{"as_of":"2026-08-10T20:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d29004d7558c464cf35a6ba80a14e18c019f9f412c6179943380f007dd540e53","coverage":[{"denominator":106,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:45:35.436548Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.23588/citation-record","integrity":"/paper/2505.23588/integrity","json":"/paper/2505.23588/citation-record.json","paper":"/paper/2505.23588"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1602.05629","last_updated":"2023-01-26T22:54:08Z","snapshot_observed_at":"2026-08-01T18:04:48.083997Z","submitted_at":"2016-02-17T23:40:56Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.05629","snapshot_observed_at":"2026-08-07T12:45:27.340670Z","title":"Federated learning of deep networks using model averaging,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.340670Z"},"links":{"cited_paper":"/paper/1602.05629","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:c6bacb1230b742f50a72be065e98748cf7a50ad2d9c80f383c3d1f6981b1106e","observation_id":"7fab7cc0-541f-4cb5-8b81-c38f6b1e11f1","resolution":{"observed_at":"2026-08-07T12:45:27.340670Z","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":"2026-08-07T12:45:27.381038Z","title":"Fedprox: Fedsplit algorithm based federated learning for statistical and system heterogeneity in medical data com- munication,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.381038Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:67bf22a29bb848bb5164245ab798d02733f4aeab602915f7dcf46671ec9b20b5","observation_id":"772ec515-b0aa-47d4-b49f-91c7518ab075","resolution":{"observed_at":"2026-08-07T12:45:27.381038Z","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":"2026-08-07T12:45:27.419610Z","title":"SCAFFOLD: stochastic controlled averaging for federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.419610Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:80bc0bce858033db3f2c5c915b8633dd41c79234583a5006cd97170d68141717","observation_id":"137447d9-85a6-4c4c-849a-448299e90378","resolution":{"observed_at":"2026-08-07T12:45:27.419610Z","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":"2026-08-07T12:45:27.483122Z","title":"Model-contrastive federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.483122Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:1d7696a08a9febc52da50045f8a69cb547c75fda02f4a13614c1c27f6b501f2f","observation_id":"c8d13219-cf0e-4ae7-b216-7594f4491c9e","resolution":{"observed_at":"2026-08-07T12:45:27.483122Z","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":"2026-08-07T12:45:27.553683Z","title":"Federated learning based on dynamic regulariza- tion,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.553683Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:1f34cbfaf9d5f4e2d55926b0137bbdca32a181dcdccd6d3a1870d05262e16f4d","observation_id":"cf66b1b2-f313-467c-b006-99771aa64858","resolution":{"observed_at":"2026-08-07T12:45:27.553683Z","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":"2026-08-07T12:45:27.628364Z","title":"Implicit gradient alignment in distributed and federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.628364Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:90d3e77225cd428647b26dde446c23350f878458918b4226949944cf4b4836d7","observation_id":"dfdb5fa9-6ba7-41c4-815f-a2ef542d3d10","resolution":{"observed_at":"2026-08-07T12:45:27.628364Z","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":"2026-08-07T12:45:27.709411Z","title":"Handling data heterogeneity in federated learning with global data distribution","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.709411Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:b62c8a13abbddcabeb286cbab2b081093f41f52df256bfc2314f85fc52dbfab2","observation_id":"69a7c94a-a817-4632-b7db-c51eb7d48bf7","resolution":{"observed_at":"2026-08-07T12:45:27.709411Z","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":"2026-08-07T12:45:27.755010Z","title":"With a little help from my friend: Server-aided federated learning with partial client participation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.755010Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:b4a6d95cd0d4bfc9b87c67353eb2f13e909a64e7611b61d6427bbb15f56917d7","observation_id":"6b8927cb-90f4-4b83-a582-3777385fe97c","resolution":{"observed_at":"2026-08-07T12:45:27.755010Z","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":"2026-08-07T12:45:27.847411Z","title":"Achieving linear speedup with partial worker participation in non-iid federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.847411Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:09970ffbb256dbb3a8a75df3b35b30b61d25be74ff7433ab687d8ac6ad7b6ca6","observation_id":"ed92cad2-92de-4f6e-872e-6fb942393d0b","resolution":{"observed_at":"2026-08-07T12:45:27.847411Z","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":"2026-08-07T12:45:27.923100Z","title":"Fast federated learning in the presence of arbitrary device unavailability,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:27.923100Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:50aceeabd2baebfa749d9ae47616fc77ebea93e0de3d8f5a50e04a06c4abd2d8","observation_id":"b736af08-a385-4deb-b515-cabe3e975273","resolution":{"observed_at":"2026-08-07T12:45:27.923100Z","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":"2026-08-07T12:45:28.074946Z","title":"Anchor sampling for federated learning with partial client participation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.074946Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:b842f61c0e6b862ddb03146bcd08bd39070c61470263403068731c6674bcd1ec","observation_id":"93b9537c-66e3-415f-9a9e-fc4f0af449bc","resolution":{"observed_at":"2026-08-07T12:45:28.074946Z","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":"2026-08-07T12:45:28.160715Z","title":"Fedvarp: Tackling the variance due to partial client participation in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.160715Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:bc6ec5ad6e405668f2f3919c43c0dfe3920bffa6bc8df49bbf0189f75d059393","observation_id":"4f054c2f-c954-4217-b616-72c75ab68794","resolution":{"observed_at":"2026-08-07T12:45:28.160715Z","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":"2026-08-07T12:45:28.273453Z","title":"Federated learning with differential privacy: Algorithms and performance analysis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.273453Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:6e4b6fba4682334b1777df0dbd280495da2d2b5b95df184d54c48b441d56981c","observation_id":"6ecbdfa4-b7c2-4fee-a572-3e0bf742cc51","resolution":{"observed_at":"2026-08-07T12:45:28.273453Z","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":"2026-08-07T12:45:28.421572Z","title":"Ldp-fed: Federated learning with local differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.421572Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:2054af24dd4320ed389adefece0e032e9c2cd89c9b3785d0e1e515b2a43aa36a","observation_id":"e3a7a57e-adc9-46ed-8d1c-1543f53ad56d","resolution":{"observed_at":"2026-08-07T12:45:28.421572Z","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":"2026-08-07T12:45:28.567235Z","title":"Federated learning and differential privacy for medical image analysis,","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.567235Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:b9311499f0b9a31fdfee2c8c0c264996bcd6054b2c8ed71877e5dfb0afc50cdd","observation_id":"3b5cd932-897a-4a6c-9695-4f1510a05874","resolution":{"observed_at":"2026-08-07T12:45:28.567235Z","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":"2026-08-07T12:45:28.657071Z","title":"Federated learning with bayesian differ- ential privacy,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.657071Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:98b645fd9f486c09d3febb7c0f6805fb1360f2009f730f476f09b5b531e48c5b","observation_id":"67b4a4c0-f21e-451f-a57c-dd742ecea5f8","resolution":{"observed_at":"2026-08-07T12:45:28.657071Z","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":"2026-08-07T12:45:28.789316Z","title":"Differential privacy meets federated learning under communication constraints,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.789316Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:41a99f6d9000c3c58531951240a2428081c94aeb6a39b5eab03dcd11784a148c","observation_id":"dcb83a83-bf50-487a-88e6-2b8440bbc484","resolution":{"observed_at":"2026-08-07T12:45:28.789316Z","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":"2026-08-07T12:45:28.894870Z","title":"Attack of the tails: Yes, you really can backdoor federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.894870Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:9d2bacb1f703df0ea4ee9f8aad62f0658144928f8d4f0f73e7ee609c3254c799","observation_id":"6ea51a52-9ef5-4cbe-b224-13cffdf60501","resolution":{"observed_at":"2026-08-07T12:45:28.894870Z","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":"2026-08-07T12:45:28.939222Z","title":"Exploring adversarial attacks in federated learning for medical imaging,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:28.939222Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:34c0bdae57197cf4769cb5a4564173f964002cb5bafe172a01a50c7260731562","observation_id":"24276563-05f6-4760-8e1f-b4c21f9bb295","resolution":{"observed_at":"2026-08-07T12:45:28.939222Z","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":"2026-08-07T12:45:29.001533Z","title":"Analyzing