{"as_of":"2026-08-22T16:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ed06b0e31260f5d430f36d81895d30a3dc916df2d949bed9ef2acbd244eb286","coverage":[{"denominator":85,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":85,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T21:12:52.855661Z","state":"measured"},{"denominator":85,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":85,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2509.08195/citation-record","integrity":"/paper/2509.08195/integrity","json":"/paper/2509.08195/citation-record.json","paper":"/paper/2509.08195"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:49.505947Z","title":"Understanding clipping for federated learning: Convergence and client-level differential privacy","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:49.505947Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:0b7e6e2e29b42f17346b67fab1c46b7b797194ac1510af05dc079a9a6349676d","observation_id":"6cb1e314-afb0-4e06-bacc-a911159910ba","resolution":{"observed_at":"2026-08-04T21:12:49.505947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05733","last_updated":"2024-10-10T03:35:54Z","snapshot_observed_at":"2026-08-18T12:59:03.252713Z","submitted_at":"2024-10-08T06:50:41Z","title":"Private and Communication-Efficient Federated Learning based on Differentially Private Sketches","version":2},"cited_work":{"arxiv_id":"2410.05733","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.05733","snapshot_observed_at":"2026-08-04T21:12:53.168070Z","title":"Private and Communication-Efficient Federated Learning based on Differentially Private Sketches","venue":"cs.LG","work_id":"26bff3ab-5763-484f-92f1-ff63b06a1146","year":2024},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:49.605622Z"},"links":{"cited_paper":"/paper/2410.05733","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:cb7da48b2969f68f12683d04d40ae01f7699ecab3f95612e2c27b31888e84aaf","observation_id":"73d87887-0c7b-4472-a682-d33ae1938d53","resolution":{"observed_at":"2026-08-04T21:12:53.172035Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:49.686737Z","title":"Sketching for first order method: efficient al- gorithm for low-bandwidth channel and vulnerability","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:49.686737Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6b5cda146746937d83281ad7a25c9566ac9904fb021aca47af47b3678c967713","observation_id":"885a2945-dcb4-48eb-8a24-eff05f27c8ca","resolution":{"observed_at":"2026-08-04T21:12:49.686737Z","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":"2026-08-04T21:12:49.788254Z","title":"Sketching for distributed deep learning: A sharper analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:49.788254Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:35413d5bf7c0aadb45611e2fc233389c277fb2580ceaf0f51a100f697fd26ead","observation_id":"860bba57-edff-40e2-baf2-c3d871868209","resolution":{"observed_at":"2026-08-04T21:12:49.788254Z","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":"2026-08-04T21:12:49.884003Z","title":"Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:49.884003Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:2d17b41dab47e6d4efd5cc6359b59e231b2629854146c678b80c7978aef8c103","observation_id":"98fde843-1b17-4212-b507-ac7cac37dedd","resolution":{"observed_at":"2026-08-04T21:12:49.884003Z","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":"2026-08-04T21:12:50.017356Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.017356Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:4a31921b2c0cc9069f27c79f838540a7a0e8a5239476bcaf59de4a7c471ab57d","observation_id":"4c5a28f9-2fef-42f7-bc59-5131d27c9d69","resolution":{"observed_at":"2026-08-04T21:12:50.017356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.619757Z","title":"Wainwright, Peter L","venue":null,"work_id":"37323347-b624-4837-a5a1-f8a9cf3e01ec","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.082296Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:9f785374952a8b5a523b9ee060ff387425514dae33638a942ce6a9533cc9a503","observation_id":"1a7d5fed-3fdc-4a04-9347-c259b21c224f","resolution":{"observed_at":"2026-08-04T21:12:56.622913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.609352Z","title":"Finding frequent items in data streams","venue":null,"work_id":"83dd115d-e3ff-49c7-b576-e842bebf0cbb","year":2002},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.171808Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:d73d50c9188dcdf1a27e6f229f514dcf6704deb60a6038c343ca66d4b79493dc","observation_id":"34a36743-c8d2-45b2-9676-8fc384aecb66","resolution":{"observed_at":"2026-08-04T21:12:56.612741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:50.244750Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.244750Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:546a2b8118c81d844653ca7be78b6ff930b778ac979f2b7e9698c0afc8de906d","observation_id":"677aea1a-df00-47a1-bff9-c496fbf33d2e","resolution":{"observed_at":"2026-08-04T21:12:50.244750Z","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":"2026-08-04T21:12:50.309059Z","title":"Geyer, Tassilo Klein, and Moin Nabi","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.309059Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:fa131560ac759486d521c2ceb06a8d4c111163d81f6379f3a723cecd6ac2bdeb","observation_id":"f19e4b4a-e1d5-4eb8-831b-99b00cd7a8b7","resolution":{"observed_at":"2026-08-04T21:12:50.309059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.13039","last_updated":"2021-01-02T22:02:32Z","snapshot_observed_at":"2026-07-06T09:31:56.096344Z","submitted_at":"2020-06-22T06:46:11Z","title":"D2P-Fed: Differentially Private Federated Learning With Efficient Communication","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13039","snapshot_observed_at":"2026-08-04T21:12:50.411303Z","title":"D2P-Fed: Differentially private federated learning with effi- cient communication.arXiv preprint