{"as_of":"2026-08-10T13:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7099103d7023bfd2024155508f1afe6c4c254ea179c74c251b33e3946f5d3ad3","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T23:32:14.132646Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.08889/citation-record","integrity":"/paper/2502.08889/integrity","json":"/paper/2502.08889/citation-record.json","paper":"/paper/2502.08889"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.725326Z","title":"Private stochastic convex optimization: Optimal rates in l1 geometry","venue":null,"work_id":"7d74f633-afaa-4360-90ed-8c25e8f7444d","year":2021},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.960500Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:e4bcb43b4452c964d4073926a91e9213a65752eeed49435075ba55fddea16804","observation_id":"24c25b6e-cb9a-4751-83bb-1899f53ac5a6","resolution":{"observed_at":"2026-08-07T23:32:14.730391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.708871Z","title":"User-level differentially private stochastic convex optimization: Efficient algorithms with optimal rates","venue":null,"work_id":"e2e490b7-ad1f-487d-b31a-2898e34068b6","year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.966622Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:7f076c1377a902efe46b8b9659fc3d505a2c6e435442dce605f189da42b2ffa7","observation_id":"b9ec761c-f1b6-41e8-8c4c-e8e7ad7eb7c5","resolution":{"observed_at":"2026-08-07T23:32:14.714107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02789","last_updated":"2024-06-04T21:26:29Z","snapshot_observed_at":"2026-08-09T17:03:44.022622Z","submitted_at":"2024-06-04T21:26:29Z","title":"Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions","version":1},"cited_work":{"arxiv_id":"2406.02789","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.02789","snapshot_observed_at":"2026-08-07T23:32:14.238500Z","title":"Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions","venue":"cs.DS","work_id":"a542f6ae-1f15-4880-a0ad-73a6b2748929","year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.971954Z"},"links":{"cited_paper":"/paper/2406.02789","citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:f272a89de8d65ad7bc1d689f955f298061580040914dc5411594353fab30bd87","observation_id":"4b663058-1031-4a6c-be7c-2ac7fd45cc67","resolution":{"observed_at":"2026-08-07T23:32:14.245977Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.692736Z","title":"From robustness to privacy and back","venue":null,"work_id":"bd9b2663-e5a5-4c44-b3e3-b38a1d61d9d4","year":2023},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.977807Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:037e0178324e1e081bede641f50ce19e55612e420b81569ddc8fb879461c7938","observation_id":"27054927-cde9-4e0b-92ea-7658edfa0738","resolution":{"observed_at":"2026-08-07T23:32:14.697913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.676554Z","title":"Information-theoretic lower bounds on the oracle complexity of convex optimization","venue":null,"work_id":"8f200540-fc7a-4ac8-a957-ceb4c43dd681","year":2009},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.983324Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:b7693eec9e617decf30fe7c796b04fcd075c8d1a87d3885b80151e6df5d6725b","observation_id":"60965546-da1d-490f-af10-4bc5b2b474ca","resolution":{"observed_at":"2026-08-07T23:32:14.681752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.06914","last_updated":"2020-06-12T02:45:21Z","snapshot_observed_at":"2026-08-04T23:39:17.985764Z","submitted_at":"2020-06-12T02:45:21Z","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.06914","snapshot_observed_at":"2026-08-07T23:32:13.988581Z","title":"Stability of stochastic gradient descent on nonsmooth convex losses","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.988581Z"},"links":{"cited_paper":"/paper/2006.06914","citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:8d6cdd347307b20c3e2ec29da85fde31d21baabc594412532d94c5b03913c97a","observation_id":"5cfaff41-dfaf-45d9-b0f4-93e32f02e739","resolution":{"observed_at":"2026-08-07T23:32:13.988581Z","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":"2026-08-07T23:32:14.660111Z","title":"Private stochastic convex optimization with optimal rates","venue":null,"work_id":"1171969e-bc21-46c4-bc8a-90ec4c14cb6b","year":2019},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.994750Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:bec25549547d0af87a490566a2dbe3715d323fc40b16b79d29fdd87056e5c106","observation_id":"dbca089b-0444-4b6c-9f7c-3df5ccd0bfb7","resolution":{"observed_at":"2026-08-07T23:32:14.665288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.644380Z","title":"Non-euclidean differentially private stochastic convex optimization","venue":null,"work_id":"af90b61b-5411-42ff-a2e8-799f759b5751","year":2021},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:13.999572Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:621b85d286fc1c70a6a4bb07e5c8693bb52e8805ba5323ecebc526450dbc3880","observation_id":"2981c22d-29cf-4913-b757-7ffbc0b73c39","resolution":{"observed_at":"2026-08-07T23:32:14.649417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.628147Z","title":"Practical