user-level privacy attack against federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.001533Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:1635145b1cdb5f5fede1e49cc81b0bf2006378ed4e26341bf2be43686612282a","observation_id":"8012f483-5394-4359-bdf3-90601c4e9738","resolution":{"observed_at":"2026-08-07T12:45:29.001533Z","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":"2026-08-07T12:45:29.146401Z","title":"Toward federated learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.146401Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:22684bf67cda0d7e7cd9f728983965052e08097e2622c4ab536a4504581300b3","observation_id":"d656876c-380e-4a75-9b17-1f8a231dcbf6","resolution":{"observed_at":"2026-08-07T12:45:29.146401Z","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":"2026-08-07T12:45:29.219104Z","title":"Zero knowledge clustering based adversarial mitigation in heterogeneous federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.219104Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:267d84f39e8d25e863b0cc9f702abd45a12671d2567696397d1d083e02319422","observation_id":"a3d9ccb9-bb0e-4654-8160-f3bfa11ab05b","resolution":{"observed_at":"2026-08-07T12:45:29.219104Z","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":"2026-08-07T12:45:29.275531Z","title":"Giant: Globally improved approximate newton method for distributed optimization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.275531Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:9465ae5cf5b47c1a4970456443336ab09bde99c781779e044438549cb9264ce5","observation_id":"73b4e403-80a3-43f0-94d4-85c4e99e0a59","resolution":{"observed_at":"2026-08-07T12:45:29.275531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.07320","last_updated":"2021-05-16T00:15:08Z","snapshot_observed_at":"2026-08-10T10:38:37.823611Z","submitted_at":"2021-05-16T00:15:08Z","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.07320","snapshot_observed_at":"2026-08-07T12:45:29.323376Z","title":"Localnewton: Reducing communication bottleneck for distributed learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.323376Z"},"links":{"cited_paper":"/paper/2105.07320","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:437e8949efae5ce3a011721d43b20f9e234840bf27bc5cfc754ab6af59440df3","observation_id":"d949a60b-85be-4d9a-825e-2fc7d307bdbd","resolution":{"observed_at":"2026-08-07T12:45:29.323376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.09576","last_updated":"2022-08-23T03:26:53Z","snapshot_observed_at":"2026-07-06T13:22:35.494601Z","submitted_at":"2022-06-20T05:25:20Z","title":"FedSSO: A Federated Server-Side Second-Order Optimization Algorithm","version":2},"cited_work":{"arxiv_id":"2206.09576","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.09576","snapshot_observed_at":"2026-08-07T12:45:36.517168Z","title":"FedSSO: A Federated Server-Side Second-Order Optimization Algorithm","venue":"cs.LG","work_id":"ea76ed31-f0e1-43b6-8bf2-028a1ecb67a6","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.361992Z"},"links":{"cited_paper":"/paper/2206.09576","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d9376b061a8d1811a87e8b107a28874932d88dba278747635165f83225368e7c","observation_id":"c666d768-aed3-4e7b-aeba-3f756c0e3836","resolution":{"observed_at":"2026-08-07T12:45:36.626072Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:29.476074Z","title":"Communication-efficient dis- tributed optimization using an approximate newton-type method,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.476074Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:770d9485c153331a5292a40ba6696759ef2222b79a028ddeed210b657e8ea6f2","observation_id":"9c630a9a-1f63-4c3d-8bec-756006c38ea3","resolution":{"observed_at":"2026-08-07T12:45:29.476074Z","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":"2026-08-07T12:45:29.628363Z","title":"Fednl: Making newton-type methods applicable to federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.628363Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:de3a2cd85df7b58a89a785f7f627b34219fac55aee0b77c1a332c42373e1e370","observation_id":"2028b3aa-9d35-411b-8d4e-aa88626244d2","resolution":{"observed_at":"2026-08-07T12:45:29.628363Z","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":"2026-08-07T12:45:29.776614Z","title":"Nys-fl: A communication efficient federated learning with nystr ¨om approximated global newton