arXiv:2006.13039, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.411303Z"},"links":{"cited_paper":"/paper/2006.13039","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:3f9d9caf5e5ff6357c7500e9fe37c00d20572aaa2b06bf4118871f7d2d0f5ce2","observation_id":"9acf48bf-5f6d-475d-b233-b8f689f0e041","resolution":{"observed_at":"2026-08-04T21:12:50.411303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.592128Z","title":"Federated learning with Bayesian differential privacy","venue":null,"work_id":"1e866fd8-b824-4c08-94b9-c1689c8469eb","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.514158Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:c300f6d3c16b6166ac13a130b15148dbe3d9f2a96916c336a0c38049dd7dca05","observation_id":"a92e052d-9d26-4bee-9c49-5ba0d28d4ab6","resolution":{"observed_at":"2026-08-04T21:12:56.595697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21594","last_updated":"2024-12-19T14:22:24Z","snapshot_observed_at":"2026-08-21T19:34:57.423852Z","submitted_at":"2024-07-31T13:29:42Z","title":"Stable Rank and Intrinsic Dimension of Real and Complex Matrices","version":2},"cited_work":{"arxiv_id":"2407.21594","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.21594","snapshot_observed_at":"2026-08-04T21:12:53.115115Z","title":"Stable Rank and Intrinsic Dimension of Real and Complex Matrices","venue":"math.NA","work_id":"0c742a88-b10b-4515-a404-e488851e12e7","year":2024},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.646727Z"},"links":{"cited_paper":"/paper/2407.21594","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:3e13e289272fe82b8300f7fcf66a3d3ae3c55a1cd463eabe5b24d8a28c83e7a0","observation_id":"d3d3e0c8-5563-4e8f-b0d2-6bc68f627dfa","resolution":{"observed_at":"2026-08-04T21:12:53.123235Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.581383Z","title":"An investigation into neural net optimization via Hessian eigenvalue density","venue":null,"work_id":"47c6e301-0506-48d3-be4d-062384b6c3b0","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.760522Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6ef1378df4a8f7f86cf6cc4bce547b2e55a3724d742fa086c20693010aca64f7","observation_id":"ebd7abd4-8207-4fcb-8f9e-0ea49e5240ef","resolution":{"observed_at":"2026-08-04T21:12:56.584772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.570949Z","title":"Hessian based analysis of SGD for deep nets: Dynamics and generalization","venue":null,"work_id":"d1b6cb82-e86a-4794-953d-38fa3d842a42","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.830056Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:38175cc46a338d8892c4b35bdb58a382f0542d252b2bd55f89c30ea8e21c74c0","observation_id":"54debbf4-ba4d-434c-a834-3ffc7fc686dd","resolution":{"observed_at":"2026-08-04T21:12:56.574281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14342","last_updated":"2024-03-05T17:07:16Z","snapshot_observed_at":"2026-08-20T04:30:51.893630Z","submitted_at":"2023-05-23T17:59:21Z","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14342","snapshot_observed_at":"2026-08-04T21:12:50.922764Z","title":"Sophia: A scalable stochastic second-order optimizer for language model pre-training.arXiv preprint arXiv:2305.14342, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.922764Z"},"links":{"cited_paper":"/paper/2305.14342","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:d0d153da837b610257bbd1e8e56520d8c1829ed876f5506099fc184ba073248c","observation_id":"bd57ed43-8e23-4aee-b56d-253bba041ffb","resolution":{"observed_at":"2026-08-04T21:12:50.922764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07476","last_updated":"2017-10-05T13:28:50Z","snapshot_observed_at":"2026-08-20T15:31:18.469129Z","submitted_at":"2016-11-22T19:24:49Z","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07476","snapshot_observed_at":"2026-08-04T21:12:50.994685Z","title":"Eigenvalues of the Hessian in deep learning: Singular- ity and beyond.arXiv preprint arXiv:1611.07476, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:50.994685Z"},"links":{"cited_paper":"/paper/1611.07476","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:aed2bb4c190afe338f42c564c23be3938f8a2e9a8005fa4c672867b81d986b4c","observation_id":"f646950f-0641-47e7-8df5-a85bfd2daaf3","resolution":{"observed_at":"2026-08-04T21:12:50.994685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.559704Z","title":null,"venue":null,"work_id":"073ae6d9-81f1-4d98-85de-05cdef4d8e90","year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.090809Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:8b81191071028b075ed051aabfde773496e6885d48114d80741474db3d89909b","observation_id":"77f81e85-0a3b-4405-baf8-67ae205969f6","resolution":{"observed_at":"2026-08-04T21:12:56.563379Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.13011","last_updated":"2022-08-01T12:08:24Z","snapshot_observed_at":"2026-08-18T11:51:43.224565Z","submitted_at":"2022-01-31T06:04:47Z","title":"On the Power-Law Hessian Spectrums in Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.13011","snapshot_observed_at":"2026-08-04T21:12:51.213934Z","title":"On the power-law Hessian spectrums in deep learning.arXiv preprint arXiv:2201.13011, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.213934Z"},"links":{"cited_paper":"/paper/2201.13011","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:bd3f17127350b82e96211745867de5110b45a9a3c81486e27d32dc076133ac01","observation_id":"da3bf9bd-86e8-4011-9d01-6e968bd9c813","resolution":{"observed_at":"2026-08-04T21:12:51.213934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16788","last_updated":"2024-10-21T08:27:23Z","snapshot_observed_at":"2026-08-18T11:52:10.492128Z","submitted_at":"2024-02-26T18:01:41Z","title":"Why Transformers Need Adam: A Hessian Perspective","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16788","snapshot_observed_at":"2026-08-04T21:12:51.314436Z","title":"Why trans- formers need Adam: A Hessian perspective.arXiv preprint