90b35c406706a2105e92cf516fdad8d81a017","observation_id":"b1699997-69e6-4d71-91e6-c5b9ad987603","resolution":{"observed_at":"2026-08-03T05:48:10.499227Z","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":"2026-08-03T05:48:10.578677Z","title":"Optimizing error of high-dimensional statistical queries under differential privacy.Proceedings of the VLDB Endowment, 11(10), 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.578677Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:6a7bd2bce399d2dc946cc93243d23679e9827f0c3fb91bea02fd5ac06fc75370","observation_id":"6a9d2562-def7-4d8f-8f01-b340dc13910d","resolution":{"observed_at":"2026-08-03T05:48:10.578677Z","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":"2026-08-03T05:48:10.626127Z","title":"A dy- namical system perspective for Lipschitz neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.626127Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:bc1e77c1ee524f75df0085532c61ea3fd369c21a349b1d64c896d39743b7ce19","observation_id":"63c30889-6c1e-4eeb-ae9c-7f9348c1f31e","resolution":{"observed_at":"2026-08-03T05:48:10.626127Z","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":"2026-08-03T05:48:10.665809Z","title":"Sharper bounds for chebyshev moment matching, with applications","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.665809Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:46237289fd3d30347ee209459501351977f8ad32de7c32e64e50fcd6ca982a2a","observation_id":"c8f01f77-f382-41ae-8746-ffa84ecf3e9b","resolution":{"observed_at":"2026-08-03T05:48:10.665809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.03238","last_updated":"2026-07-09T21:40:53Z","snapshot_observed_at":"2026-08-20T18:36:35.111387Z","submitted_at":"2025-12-02T21:14:39Z","title":"How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.03238","snapshot_observed_at":"2026-08-03T05:48:10.750021Z","title":"How to dp-fy your data: A practical guide to generating synthetic data with differential privacy.arXiv preprint arXiv:2512.03238, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.750021Z"},"links":{"cited_paper":"/paper/2512.03238","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:9b205e1c6177519de522de7db2b929334d572d6a7873999ad78986b9da63869d","observation_id":"e54b765c-fcd2-46ae-8e07-3bc134138316","resolution":{"observed_at":"2026-08-03T05:48:10.750021Z","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":"2026-08-03T05:48:10.805124Z","title":"Stochastic gradient descent with differentially private updates","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.805124Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:1725fcfd7a9562ec944d2069628446f9952b40d29076df59b20fd0fc7f7a9894","observation_id":"1a3a1a4a-b672-4969-b31c-482a2531f043","resolution":{"observed_at":"2026-08-03T05:48:10.805124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"0901.2698","last_updated":"2009-10-13T03:15:17Z","snapshot_observed_at":"2026-08-15T05:57:11.726771Z","submitted_at":"2009-01-18T13:20:59Z","title":"On integral probability metrics, \\phi-divergences and binary classification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0901.2698","snapshot_observed_at":"2026-08-03T05:48:10.853634Z","title":"On integral probability metrics,ϕ-divergences and binary classification","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.853634Z"},"links":{"cited_paper":"/paper/0901.2698","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:eac17493ef67f5f74d4c31e781f3b1b0646618bf1d75cdcbd787a32622f0c83b","observation_id":"e7697bd5-c0aa-4810-af6c-a35151447382","resolution":{"observed_at":"2026-08-03T05:48:10.853634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1501.06095","last_updated":"2015-01-24T23:26:21Z","snapshot_observed_at":"2026-08-19T06:05:56.394485Z","submitted_at":"2015-01-24T23:26:21Z","title":"Between Pure and Approximate Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1501.06095","snapshot_observed_at":"2026-08-03T05:48:10.929712Z","title":"Between pure and approximate differential privacy","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:10.929712Z"},"links":{"cited_paper":"/paper/1501.06095","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:6c2c03208fb9d99eb6e397eb774c482a71c98066c8f694829de60daaa627bbf2","observation_id":"d16fb5d1-70ad-429f-a33b-14cb180cec2c","resolution":{"observed_at":"2026-08-03T05:48:10.929712Z","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":"2026-08-03T05:48:11.086609Z","title":"Differentially private k-means clustering","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.086609Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:ae0520a576e54e2835acefc46733bc5e0832599df30e2eb80c980a2e2eca2ddf","observation_id":"64257357-08c0-4c62-8f79-06dd811980c0","resolution":{"observed_at":"2026-08-03T05:48:11.086609Z","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":"2026-08-03T05:48:11.218687Z","title":"1, Basic theory","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.218687Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:1d9c91a40aff76000633cbe1c677ce0c1282c9aba226589f03f277eb3bc6ddc7","observation_id":"17690b7f-2c6d-4038-adfc-e9861929ea21","resolution":{"observed_at":"2026-08-03T05:48:11.218687Z","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":"2026-08-03T05:48:11.320775Z","title":"Private multiplicative weights beyond linear queries","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.320775Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:9869990f47dcc437bc0b5c9b2e9841f57f6a23621a77941cd369a7020a5d7b5e","observation_id":"ae680273-fa96-4808-adfe-ff76d723e32f","resolution":{"observed_at":"2026-08-03T05:48:11.320775Z","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":"2026-08-03T05:48:11.396833Z","title":"Pcps and the hardness of generating synthetic