direc- tion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.776614Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:401f582084fa64ec8f86ab2c7af5cfcde01b1e707aee1bfb7e2e0f61523d7802","observation_id":"1c5c307e-60fe-4a97-870a-357778292e00","resolution":{"observed_at":"2026-08-07T12:45:29.776614Z","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":"2026-08-07T12:45:29.937445Z","title":"Fonn: Federated optimization with nys-newton,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:29.937445Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:22b5d657e26ac0ff6ffbb6a28c3e1fe804ed4eb5e91e0c2f8a72339fc3cf1bac","observation_id":"8fa17e95-0245-4741-871c-b0cea026cc0d","resolution":{"observed_at":"2026-08-07T12:45:29.937445Z","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":"2026-08-07T12:45:46.240078Z","title":"Over-the-air federated learning via second-order optimization,","venue":null,"work_id":"ec6985f3-fe52-4c7b-a4bb-6f2b24c4cc46","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.100830Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:757349f131a565c4acc45987d67a89001c8abf81030b4b028c31bfaa34c70367","observation_id":"b97e7c09-9f01-4a53-8a5d-52f76cee3e31","resolution":{"observed_at":"2026-08-07T12:45:46.299245Z","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":"2026-08-07T12:45:46.121690Z","title":"Foplahd: Federated optimization using locally approximated hessian diagonal,","venue":null,"work_id":"4cd93521-becd-46a8-a881-743b3d4d4941","year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.160723Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:45b149c21053406851db9435b635acdb063ef23508f084cb8e33daa98a9c48ba","observation_id":"e283f66d-0c59-434d-8b8b-20c5e1ae087b","resolution":{"observed_at":"2026-08-07T12:45:46.176567Z","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":"2026-08-07T12:45:45.935204Z","title":"Done: distributed approximate newton-type method for federated edge learning,","venue":null,"work_id":"3d1ed6e8-b8fc-4c47-bfc0-cca3a17f3991","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.217043Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:385aab96556c5c6442037bfcdd82f7111dd136663d8d8ef1119b4d1a0ded2878","observation_id":"d1984c70-7798-407b-b588-3f080e0622c6","resolution":{"observed_at":"2026-08-07T12:45:46.024711Z","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":"2026-08-07T12:45:45.744064Z","title":"Freng: Federated optimization by using regularized natural gradient descent,","venue":null,"work_id":"4081b41a-07ae-445f-9295-98b063e79d9f","year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.258894Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:6960b9c3abf858078815af9d0208b440eff9de9996ffbf1d5cc4ed10ff4c6a93","observation_id":"4a769606-e0a8-47eb-a0cc-773e5825fb85","resolution":{"observed_at":"2026-08-07T12:45:45.856939Z","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":"2026-08-07T12:45:45.486805Z","title":"Federated learning review: Fundamentals, enabling technologies, and future applications,","venue":null,"work_id":"50f1d5ec-ad9b-45ce-95cd-60b2c799f1de","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.297189Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d14d2184ec5a1fa41c898c7996901427277692e8c7dc5c45838c70632b5792b2","observation_id":"fd259a70-5743-484e-abc0-106679c6f6de","resolution":{"observed_at":"2026-08-07T12:45:45.622688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:30.336185Z","title":"The impact of adversarial attacks on federated learning: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.336185Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:7945c30babdf04a5e2a3d0e7d24e817544f7cbcd72e331dade5b584f23b87ad9","observation_id":"2f64f7e0-20da-4e65-866e-d3727efa2b9f","resolution":{"observed_at":"2026-08-07T12:45:30.336185Z","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":"2026-08-07T12:45:45.269204Z","title":"A systematic survey for differential privacy techniques in federated learning,","venue":null,"work_id":"7df9f775-924f-402f-9309-7060c25ddbb5","year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.396062Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:05dd9d9f3f87521c23aa6f4e6d5e4bb83ddc69c8429b6590d5a97d88574e05fa","observation_id":"d4709ccb-69ee-401a-b4a9-179c2ae54448","resolution":{"observed_at":"2026-08-07T12:45:45.379516Z","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":"2026-08-07T12:45:45.019822Z","title":"Differential privacy federated learning: A comprehensive review","venue":null,"work_id":"c01f6176-80a8-43fe-b3ec-49b230908eaa","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.486462Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:3dc5921ffdddf118c7e10027914befcf6845f877733c8cb538f313f36babece6","observation_id":"e1590fef-e828-4da9-94b2-af3b2994af8a","resolution":{"observed_at":"2026-08-07T12:45:45.113888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:30.544139Z","title":"Differentially