arXiv:2402.16788, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.314436Z"},"links":{"cited_paper":"/paper/2402.16788","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:30750f591635bcd1855b46c76fb287a5ad4154f43b35cd43c96ec1923e8474d0","observation_id":"97ac1617-c7de-4a19-8d93-597025ab19dd","resolution":{"observed_at":"2026-08-04T21:12:51.314436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.548910Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"546d01d5-8db2-4b14-a84e-eaec0a3a33e4","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.412648Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:3a4771fae65af22e0cc9f264eec267232c0399b0317fbdff8c75b0317398a67f","observation_id":"32eac1fe-ebca-4b3e-81c2-9e477c1c7ec7","resolution":{"observed_at":"2026-08-04T21:12:56.552673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-08-19T20:02:33.106623Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-08-04T21:12:51.552457Z","title":"FedNL: Making Newton-type meth- ods applicable to federated learning.arXiv preprint arXiv:2106.02969, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.552457Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:429968324f34d274c7e89daa480c8351e02de4b512ec4d88f086a3e258918a17","observation_id":"bd38a1f0-30da-4202-b684-0465e3d5210e","resolution":{"observed_at":"2026-08-04T21:12:51.552457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.538623Z","title":"Momentum provably improves error feed- back!Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"eb8bb187-a4c4-46c4-9e49-deaf06c51db8","year":2024},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.638087Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:ebb1c19d1eeb24a7a87c7e48e9931e3c8b76a6b17570c38af7c50cef92900f8d","observation_id":"2665af9f-ed34-477c-950f-4a8e52bf871b","resolution":{"observed_at":"2026-08-04T21:12:56.541939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.359311Z","title":"FetchSGD: Communication-efficient federated learning with sketching","venue":null,"work_id":"a859c7b1-4f83-4aa8-a74e-abd27e02c063","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.728189Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:27cb93b9db16b8fb0412ae23564ba6626290f311eaedef54a7eaf6724afd6f07","observation_id":"e1f410f8-a41a-4270-83e0-327535896515","resolution":{"observed_at":"2026-08-04T21:12:56.427694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-04T21:12:51.774554Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.774554Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:400c8b5494c1cde4aea408ea8c4a2e02515b9a5eaf27fc299e437da136c5dae6","observation_id":"3db9492f-a44c-42f1-ba54-2295f4b8f930","resolution":{"observed_at":"2026-08-04T21:12:51.774554Z","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":"2026-08-04T21:12:51.869846Z","title":"Adaptive methods for nonconvex optimization.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.869846Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:427873f165f875a177baabca16d8d8901f342c3cac65b833350515a2828b8642","observation_id":"6676055f-7c97-4d41-9f09-12d5525ef01d","resolution":{"observed_at":"2026-08-04T21:12:51.869846Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:56.183628Z","title":"Improved convergence of differential private SGD with gradient clipping","venue":null,"work_id":"a5fe93bd-c5f4-4cba-be75-46edf62f371d","year":2023},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.933984Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:16fa19206a22ca46abd1ad1995545d27daac158a3aa48c3c29c78952d11ca7ba","observation_id":"a4cfab35-b12b-4a54-ab84-c5d8b8b2fcb9","resolution":{"observed_at":"2026-08-04T21:12:56.223603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.995786Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","venue":null,"work_id":"6b30cf52-d29d-426b-97f4-a2753b078d21","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.005075Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6862a065c123314790e9d27f64d599f652ef82f63f3a5d1b5bb9f14a0e2bccb5","observation_id":"5c7f80f8-17eb-4d05-814e-7f202ca28686","resolution":{"observed_at":"2026-08-04T21:12:56.066768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.867640Z","title":"Information leaks in federated learning","venue":null,"work_id":"65ad3d89-b66e-4c8c-90c0-55ee843bfdbe","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.066259Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:9391d498af9c5cc974084d21b76a3a160b630cea81604bd27550f1bc3fe0ab18","observation_id":"283b07f0-263c-4c73-b4b5-954e434f9e23","resolution":{"observed_at":"2026-08-04T21:12:55.915871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.732730Z","title":"DBA: Distributed backdoor attacks against federated learning","venue":null,"work_id":"260eace8-7fd4-4e13-8a8e-2748ea0cd141","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.127461Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:c90e9934b1e7975fbef1550887eb9c3f1d320a6c28d7b497ff346131790f48af","observation_id":"0df0d5c4-579d-481c-bcb0-274a6b480545","resolution":{"observed_at":"2026-08-04T21:12:55.783229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-20T00:01:01.707115Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-04T21:12:52.224737Z","title":"IDLG: Improved deep leakage from gradients","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.224737Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:77565bdcfb5a514577fa8d3cd9504261356b8079bcdceedc62a2bad134bef006","observation_id":"185ded53-f506-4cd6-b3f4-6b941656c205","resolution":{"observed_at":"2026-08-04T21:12:52.224737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.562767Z","title":"Deep leakage from gradients.