data","venue":null,"work_id":null,"year":2078},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.396833Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:bf0adc3264bd8f9c367d2a2f989ae1d5b135b04fa79577e9a13004c90022ef98","observation_id":"a67e65cd-118b-47de-acfd-5de13cd224b7","resolution":{"observed_at":"2026-08-03T05:48:11.396833Z","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":"2026-08-03T05:48:11.468649Z","title":"Springer, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.468649Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:93764cadf989e916d76816d11ecd2c714fe5ea0f8d5d7e85b689a6448f693420","observation_id":"e2906254-51c6-45e3-b45a-bda4e0ef68c2","resolution":{"observed_at":"2026-08-03T05:48:11.468649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.10523","last_updated":"2021-01-21T14:01:55Z","snapshot_observed_at":"2026-08-16T18:57:23.323211Z","submitted_at":"2020-12-18T21:35:26Z","title":"A closed form scale bound for the $(\\epsilon, \\delta)$-differentially private Gaussian Mechanism valid for all privacy regimes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.10523","snapshot_observed_at":"2026-08-03T05:48:11.566880Z","title":"A closed form scale bound for the (ε, δ)-differentially private gaussian mechanism valid for all privacy regimes.arXiv preprint arXiv:2012.10523, 2020","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.566880Z"},"links":{"cited_paper":"/paper/2012.10523","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:60a3eebcb4652fbf451caa65601dcc639d54708d6ce31c81ed7047f76ff1e97f","observation_id":"5b73d430-02c6-434f-b0e8-06d7bb2edc11","resolution":{"observed_at":"2026-08-03T05:48:11.566880Z","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":"2026-08-03T05:48:11.626478Z","title":"Distance-based classification with Lipschitz functions.J","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.626478Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:216cbbeacf5cb0cba21503d2c05618c2aca622f2bb5bfdb7bb1534330ef1031d","observation_id":"10e36951-a8c0-4639-bf3f-ecd35eab7be3","resolution":{"observed_at":"2026-08-03T05:48:11.626478Z","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":"2026-08-03T05:48:11.685687Z","title":"Differentially private data releasing for smooth queries.The Journal of Machine Learning Research, 17(1):1779–1820, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.685687Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:3a1aaf9a3ba01a59a4dfeed532281f57a07195ded7eb0ac958959e8b417025f4","observation_id":"287db72f-c7d5-43f9-8020-783576bd922b","resolution":{"observed_at":"2026-08-03T05:48:11.685687Z","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":"2026-08-03T05:48:11.736774Z","title":"A statistical framework for differential privacy","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.736774Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:515fd3290fc5fe422ff7c6d29be5c14590db4bc19926559ced237116db76b982","observation_id":"96940994-f7dd-4140-b6cd-e4b6b6975ff3","resolution":{"observed_at":"2026-08-03T05:48:11.736774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11778","last_updated":"2025-02-17T13:13:16Z","snapshot_observed_at":"2026-08-19T04:00:11.503573Z","submitted_at":"2025-02-17T13:13:16Z","title":"Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11778","snapshot_observed_at":"2026-08-03T05:48:11.811123Z","title":"Private synthetic graph generation and fused gromov-wasserstein distance.arXiv preprint arXiv:2502.11778, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.811123Z"},"links":{"cited_paper":"/paper/2502.11778","citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:0e17b707b705bdbcda8ea0e927ebb6a656e69968443cf164753b7f7154eeac14","observation_id":"83cdebe6-40e2-4a07-8a87-4c880bd17843","resolution":{"observed_at":"2026-08-03T05:48:11.811123Z","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":"2026-08-03T05:48:11.863490Z","title":"Assouad, fano, and le cam","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.863490Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:115e375d7c245e6ec636d19c0134ac023f68ba93e267087ac44d788d8497c507","observation_id":"5b6d5bbc-a795-4be3-bd99-d5ad43166179","resolution":{"observed_at":"2026-08-03T05:48:11.863490Z","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":"2026-08-03T05:48:11.921059Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:11.921059Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:42a2dc52fc656a879175dce2bf9363df1202a9e610aa57454e78fd31635e9de3","observation_id":"f34545b8-19fd-4e34-83b9-0d5ea3fa9769","resolution":{"observed_at":"2026-08-03T05:48:11.921059Z","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":"2026-08-03T05:48:12.042734Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:12.042734Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:71051fe10756d13fceb37559b732bbe8fdb4e8685c87fc062d9156cdbda962da","observation_id":"b27d72c3-a17e-4459-920d-288db4c4f9e1","resolution":{"observed_at":"2026-08-03T05:48:12.042734Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-08-03T05:48:12.159086Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:12.159086Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:82889e4c8322542124d79039cc8f28542662e08d72e23a1e18613e01429a654a","observation_id":"06644b43-4441-4fcd-a421-0748a5ebac7b","resolution":{"observed_at":"2026-08-03T05:48:12.159086Z","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":"2026-08-03T05:48:12.273148Z","title":"23 Lemma 12(Jackson’s Theorem for 1-dimensionalk-smooth functions, [40]).Letm, k≥1and a even periodic functiongwith period2πsatisfies∥g (k)∥L∞([0,π]d) ≤1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T05:48:12.273148Z"},"links":{"citing_paper":"/paper/2602.01607"},"observation_digest":"sha256:6c0ef2e5b1d2dbc3bd6fee7d5e9016910a1805666e08a2e28ef589405d61b941","observation_id":"7250c43f-78f1-4dc8-bd5f-98dabc627b7c","resolution":{"observed_at":"2026-08-03T05:48:12.273148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.01607","last_updated":"2026-06-04T00:07:53Z","latest_version":3,"primary_category":"math.ST","snapshot_observed_at":"2026-08-13T15:57:09.917185Z","submitted_at":"2026-02-02T03:54:11Z","title":"Minimax optimal differentially private synthetic data for smooth queries"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":66,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":67},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2602.01607."}