gauss-newton optimisation for deep learning","venue":null,"work_id":"39952a79-a822-46f7-bf15-c360dc01a802","year":2017},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.004750Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:f19bf5ab6a6f5c94d5e69d8da8e6417b7411ab0d2577fe74874a1c41f1059979","observation_id":"2c10ed38-3f65-4e93-bc65-0e3a03c67ad5","resolution":{"observed_at":"2026-08-07T23:32:14.633826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.611932Z","title":"User-level private stochastic convex optimization with optimal rates","venue":null,"work_id":"6dc0ad13-aee6-4247-9fe5-0683cea64112","year":2023},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.009908Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:2d6cd8a645f3481f69b02d0c67126dde8ff419ab828ca6e1e5e1a40564c60d79","observation_id":"022ef1f0-82b9-4622-b2c0-1f91087d4263","resolution":{"observed_at":"2026-08-07T23:32:14.617238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.596215Z","title":"Private empirical risk minimization: Efficient algorithms and tight error bounds","venue":null,"work_id":"ee0035ac-501b-44e4-b0fa-f2e4205c0911","year":2014},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.014779Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:d4f02de3f8099d16299e01cd4bb8ad97a129a32d092b97810e2f65cffd83d317","observation_id":"329b9531-f48e-4d46-8f04-94ab79e777a4","resolution":{"observed_at":"2026-08-07T23:32:14.601313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.581462Z","title":"Convex optimization: Algorithms and complexity","venue":null,"work_id":"e26fb00e-ee5c-47e2-aabb-d30f120298b6","year":2015},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.020158Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:a1757bf8bfc60bb5de9333beabbfa66941aac4fdbbcee383636ca80271084d5f","observation_id":"e7061bcf-4948-48d4-8b8a-aa55dea387a4","resolution":{"observed_at":"2026-08-07T23:32:14.585928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.565507Z","title":"Optimal rates for o (1)-smooth dp-sco with a single epoch and large batches","venue":null,"work_id":"effdfd53-682a-443e-a4d4-9d597d747b06","year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.025242Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:ff84eaf08729e128f89af1593838de20689bc7a7df33018e48c37a63eff24fd0","observation_id":"ba4d6bb2-13a6-4014-8e16-91e86cc1f404","resolution":{"observed_at":"2026-08-07T23:32:14.570608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.549318Z","title":"Extracting training data from large language models","venue":null,"work_id":"17e81de7-2801-41df-a4be-94a93e40773a","year":2021},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.030249Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:82fea7bf8d9fbb0619615ee318bcd03403960ef069a902e0e74ee2aa5152d993","observation_id":"f7a03e5c-947a-4914-8ef5-ae61a6f533f8","resolution":{"observed_at":"2026-08-07T23:32:14.554528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07114","last_updated":"2024-02-11T06:21:18Z","snapshot_observed_at":"2026-07-06T17:28:31.413289Z","submitted_at":"2024-02-11T06:21:18Z","title":"Towards Quantifying the Preconditioning Effect of Adam","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07114","snapshot_observed_at":"2026-08-07T23:32:14.035214Z","title":"Towards quantifying the preconditioning effect of adam","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.035214Z"},"links":{"cited_paper":"/paper/2402.07114","citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:ca1cc6933419a1a3a46c244eef27f703c43ae4378bebbc676d9da6d145d81ce5","observation_id":"c07890ce-ceed-4e50-948e-df0cfabdd803","resolution":{"observed_at":"2026-08-07T23:32:14.035214Z","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":"2026-08-07T23:32:14.533266Z","title":"The projection median of a set of points","venue":null,"work_id":"13e55e93-9b4e-4e2c-9e29-53c3c915b70e","year":2009},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.040688Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:6657b2ba184afeb6b9d7e7904296debf53264ecf81d7e037a6271c6a768134cb","observation_id":"bd99c2d6-1e4c-4dfa-90a1-3ce1eb0cd644","resolution":{"observed_at":"2026-08-07T23:32:14.538265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.516251Z","title":"Differential privacy and robust