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"3cde99a1-bc28-4a50-b72d-e7acd48c29ce","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.291775Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:7c47fc0c3471da5d372a447c45f3115acefe83d87a58dee57bd878b8176ffa44","observation_id":"a7d931bf-b3e6-4742-99ef-6803574e29bb","resolution":{"observed_at":"2026-08-04T21:12:55.631581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.364982Z","title":"Andersen, Jun Woo Park, Alexander J","venue":null,"work_id":"6a91a1a3-5c6c-4456-91cd-e577982c3059","year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.329006Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:ad82bc93f73d7d5f77fd8f07ca13c0fcf3c1307cebf9f8fcd3225c6bc6c3f104","observation_id":"2ff8bba1-e1cb-4728-94ad-bedf54b7e018","resolution":{"observed_at":"2026-08-04T21:12:55.454527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:55.172481Z","title":"Brendan McMahan, Brendan Avent, Aur ´elien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al","venue":null,"work_id":"12d5cd58-2279-4734-9370-9d43755a30f3","year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.422405Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:c878a8a1ef5b39741ca6efdf2995fbe11395516e694ea5afbdd55b91a6005aae","observation_id":"b2b1e4a3-dcc2-452a-bc3d-00bd742b2132","resolution":{"observed_at":"2026-08-04T21:12:55.246695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:54.963127Z","title":"Andersen, Alexander J","venue":null,"work_id":"54caf20f-6f93-46c9-a2af-1f2b62948aa0","year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.526823Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:11df3f3fead9bde0f2e01e1b69aa980c7373673709b7140ede2eb233dedde272","observation_id":"28420740-cf23-4032-adad-dc1d06964f06","resolution":{"observed_at":"2026-08-04T21:12:55.041200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.01887","last_updated":"2020-06-23T03:28:30Z","snapshot_observed_at":"2026-08-18T15:24:54.289687Z","submitted_at":"2017-12-05T19:48:11Z","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.01887","snapshot_observed_at":"2026-08-04T21:12:52.601296Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.601296Z"},"links":{"cited_paper":"/paper/1712.01887","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:ecd5a49a2db423f7ba8a6a7f6fae6b361302c5b9bee40408d2a20870095664d3","observation_id":"4fd12059-a8be-43c1-b2c4-3f461ff46945","resolution":{"observed_at":"2026-08-04T21:12:52.601296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:54.775549Z","title":"Atomo: Communication-efficient learning via atomic sparsification.Advances in Neural In- formation Processing Systems, 31, 2018","venue":null,"work_id":"6a394db1-3d23-417f-a982-c4f8468c5f85","year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.662245Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:27baebec9211b369dae5396000f4f837138129c741cf8ea8ce4bbcadeb51b508","observation_id":"097a903e-1ba1-45aa-9d01-9dfffa3e73da","resolution":{"observed_at":"2026-08-04T21:12:54.850468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:54.533273Z","title":"Inan, Berivan Isik, Ayfer Ozgur, and Tsachy Weissman","venue":null,"work_id":"af274c42-9a96-47f1-a552-e7964cb953ff","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.707590Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6f8c37bafd6fcb11b160e8a11c976543497013d9ba4e2659c8bc567ba7515dab","observation_id":"5abefdd8-72ce-4c46-b337-f0179d9d641c","resolution":{"observed_at":"2026-08-04T21:12:54.624542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:54.223349Z","title":"QSGD: Communication- efficient SGD via gradient quantization and encoding.Advances in Neural Information Processing Sys- tems, 30, 2017","venue":null,"work_id":"823a8fdf-38b7-424a-b224-07cfa85fc4ad","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.710747Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6f275fac336d4ac635e39d03874d07e2b5909eb61d8a2b4da8d66d4c19dafb5f","observation_id":"a48c6935-423a-42e0-beee-018463cfe1d4","resolution":{"observed_at":"2026-08-04T21:12:54.345176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:54.034751Z","title":"Communication-efficient federated learning for heteroge- neous edge devices based on adaptive gradient quantization","venue":null,"work_id":"23256846-57d0-4200-8cc6-3136e37b22bf","year":2023},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.713861Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:5cbb57938948b5d43568f9c46b34010a05c376de18ad8dbccb450257f33639fe","observation_id":"5f2710ca-8e7f-4afe-9380-dfd931fff0a9","resolution":{"observed_at":"2026-08-04T21:12:54.107132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.763415Z","title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quanti- zation","venue":null,"work_id":"f4ef2fe6-5c83-4fb3-a861-368dcf1167a6","year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.717193Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:0d66c282b1e42246765e2240808311a2fe14bf50278de5359d440ed5fb9b9008","observation_id":"2ea4794f-14a6-4073-92d4-4ea86d57b3d9","resolution":{"observed_at":"2026-08-04T21:12:53.870976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.697449Z","title":"Communication-efficient distributed SGD with sketching.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"4b298109-fe6f-408f-91c3-9bd3afd8d264","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.720123Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:2825b781d391d241ca5ee8aa015945da44d277447c4fe84c4ed3cd6ae4b41a40","observation_id":"c115bb44-dc6a-46a8-9768-d1056bccf986","resolution":{"observed_at":"2026-08-04T21:12:53.719880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.628390Z","title":"Stich, Jean-Baptiste Cordonnier, and Martin Jaggi","venue":null,"work_id":"0bde50d9-d358-4701-90d7-4ea2b646f1f8","year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.723419Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:ea44e46c0f31325559c0e73b3b1251b51dd27ce9ef161db00273e1672303beb6","observation_id":"eb9d3f31-8f91-4526-baaf-b2542484f5ac","resolution":{"observed_at":"2026-08-04T21:12:53.658522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.603025Z","title":"LDP-Fed: Federated learning with local differential privacy","venue":null,"work_id":"9abc4b8b-bd36-4b8a-b9a3-55848a1be3ca","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.727289Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:5f0d492a99ddb9541ce7c7ee5ddc8d0d6e9dcc130018943861d3e264600fa5fd","observation_id":"5b19600b-3ff2-4bba-a22d-24ea19468357","resolution":{"observed_at":"2026-08-04T21:12:53.610194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.576293Z","title":"A hybrid approach to privacy-preserving federated learning","venue":null,"work_id":"d3d22a77-19f5-4c38-a0ce-3c17256bf407","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.730266Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:00088bd52af055b789247407e797d9ce2af156e0a56a405fef64b0c91aaeca72","observation_id":"2ddbaf9f-3b93-4be8-9b33-3b99030f8244","resolution":{"observed_at":"2026-08-04T21:12:53.587634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.564149Z","title":"Canonne, Gautam Kamath, and Thomas Steinke","venue":null,"work_id":"981fa49d-8516-414c-987c-4691247ce7c8","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.733754Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:7773d8c6da191f9188779a22a6f9f2654c6cd29d5180d75fc8afdcec0d7bb356","observation_id":"f3d4810c-bd71-4a1a-bcf7-081d81a44b79","resolution":{"observed_at":"2026-08-04T21:12:53.567550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.05021","last_updated":"2017-07-24T21:47:51Z","snapshot_observed_at":"2026-08-17T23:05:43.968470Z","submitted_at":"2017-04-17T16:32:02Z","title":"Sparse Communication for Distributed Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.05021","snapshot_observed_at":"2026-08-04T21:12:52.736913Z","title":"Sparse communication for distributed gradient descent.arXiv preprint arXiv:1704.05021, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.736913Z"},"links":{"cited_paper":"/paper/1704.05021","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:89a34f5d5e5d0e6f7ffeeb51d8945d39e11d9259470b2bc711ad33870bb2a1e4","observation_id":"b76e01a2-3435-44a9-abc0-4fc254701c87","resolution":{"observed_at":"2026-08-04T21:12:52.736913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.552507Z","title":"Yu, Sanjiv Kumar, and H","venue":null,"work_id":"af9b2b53-fa07-4a51-9ca6-c7c3fed6053e","year":null},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.740367Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:94b18c370e63fdc34e1647e2c5b0d732952ac0b1c1d3df6c855ea8df8a6cbf15","observation_id":"069ec941-891d-4576-9d44-d9aadcc68136","resolution":{"observed_at":"2026-08-04T21:12:53.556211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.540683Z","title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning.Advances in Neural Informa- tion Processing Systems, 30, 2017","venue":null,"work_id":"fb94dc4f-13c6-41fc-b2f2-a7e116d15174","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.743671Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:9a316eeb544006835714f4bfaad27529e758f0395fb87a64074d5125a092691a","observation_id":"dd15e354-d220-4c75-8193-f85f08027b99","resolution":{"observed_at":"2026-08-04T21:12:53.544594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.526703Z","title":"Drive: One-bit distributed mean estimation.Advances in Neural Information Processing Sys- tems, 34:362–377, 2021","venue":null,"work_id":"51da84f4-df0f-4a5f-9c91-8a34f307b01a","year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.746616Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:9a790e721028992d85d795891486f4c6a4f7327246ed092a95373502ff3228dc","observation_id":"075230c9-f2ab-4525-a6a8-924b243c4f81","resolution":{"observed_at":"2026-08-04T21:12:53.532155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.514496Z","title":"Masked training of neural networks with partial gradients","venue":null,"work_id":"fa8d997f-e44a-4a18-b146-e252ca2c7fca","year":null},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.749748Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:6ab2c7fab324a972042b123bbba8554ff7b0a02e235ad268539a5e3bf54a58e5","observation_id":"874b6f07-da5f-4a85-b82e-e0538ee71772","resolution":{"observed_at":"2026-08-04T21:12:53.517931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.502604Z","title":"PowerSGD: Practical low-rank gradient compression for distributed optimization.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"ded4d717-b561-4d36-8383-dd75830698c1","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.752955Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:f61e2585e2bc99991e2a7e632f820663013b5bf1097df751e44762035fbf96a0","observation_id":"50d2822d-76db-470c-be92-a1858c3ec1a8","resolution":{"observed_at":"2026-08-04T21:12:53.506443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.490529Z","title":"SketchML: Accelerating distributed machine learning with data sketches","venue":null,"work_id":"10ae23ce-a614-4016-b16f-6a7383322158","year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.756010Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:cec32aa1274c9736b7455b1e277b5bcf192f4793546290c47c36285ae23142ec","observation_id":"4d938735-70e9-4482-a18c-a2886ecacde3","resolution":{"observed_at":"2026-08-04T21:12:53.494210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15328","last_updated":"2023-02-09T01:54:34Z","snapshot_observed_at":"2026-08-16T16:27:54.312768Z","submitted_at":"2022-09-30T09:11:09Z","title":"Sparse Random Networks for Communication-Efficient Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15328","snapshot_observed_at":"2026-08-04T21:12:52.759124Z","title":"Sparse random networks for communication-efficient federated learning.arXiv preprint