{"as_of":"2026-08-18T23:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:32a24715e33ccfc5e61490e206361e6ccaee693240750cd14368331dd613d801","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T18:03:14.954752Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2509.10385/citation-record","integrity":"/paper/2509.10385/integrity","json":"/paper/2509.10385/citation-record.json","paper":"/paper/2509.10385"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T18:03:11.149164Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.149164Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:0cad235ff9cce86730165a9554889f75c80775c541bd7569de2f83dcb29b0e38","observation_id":"b7182422-e396-458f-a05b-b3aadd35ca87","resolution":{"observed_at":"2026-08-04T18:03:11.149164Z","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":"2026-08-04T18:03:11.294749Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.294749Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:06b9d94f267aad883fdb80d950f7a01085d8e55dc8e82f621b5e2ab0eda60dbf","observation_id":"36fa8418-6d80-40e3-bfc9-962a3279b49f","resolution":{"observed_at":"2026-08-04T18:03:11.294749Z","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":"2026-08-04T18:03:11.401308Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.401308Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:876f7d77eabd43ddf6a8dec0878adcfe6ea39ac5a8d4a82ed1ddfe7118af76f2","observation_id":"5656f08c-2335-434b-b320-43ebe6ddc5f2","resolution":{"observed_at":"2026-08-04T18:03:11.401308Z","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":"2026-08-04T18:03:11.514744Z","title":"Property inference attacks on fully connected neural networks using permutation invariant representations,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.514744Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:b33a8443b84723faa7eef0f87b140e399f03277046cfcdfceef5ca6d9082c1c8","observation_id":"d1d30cbc-a74e-4545-b74f-b7ec707d42a4","resolution":{"observed_at":"2026-08-04T18:03:11.514744Z","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":"2026-08-04T18:03:11.604750Z","title":"Federated learning in non-iid settings aided by differentially private synthetic data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.604750Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:b0dc82bb8f226ff70616f21dba86db6f13d1cfb2180d9b7615e85ab0465dee4d","observation_id":"838fd683-7e44-46df-9a4a-565cbb2d2980","resolution":{"observed_at":"2026-08-04T18:03:11.604750Z","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":"2026-08-04T18:03:11.730986Z","title":"Gen- erative models for effective ml on private, decentralized datasets,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.730986Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:3dc61ec42bc776ca1f01060031ffe5c243b190a816271731d7a8eed08f399b20","observation_id":"f765c905-0ace-48c9-af33-8b442bccf764","resolution":{"observed_at":"2026-08-04T18:03:11.730986Z","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":"2026-08-04T18:03:11.859623Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.859623Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:1ffc3c7dca44cd12881db5e5b334d9e5e89f4aba850a329416f61b4db5cd18ed","observation_id":"b6f5e535-0544-4295-81f1-5dfb9db2ef4c","resolution":{"observed_at":"2026-08-04T18:03:11.859623Z","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":"2026-08-04T18:03:11.994752Z","title":"Federated machine learning: Concept and applications,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:11.994752Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:8e8df89de03bd5aa1409f1805395e95673b2d593eafe70b9d6d263194279a0fb","observation_id":"7bd66ecc-638f-43e8-98b8-768a8212802d","resolution":{"observed_at":"2026-08-04T18:03:11.994752Z","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":"2026-08-04T18:03:12.046594Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.046594Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:c29c28a03af3aa5c8e84c1454cc5dcc9da1153c31b423ccdd6bf341884e70dc5","observation_id":"419b763c-1c08-4ad0-82a3-a9a12a9ac5df","resolution":{"observed_at":"2026-08-04T18:03:12.046594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05492","last_updated":"2017-10-30T20:52:14Z","snapshot_observed_at":"2026-08-13T17:19:46.488095Z","submitted_at":"2016-10-18T09:11:51Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-08-04T18:03:12.095529Z","title":"Federated learning: Strategies for improving communication efficiency,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.095529Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:e8405057d1213e09aa4b644d94e65d780be19a041238672ba204e6da59c4a54a","observation_id":"49123223-5cff-4827-accf-2b88fe127b80","resolution":{"observed_at":"2026-08-04T18:03:12.095529Z","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":"2026-08-04T18:03:12.164358Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.164358Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:f4cd865e43443c4a4dd4ff1616ebfb48c30adab786d4c9b20a89457381cc515e","observation_id":"95044c43-a191-48dc-921a-95541548519f","resolution":{"observed_at":"2026-08-04T18:03:12.164358Z","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":"2026-08-04T18:03:12.234756Z","title":"Handling privacy-sensitive medical data with federated learning: challenges and future directions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.234756Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:9d3f05c928b841ca87732bc870e7b59c2256c11ef7e18510a2fec94f8a1e79ba","observation_id":"5b43cb27-b7a7-4bfa-a2cd-b5ef5d9f0b42","resolution":{"observed_at":"2026-08-04T18:03:12.234756Z","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":"2026-08-04T18:03:12.304754Z","title":"Cafe: Catastrophic data leakage in vertical federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.304754Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:3a75c8b247987bef5ce04473a313560292a5a58e536c2ef5e2cb06539897f915","observation_id":"d349c528-6c18-45a7-a935-84bac8eac6e2","resolution":{"observed_at":"2026-08-04T18:03:12.304754Z","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":"2026-08-04T18:03:12.384756Z","title":"Tapfed: Threshold secure aggregation for privacy-preserving federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.384756Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:f75e07d15c4906bad93571bbea17c83c149a4d5f6f82df6194343be17510aef8","observation_id":"d9bf468b-0406-4b11-9789-0896f29e744b","resolution":{"observed_at":"2026-08-04T18:03:12.384756Z","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":"2026-08-04T18:03:12.494759Z","title":"Privacy-preserving federated learning via functional encryption, revisited,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.494759Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:86a7b21dae7b18c50bdfc78b242974737118fd94c2d5b69cb255cf17e26c966f","observation_id":"8054d727-8d54-4749-93f2-1b3398a6d3d5","resolution":{"observed_at":"2026-08-04T18:03:12.494759Z","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":"2026-08-04T18:03:12.564738Z","title":"Differentially private federated learning: An information- theoretic perspective,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.564738Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:54ef779c534343f379b5755c5a6c42151904be7a86c64a4d29f7006cd36cb5f6","observation_id":"4f6b6365-5f26-4b0d-b474-b45f2745b628","resolution":{"observed_at":"2026-08-04T18:03:12.564738Z","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":"2026-08-04T18:03:12.634859Z","title":"Fedv: Privacy-preserving federated learning over vertically partitioned data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.634859Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:56d9b6961c8ba3e9c9511495433fbe257a688854eb8bf225356edf8cf40e6eba","observation_id":"8b853793-cbf8-48bb-9895-5392edcfdeea","resolution":{"observed_at":"2026-08-04T18:03:12.634859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.07557","last_updated":"2018-03-01T10:12:27Z","snapshot_observed_at":"2026-08-16T10:57:46.215293Z","submitted_at":"2017-12-20T16:28:37Z","title":"Differentially Private Federated Learning: A Client Level Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.07557","snapshot_observed_at":"2026-08-04T18:03:12.740476Z","title":"Differentially private federated learning: A client level perspective,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.740476Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:a38b5f28f7be73b724858873bf20c9bc6f38468b7b80b19e8e0db19eb8f89cde","observation_id":"f9ce7cee-ec46-4ef4-9be3-ed9f1fd36de9","resolution":{"observed_at":"2026-08-04T18:03:12.740476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16121","last_updated":"2026-04-29T11:42:08Z","snapshot_observed_at":"2026-08-01T22:21:58.198228Z","submitted_at":"2024-11-25T06:14:06Z","title":"DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16121","snapshot_observed_at":"2026-08-04T18:03:12.884752Z","title":"Dp-cda: An algorithm for enhanced privacy preservation in dataset synthesis through randomized mixing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.884752Z"},"links":{"cited_paper":"/paper/2411.16121","citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:e32387613ffafcad1bf2fac74d2bb81042e6937b96889a17af3e6ff4329306b1","observation_id":"d3fad9e8-e42f-4d9a-a3d6-de774b2d67e2","resolution":{"observed_at":"2026-08-04T18:03:12.884752Z","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":"2026-08-04T18:03:12.971980Z","title":"A correlated noise-assisted decentralized differentially private estimation protocol, and its application to fmri source separation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:12.971980Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:7233304fbfa80046ea0cd7d1f56ae2595f849226476ff1f02454dceff486a146","observation_id":"4e252b6c-45bf-4633-be0c-6ac7a2fa5703","resolution":{"observed_at":"2026-08-04T18:03:12.971980Z","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":"2026-08-04T18:03:13.054769Z","title":"Privacy-preserving non-negative matrix factorization with outliers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.054769Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:6c5807d9b51bb3f0a7cbee174ddfc5e0bfa7b249b75cf9b5626192db8e48304f","observation_id":"52c89b58-0889-439f-8949-65dc839122f8","resolution":{"observed_at":"2026-08-04T18:03:13.054769Z","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":"2026-08-04T18:03:13.194838Z","title":"Approximating functions with approximate privacy for applications in signal estimation and learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.194838Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:e4c9597682435f2aaab9442a85e1c2eb10e0b3ed7c85effe6bd14b2f269cdfea","observation_id":"aa588a51-762a-43ba-ac6b-7842acef3dd9","resolution":{"observed_at":"2026-08-04T18:03:13.194838Z","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":"2026-08-04T18:03:13.294750Z","title":"Subsampled rényi differential privacy and analytical moments accountant,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.294750Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:0070ec2b2507c012f9e84e8929ac45bd5653359483aca3cbba07370faa42fcc8","observation_id":"f60c09ea-732c-4f80-97ad-8286bf5329cb","resolution":{"observed_at":"2026-08-04T18:03:13.294750Z","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":"2026-08-04T18:03:13.484872Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.484872Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:cad815de99c86fc60bcfe44d960bc7363d29db41eef06da8d087850858f7ace5","observation_id":"5398ecef-5bf9-40ee-8d3d-ed150c339a26","resolution":{"observed_at":"2026-08-04T18:03:13.484872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-04T18:03:13.634753Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.634753Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:00c0cd181d41255ce755d09844e2fb3b86bdda5db3a4efe42c54f7042e42cdb0","observation_id":"183fde81-7a12-43ab-9734-b549958878bf","resolution":{"observed_at":"2026-08-04T18:03:13.634753Z","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":"2026-08-04T18:03:13.774755Z","title":"Dppro: Differentially private high-dimensional data release via random projection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.774755Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:a6ce15d4bc9f68171d590c330cccbd7e54c7fd1a177b439e57857230d1d8e29f","observation_id":"fa3d0941-316a-41fb-876a-8255386dd287","resolution":{"observed_at":"2026-08-04T18:03:13.774755Z","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":"2026-08-04T18:03:13.954745Z","title":"Privacy-preserving data mining,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:13.954745Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:eb6ab9814095b436d32aefc6ead03832f26efa3f58aa08776322ba80e4b9c78c","observation_id":"d34e5839-56bd-432e-86c9-3b400ed54978","resolution":{"observed_at":"2026-08-04T18:03:13.954745Z","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":"2026-08-04T18:03:14.150595Z","title":"Synthesizing differentially private datasets using random mixing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.150595Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:ed7af233076cfd50bbc43f7d9b5556b66df88869e5923c3d61af8328ca638bd4","observation_id":"d9ed224a-9943-4218-b231-81e3b27f9a16","resolution":{"observed_at":"2026-08-04T18:03:14.150595Z","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":"2026-08-04T18:03:14.274755Z","title":"Calibrating noise to sensitivity in private data analysis,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.274755Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:1a596a98920680909400fc99cf181d7c7f9f418effc4d51dad37403858f8f8e7","observation_id":"67a9c27b-1194-4b5b-9d1a-cc61816542fa","resolution":{"observed_at":"2026-08-04T18:03:14.274755Z","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":"2026-08-04T18:03:14.624751Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.624751Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:a6e5daf9e54c700351628d9f316c08d41ae475ab3a1420c90356d82583d7c6e0","observation_id":"6d7bc043-b13c-40f7-ba54-6ff007d87d59","resolution":{"observed_at":"2026-08-04T18:03:14.624751Z","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":"2026-08-04T18:03:14.874755Z","title":"Mechanism design via differential privacy,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.874755Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:eb71e0d7062b12b08ab8f734ad34f6bd63dce247ea14bff3c4079349576c0adb","observation_id":"a07bd80a-721e-4462-8144-4ab7485f75d6","resolution":{"observed_at":"2026-08-04T18:03:14.874755Z","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":"2026-08-04T18:03:14.954752Z","title":"Rényi differential privacy,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.954752Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:bb14a392c2d65dbcbd48f45b840beba3f82fe2f22cde6046fd139bbb6c1b53ea","observation_id":"9cceb0fb-ff7a-4611-b85e-201e9c3f2911","resolution":{"observed_at":"2026-08-04T18:03:14.954752Z","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":"2026-08-04T18:03:14.501411Z","title":"265–284, Springer, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise","version":1},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-04T18:03:14.501411Z"},"links":{"citing_paper":"/paper/2509.10385"},"observation_digest":"sha256:70bb259943505ee5e1a55e5b9a1a76f31f8bea7a18f08e887dec0503d04fc801","observation_id":"a8e4046f-7a08-429a-ba9a-7bc46d5dcb59","resolution":{"observed_at":"2026-08-04T18:03:14.501411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10385","last_updated":"2025-09-12T16:18:35Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-18T00:39:33.505286Z","submitted_at":"2025-09-12T16:18:35Z","title":"Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":33},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2509.10385."}