statistics","venue":null,"work_id":"560b549f-fd4a-4db9-9b67-9ddb13e346a6","year":2009},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.045549Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:1f9e0e84eee0a3aeb183aff00f37325167fcef7505917dadc51a516a1e2a4a4f","observation_id":"95ccfebb-5ca5-43ec-b00c-89ee0b8e964f","resolution":{"observed_at":"2026-08-07T23:32:14.521319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.499941Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"7741f9e3-b424-47a4-859a-70b21c24c908","year":2006},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.050571Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:5a5776f15dc3d8651bf4c650c7c3fe4da88c90f7e2f1c9f5ca25610db91f3776","observation_id":"a4bdb948-a773-4ce7-8e6c-d6c1ea48c053","resolution":{"observed_at":"2026-08-07T23:32:14.505368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.484541Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"efe23fef-218a-4b04-a3e5-c18272a221db","year":2014},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.054964Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:46b8a2c9b3dd700e8b3c15068040e13a59ada2bfb2e799f591a0a15ed5b1fb1a","observation_id":"7aac0ea0-1dc5-4249-a58d-7761369f3370","resolution":{"observed_at":"2026-08-07T23:32:14.489458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.469084Z","title":"Private stochastic convex optimization: optimal rates in linear time","venue":null,"work_id":"ec8aca2e-0ed8-48fd-b58e-d1f492cfc8fa","year":2020},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.059523Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:f6547f7d69f1b72aab73c0b5c268c687a2fe8489581ff210530eedce2981a791","observation_id":"919df5c7-6bbe-4cae-be7b-a340a51a81be","resolution":{"observed_at":"2026-08-07T23:32:14.474336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04912","last_updated":"2023-05-08T17:47:28Z","snapshot_observed_at":"2026-07-06T15:24:42.200476Z","submitted_at":"2023-05-08T17:47:28Z","title":"On User-Level Private Convex Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04912","snapshot_observed_at":"2026-08-07T23:32:14.063997Z","title":"On user-level private convex optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.063997Z"},"links":{"cited_paper":"/paper/2305.04912","citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:99edef91698b319b297bd82362d4f800a7716cfcee437203953dd57d69519751","observation_id":"be60ecd6-a37c-44c0-bde0-a581ccbda534","resolution":{"observed_at":"2026-08-07T23:32:14.063997Z","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":"2026-08-07T23:32:14.453126Z","title":"Private convex optimization via exponential mechanism","venue":null,"work_id":"1a4efa95-1f8f-494d-b1e2-263720fb14ed","year":1948},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.068770Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:0a9c4281434ac4f6eba829cd104d9dc764ab96e2eaebe32a19b441245b01846c","observation_id":"db451345-3bd6-4f25-9db1-5e6b1c44d02f","resolution":{"observed_at":"2026-08-07T23:32:14.458104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.03736","last_updated":"2019-02-11T05:41:28Z","snapshot_observed_at":"2026-08-01T10:38:57.624492Z","submitted_at":"2019-02-11T05:41:28Z","title":"A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.03736","snapshot_observed_at":"2026-08-07T23:32:14.073211Z","title":"A short note on concentration inequalities for random vectors with subgaussian norm","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.073211Z"},"links":{"cited_paper":"/paper/1902.03736","citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:f47585ea0cdaad18360e6792112cba4d186767fc1885780e8a3bd7a38bac4e5d","observation_id":"4e78d2b6-b12d-47d4-9753-31ad6b599935","resolution":{"observed_at":"2026-08-07T23:32:14.073211Z","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":"2026-08-07T23:32:14.437285Z","title":"Privately learning high-dimensional distributions","venue":null,"work_id":"610d24fd-d897-41e9-a152-12d57b7f55de","year":1902},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.078812Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:f868887b0f22078e5523bf4a5bb8ba4c913c64bc3d85088e8592610256e083d9","observation_id":"9427d7b0-172f-4dad-9acc-91f247a09b4a","resolution":{"observed_at":"2026-08-07T23:32:14.442688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.421876Z","title":"Differential privacy and robust statistics in high dimensions","venue":null,"work_id":"1c0165d0-c24e-4fc3-90c1-8cf1eed30acc","year":2022},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.083668Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:2c9bc01c9909270d509c47c2f884c6c3e3cbc5ade656d935acbb43aa3f083bfc","observation_id":"ee2eee6f-9f59-4f2e-b2c4-002866f2f25a","resolution":{"observed_at":"2026-08-07T23:32:14.426800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.405623Z","title":"Faster algorithms for user-level private stochastic convex optimization","venue":null,"work_id":"af0907a9-2e03-4b91-8f9b-0f915aa0d385","year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.088545Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:e9548c52f377e7c11472f6a83de3b7fda9d4266facd2126fa1628a811a85fec7","observation_id":"abc97b26-2679-430e-92b6-4a420ac82853","resolution":{"observed_at":"2026-08-07T23:32:14.410761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.390415Z","title":"Learning