arXiv:2209.15328, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.759124Z"},"links":{"cited_paper":"/paper/2209.15328","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:40a6b457decb045a709fba7f99f3d34ef05c1e94a351185f7618115bd250d0e9","observation_id":"40a57b13-27ed-4d7c-bba4-2ae9b7704a70","resolution":{"observed_at":"2026-08-04T21:12:52.759124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03371","last_updated":"2020-08-07T20:45:12Z","snapshot_observed_at":"2026-08-14T20:23:06.504001Z","submitted_at":"2020-08-07T20:45:12Z","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03371","snapshot_observed_at":"2026-08-04T21:12:52.762668Z","title":"LotteryFL: Per- sonalized and communication-efficient federated learning with lottery ticket hypothesis on non-iid datasets.arXiv preprint arXiv:2008.03371, 2020","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.762668Z"},"links":{"cited_paper":"/paper/2008.03371","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:5d5a178b0ccf6ae1def46865e337aeca2c51f8107434e2eda4bd85d1e1a6c357","observation_id":"2ff1e93b-bfba-452d-9e99-fda5880eb099","resolution":{"observed_at":"2026-08-04T21:12:52.762668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.477959Z","title":"FedMask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking","venue":null,"work_id":"d03bc300-b8bd-4c60-b327-a7ddb7e23d4c","year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.765889Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:a9c0b4226ab6ffd502f17769b31751f9ea3034ecc2d3b21335d5996ce2ccdeff","observation_id":"f71be9f4-2a10-4268-9d8b-0846251257c8","resolution":{"observed_at":"2026-08-04T21:12:53.482074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.463954Z","title":"An improved data stream summary: the count-min sketch and its applications.Journal of Algorithms, 55(1):58–75, 2005","venue":null,"work_id":"77e67b69-454a-4013-9d3c-d30b0b8d8feb","year":2005},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.768968Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:d06db3d48be6bcf08960070ff7106902b1a5c97eb45c88c81e4b7ddf1f6032e5","observation_id":"1f08b048-1df0-4432-8c19-1d433a5b0438","resolution":{"observed_at":"2026-08-04T21:12:53.468395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.449839Z","title":"Space-efficient online computation of quantile summaries","venue":null,"work_id":"e1cc95d4-ac6a-48e7-bbc7-e8dc54045b2a","year":2001},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.771881Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:c18d39f0b005342f951aa76daff38dd2372c70076572b9492388d8287b4988eb","observation_id":"53d65609-cc8b-4d04-be56-558db50c47d7","resolution":{"observed_at":"2026-08-04T21:12:53.454142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.436966Z","title":"Kane and Jelani Nelson","venue":null,"work_id":"5173aba9-f310-47ae-a748-ef2305d666e7","year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.775116Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:a9e38a9eac1c5480dc01dee536ecc1cbc07eb887622a9f3ff88859bfbdee2917","observation_id":"7892d047-8087-4ae9-820b-c77ac852c81e","resolution":{"observed_at":"2026-08-04T21:12:53.440396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.425318Z","title":"Tropp, Alp Yurtsever, Madeleine Udell, and Volkan Cevher","venue":null,"work_id":"f0dbfe9a-2eba-4e59-9d3f-272a23a5fc69","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.777970Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:7891babe8525984d8fca6f82e63967e86b81de2d48e541e4ddef1fe4125fd0f5","observation_id":"e7d58e71-7f05-4f12-b451-ce2e4b7e5ceb","resolution":{"observed_at":"2026-08-04T21:12:53.429179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.412649Z","title":"Graph sketches: sparsification, spanners, and subgraphs","venue":null,"work_id":"4ae7f448-20a3-4a6b-9ce9-bac4772bc1b7","year":2012},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.780899Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:af586f489937a4f3f801f77160ac516a6db015d5ddc5c3e9f27d78964393c631","observation_id":"74503705-96c3-42f3-ab3c-6196e7c35d15","resolution":{"observed_at":"2026-08-04T21:12:53.416819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.400959Z","title":"Asymptotics for sketching in least squares regression.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"b3e0c4fd-a1b7-490b-9675-7b959af7d80f","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.783883Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:19d80079cb6f97576f5837e5face4cf463c1f6db59ac26d9ad1ec98750704705","observation_id":"e6d4e0d0-08d3-46e8-be56-67e3dfcfb75a","resolution":{"observed_at":"2026-08-04T21:12:53.404506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.04975","last_updated":"2020-08-11T19:22:48Z","snapshot_observed_at":"2026-08-17T15:49:22.129735Z","submitted_at":"2020-08-11T19:22:48Z","title":"FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching","version":1},"cited_work":{"arxiv_id":"2008.04975","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.04975","snapshot_observed_at":"2026-08-04T21:12:52.959717Z","title":"FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching","venue":"stat.ML","work_id":"f256e06b-a499-470c-90b4-6b1438cecad7","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.786724Z"},"links":{"cited_paper":"/paper/2008.04975","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:020142909aad77fc9066948e7f9a9c3c82ceedeaea0b886088902a79006666fc","observation_id":"6f31e1a6-5f4d-4dc3-857d-f42b2f85fc19","resolution":{"observed_at":"2026-08-04T21:12:52.964037Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.387230Z","title":"Choquette-Choo, Peter Kairouz, and Ananda Theertha Suresh","venue":null,"work_id":"f46346b4-d10a-4f7d-b551-461c06ee7259","year":2022},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.789854Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:9b91bb82cd01a2c666e88b3790259fcf2d8c9e3d1eac868b4dfd75920399a010","observation_id":"52dae356-ef0f-42db-bb2b-6d162a7c9bcf","resolution":{"observed_at":"2026-08-04T21:12:53.391785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.373635Z","title":"The algorithmic foundations of differential privacy.Foundations and Trends in Theoretical Computer Science, 9(3–4):211–407, 2014","venue":null,"work_id":"91eca5b3-4d41-42ca-95fe-80fbcdcf775f","year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.793315Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:f510ac3223e2212ddb7aaacfdc82b1df6db3b4a48b44dd9794ecd9654c4ca0ac","observation_id":"fc970a66-855f-4dc6-afd8-6ba293cb3c0f","resolution":{"observed_at":"2026-08-04T21:12:53.377510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.356141Z","title":"Yang, Farhad Farokhi, Shi Jin, Tony Q","venue":null,"work_id":"e5a84948-2211-4b7e-8c2b-6b0d0069b045","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.796509Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:efe3bd7edaf409c96de40b25be33685cdd34d91bd07bf6ea698a4920f40b970e","observation_id":"628aa69e-8ec8-4791-afdc-6dec62ec98d4","resolution":{"observed_at":"2026-08-04T21:12:53.364130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.343183Z","title":"Brendan McMahan, Sar- var Patel, Daniel Ramage, Aaron Segal, and Karn Seth","venue":null,"work_id":"2e5281ea-6feb-41e7-bc64-c72b79649a49","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.799802Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:f9c1020f9711a7b925bb702ee56f1b8588be004ee99d6ddc828057f7e1224c89","observation_id":"fb5f5a17-d792-4b09-8437-d6c8856f5685","resolution":{"observed_at":"2026-08-04T21:12:53.347032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.330137Z","title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs","venue":null,"work_id":"c32f8d7e-1cbd-4bfc-af2c-9401201fb2a9","year":2014},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.803288Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:f10c8f9ee650f6330870099b9da85917517b096182cda9d10072a8cd159a0e14","observation_id":"99b48097-43e6-498a-8049-cf18632bc88a","resolution":{"observed_at":"2026-08-04T21:12:53.333917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.317810Z","title":"An elementary proof of a theorem of Johnson and Linden- strauss.Random Structures & Algorithms, 22(1):60–65, 2003","venue":null,"work_id":"9349b13f-e026-49fe-9a68-b8d78630c53d","year":2003},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.806545Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:b6e061f400752bdcdd4be6c53b95102d7168c99e8d28b2df06a3a3643973f79f","observation_id":"18f14081-342f-486b-965a-0e7d4babc3d3","resolution":{"observed_at":"2026-08-04T21:12:53.321714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.304055Z","title":"Group normalization","venue":null,"work_id":"037150ea-e023-40b8-9dc4-f36c8df2ce55","year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.809473Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:3ef0858be04fa88c09f370a924501ff38889872308fc11ccc029d5d61d40f9bc","observation_id":"523aa17d-afe3-4b7b-b2a1-aff49b877134","resolution":{"observed_at":"2026-08-04T21:12:53.308244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.289369Z","title":null,"venue":null,"work_id":"b733aeb6-2e7a-4321-84a2-829c2ff48579","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.812411Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:105164885866c99c3af9efabf20f2d8d86bf9bfd1feafcdfc921d04a8c711bc5","observation_id":"8a1fbd06-7620-43d9-a841-3815c0731771","resolution":{"observed_at":"2026-08-04T21:12:53.293834Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:52.815709Z","title":"Adaptive subgradient methods for online learning and stochastic optimization.Journal of Machine Learning Research, 12(7), 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.815709Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:53bb4d5d528447d89dfd927bb5fc237b53a545be342e2c1673c1b5e280c7f359","observation_id":"b172e0fb-80ea-4e55-ab32-887659c79ede","resolution":{"observed_at":"2026-08-04T21:12:52.815709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.262414Z","title":"Divide the gradient by a running average of its recent magni- tude","venue":null,"work_id":"c0fdd884-22b5-4703-aee9-a1c00408cdcc","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.818551Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:84eff4dcda54aadfe20fa4cd6acd2db2fc657b443f293b8d6256b96d598ca7b7","observation_id":"1e6ab9db-ba45-406c-a82a-f3680c9224c9","resolution":{"observed_at":"2026-08-04T21:12:53.265923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.5701","last_updated":"2012-12-22T15:46:49Z","snapshot_observed_at":"2026-08-19T05:19:50.480481Z","submitted_at":"2012-12-22T15:46:49Z","title":"ADADELTA: An Adaptive Learning Rate Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.5701","snapshot_observed_at":"2026-08-04T21:12:52.821331Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.821331Z"},"links":{"cited_paper":"/paper/1212.5701","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:225f47b8a0581a8d4a91b9268d995d8f8832ebdce0adb758e959737c791d5638","observation_id":"dae07019-ae4f-40f9-a7ae-bf754d0a9148","resolution":{"observed_at":"2026-08-04T21:12:52.821331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09843","last_updated":"2019-02-26T10:22:48Z","snapshot_observed_at":"2026-08-19T14:19:09.693041Z","submitted_at":"2019-02-26T10:22:48Z","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.09843","snapshot_observed_at":"2026-08-04T21:12:52.824549Z","title":"Adaptive gradient methods with dynamic bound of learning rate.arXiv preprint arXiv:1902.09843, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.824549Z"},"links":{"cited_paper":"/paper/1902.09843","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:7838a0ddc4ed231883aa69ecf1c359769b5ccf63fb08276fd7e709ae49038151","observation_id":"e6750a05-ddb7-46f3-914a-e06c17246a11","resolution":{"observed_at":"2026-08-04T21:12:52.824549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00295","last_updated":"2021-09-08T23:37:17Z","snapshot_observed_at":"2026-08-13T06:06:10.844945Z","submitted_at":"2020-02-29T16:37:29Z","title":"Adaptive Federated