with user-level privacy","venue":null,"work_id":"1f425c62-3643-4c48-b523-d7ef5eff062d","year":2021},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.093557Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:42536fa9d0e26b401cb36457fdd84f54180d55e2e544e4fa95b528a1b69a917a","observation_id":"a0405b5a-ed92-42af-b3ff-c9a53ed7c532","resolution":{"observed_at":"2026-08-07T23:32:14.394917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.375147Z","title":"Analyzing leakage of personally identifiable information in language models","venue":null,"work_id":"724d6a0c-e7be-44ab-abc2-e56eeb437c99","year":2023},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.098683Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:87d5dec8769b88310c16d711c583b9ba98c9b7b069bd3ee6a12018814631f351","observation_id":"7c0361e8-dc2c-4170-88d3-6999d3432fdb","resolution":{"observed_at":"2026-08-07T23:32:14.380034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.359867Z","title":"On the linearity of large non-linear models: when and why the tangent kernel is constant","venue":null,"work_id":"1cdd27fc-6aa6-41f3-a3ab-f43209693838","year":2020},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.103376Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:e9c8e343f5253f040459ee9386a89336efc66f84f77ff5cac91473dd09d4aad5","observation_id":"4c8591e0-8e59-43fb-9ec1-3fa1bb3459ad","resolution":{"observed_at":"2026-08-07T23:32:14.364512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.344500Z","title":"Optimizing neural networks with kronecker-factored approximate curvature","venue":null,"work_id":"ff8b549a-a6e0-40ee-ac88-6e4f5d3ae3cb","year":2015},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.108165Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:cb211f34a453f176f226a086fc2ed766872ead6c8753141d03c25a533ac5d452","observation_id":"1624a7c1-3396-47d3-bca3-80e7fbf8cdc2","resolution":{"observed_at":"2026-08-07T23:32:14.349287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.325502Z","title":"Faster rates of private stochastic convex optimization","venue":null,"work_id":"7ad46eb0-e46f-4bd2-aac6-bc6c6784000a","year":2022},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.113342Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:8e657b1c29e6b2a9930d3c24a2756e90b5cc33e3551ccd13d41f077f33dff860","observation_id":"abf0c5e4-a899-4763-9279-951999307a81","resolution":{"observed_at":"2026-08-07T23:32:14.331228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.309321Z","title":"Perturbed m-estimation: A further investigation of robust statistics for differential privacy","venue":null,"work_id":"feed7c12-bf0d-4668-8688-6993813b640d","year":2012},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.118047Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:07c33cb75b841133d405b5b84e2d77de025139bbcf8b1cc139c22ceb3b81c9d3","observation_id":"e44de061-e8be-4b22-a812-d3c14fc4e710","resolution":{"observed_at":"2026-08-07T23:32:14.314512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.292542Z","title":"Convergence rates of stochastic gradient descent under infinite noise variance","venue":null,"work_id":"8081b569-be4f-494a-9f79-1f0e6d799aa1","year":2021},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.123020Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:e4f0f8544905a69f870a5c86a149e7d5f2227c964f73345af62057859f376e86","observation_id":"c60bde61-ac18-4f5e-9ffe-244e66497345","resolution":{"observed_at":"2026-08-07T23:32:14.298101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.275664Z","title":"Advances in private training for production on-device language models","venue":null,"work_id":"433f7695-1de2-422b-8436-0193314b84fa","year":2024},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.127701Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:5b2204f2aa02d093b449e258b1a704c2342ae351e735aeac172ff14f5a149817","observation_id":"fbd30e1b-4a57-4b5e-8570-b9b981c2b0f3","resolution":{"observed_at":"2026-08-07T23:32:14.280696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:32:14.258530Z","title":"Differentially private online-to-batch for smooth losses","venue":null,"work_id":"74f9eb0e-491c-40fa-b1aa-8207ec091e99","year":2022},"citing_paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:14.132646Z"},"links":{"citing_paper":"/paper/2502.08889"},"observation_digest":"sha256:0e6e7934ef0a40055c47ee79393f53704e02f423399a650b7fcdd8c502c878c1","observation_id":"7ec3190a-f22f-4fdc-9564-85c34aa4a5b7","resolution":{"observed_at":"2026-08-07T23:32:14.263912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.08889","last_updated":"2025-02-13T02:05:45Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T13:02:59.551125Z","submitted_at":"2025-02-13T02:05:45Z","title":"Linear-Time User-Level DP-SCO via Robust Statistics"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":30},"total_outbound_references":35},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2502.08889."}