Optimization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.00295","snapshot_observed_at":"2026-08-04T21:12:52.827626Z","title":"Brendan McMahan","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.827626Z"},"links":{"cited_paper":"/paper/2003.00295","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:361a176d2786a339a8a6914204726362a9c86aea40a5128d56dcc9914805452a","observation_id":"b6a6243d-b713-499a-b08f-6f25bd7b456a","resolution":{"observed_at":"2026-08-04T21:12:52.827626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.250288Z","title":"R ´enyi differential privacy","venue":null,"work_id":"576e5327-94e4-4c27-8144-3ddcb8c57643","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.830689Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:dcc4df5faffdfc75447c3dcc0351b596209945ad1f4890f19c784d7c65a01ccf","observation_id":"7ac90d1f-ecf3-4e26-ba97-3b1059588aee","resolution":{"observed_at":"2026-08-04T21:12:53.253806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.00972","last_updated":"2019-12-06T18:35:54Z","snapshot_observed_at":"2026-07-06T08:34:24.211365Z","submitted_at":"2019-11-03T21:19:13Z","title":"Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches","version":2},"cited_work":{"arxiv_id":"1911.00972","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.00972","snapshot_observed_at":"2026-08-04T21:12:52.912390Z","title":"Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches","venue":"cs.LG","work_id":"3b5f9166-f5c7-47e2-b686-d7f85698f465","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.833619Z"},"links":{"cited_paper":"/paper/1911.00972","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:e2ddbac13cbfcb790e8e9b00e3874146f5e4487b25cf0a2caf919c77fb1d517c","observation_id":"28112a80-d482-4b37-89cc-b70dd5ef4ecc","resolution":{"observed_at":"2026-08-04T21:12:52.918559Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.236795Z","title":"On measures of entropy and information","venue":null,"work_id":"8ab1481f-4ddb-4294-b6cf-ae91ceb839f1","year":1961},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.837071Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:56252459e5bca68274f5ed38b6dc9d22caca64944101cb557fe1bfb4abe41911","observation_id":"1f027e3a-f9ad-4637-bc5f-05bdd3f08a79","resolution":{"observed_at":"2026-08-04T21:12:53.240687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.223061Z","title":null,"venue":null,"work_id":"e54a97a1-7b0e-4211-8a57-6c65b32a044c","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.840175Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:de70d8f2771dc979f1a64cac1af48647eab30d12549ccc5ff84829b3a1e982de","observation_id":"3d59527d-6e90-4341-b107-29026be99673","resolution":{"observed_at":"2026-08-04T21:12:53.227685Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-08-16T09:50:11.319379Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-04T21:12:52.843063Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.843063Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:39402e14edb60e54fb72d307fc185df16dc44c65c5375a94609c4ccc315e3c98","observation_id":"da102f70-0ff1-4631-9df3-e662c8652678","resolution":{"observed_at":"2026-08-04T21:12:52.843063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.208083Z","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"a89325d0-65fa-4843-beaa-69e132222ef9","year":2019},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.846287Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:89770fc8c122687ca13381a1de9028ae7baadc57424c2f5c84c991a1597f11d2","observation_id":"502791fa-0dd0-4087-a976-4125e09cbae8","resolution":{"observed_at":"2026-08-04T21:12:53.213045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1508.06110","last_updated":"2016-01-06T10:35:43Z","snapshot_observed_at":"2026-08-14T22:35:19.383771Z","submitted_at":"2015-08-25T11:24:11Z","title":"Efficient Private Statistics with Succinct Sketches","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.06110","snapshot_observed_at":"2026-08-04T21:12:52.849424Z","title":"Efficient private statistics with succinct sketches.arXiv preprint arXiv:1508.06110, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.849424Z"},"links":{"cited_paper":"/paper/1508.06110","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:bba61f44a44564d59480ff99edda66264699c674972501be0aecd94e98739b3e","observation_id":"b89d0893-f0a7-476d-9449-9cb8fe6fc7e7","resolution":{"observed_at":"2026-08-04T21:12:52.849424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.193768Z","title":"Federated heavy hitters discovery with differential privacy","venue":null,"work_id":"fd18ddf1-d101-4932-b165-464e1bad754f","year":2020},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.852628Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:b3cbcb63b89982a14787c369c9f0cd0bfbcf8e42edcebd8fdc69048ee01c9583","observation_id":"9cfe8cd4-b196-454e-b83c-bf009d1fa298","resolution":{"observed_at":"2026-08-04T21:12:53.197527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T21:12:53.181501Z","title":"ηlocal N X c∈Ct R⊤ t Rtclip ∆c,t ηlocal , τ +R ⊤ t zc,t # i ≤ √1−β 2ηlocal N ϵ2 X c∈Ct R⊤ t Rtclip ∆c,t ηlocal , τ i + √1−β 2ηlocal N ϵ2","venue":null,"work_id":"bd7be473-9e12-4325-b6fd-7ed72c77687a","year":2017},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:52.855661Z"},"links":{"citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:eef6223dede67fc338befd8871a1203b0c1c0907d52e839481955cd86d5349c0","observation_id":"f05d994b-91e4-4fb8-b76d-aad2dc4e8ec9","resolution":{"observed_at":"2026-08-04T21:12:53.185685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T23:02:38.802679Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning"},"reference_resolution":{"displayed":85,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":4,"verified_fuzzy":52},"total_outbound_references":85},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 0 inbound Pith citation observations for arXiv:2509.08195."}