private federated learning: A systematic review,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.544139Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:077d9b899bda2093df8e5cb2c622a0e60b0e033cbe5c9817652b246319afc62c","observation_id":"a2adc8cc-d703-485a-b008-ecf0817d0479","resolution":{"observed_at":"2026-08-07T12:45:30.544139Z","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":"2026-08-07T12:45:44.805418Z","title":"A survey of security threats in federated learning,","venue":null,"work_id":"ff7ae421-731a-4ff4-9a45-f5bb80327415","year":2025},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.610354Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:6e68b1244f509faa1a65d8bdfd5d8d9431af3db85402f0c83b6ffd1e72e0431b","observation_id":"e94125e3-ab15-4e53-8a2b-47b84b91c681","resolution":{"observed_at":"2026-08-07T12:45:44.920369Z","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":"2026-08-07T12:45:44.557551Z","title":"Challenges, applications and design aspects of federated learning: A survey","venue":null,"work_id":"0f078445-8557-42a1-a6ff-60f2da72fdc0","year":null},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.727848Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:e5af348d36a8b0a09ccc12f28b49b191e73fb1d014ed0b3deacf84302487d3c6","observation_id":"f2b31969-e466-4b38-b7ef-43dbdae879d6","resolution":{"observed_at":"2026-08-07T12:45:44.678999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:30.826582Z","title":"Federated learning on non-iid data: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.826582Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:129059d532f0d71efb1697700d67b99de4b8ecbbb3a4da41761422b5b98927ef","observation_id":"0af9acf5-60c0-4d2a-907c-f7ebad77893c","resolution":{"observed_at":"2026-08-07T12:45:30.826582Z","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":"2026-08-07T12:45:30.900776Z","title":"Federated learning with non-iid data: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.900776Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:b1db512ccf095e80772f89fd7b940114df0ea8daf31ad6d186b9bed0a8b1b899","observation_id":"f4d71504-943f-4add-bf07-00213b667d67","resolution":{"observed_at":"2026-08-07T12:45:30.900776Z","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":"2026-08-07T12:45:44.321893Z","title":"A survey of federated learning on non-iid data,","venue":null,"work_id":"d171996f-6c07-4f71-ac7a-7f3938a7744b","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:30.983094Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d2dae59babe9f448145ff08f665cd8ed8531bf09b50347fdcb1dbb41e714f1f8","observation_id":"37d7311a-cb42-4943-b1b1-11bce29f7f36","resolution":{"observed_at":"2026-08-07T12:45:44.438290Z","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":"2026-08-07T12:45:44.071826Z","title":"Federated learning for generalization, robustness, fairness: A survey and benchmark,","venue":null,"work_id":"2ec53576-60cc-425b-8092-f05f132bce78","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.127533Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:8f204307f4e8115bcbbc03a345d029af7c5ac71be7752fabd98840fcd61256ee","observation_id":"4485da2b-fa45-426c-aff9-4113a80c4045","resolution":{"observed_at":"2026-08-07T12:45:44.170303Z","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":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-07T12:45:31.209096Z","title":"Federated learning with non-iid data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.209096Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:29e5784ab386eca3049cb5d337595bc1d3d44b3ba6cd2002bea32e16ee834401","observation_id":"f390a9f7-a62a-42eb-90bb-6bd65a25c935","resolution":{"observed_at":"2026-08-07T12:45:31.209096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.02388","last_updated":"2021-09-06T12:04:08Z","snapshot_observed_at":"2026-07-06T11:44:39.782753Z","submitted_at":"2021-09-06T12:04:08Z","title":"On Second-order Optimization Methods for Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.02388","snapshot_observed_at":"2026-08-07T12:45:31.278385Z","title":"On second- order optimization methods for federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.278385Z"},"links":{"cited_paper":"/paper/2109.02388","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:c386757977c574295bef317ab41b5d64ef3b5bc030f9e72d3f78f522d912b913","observation_id":"1cd69a4c-9d9f-4ab7-a2a9-5ee97420f57b","resolution":{"observed_at":"2026-08-07T12:45:31.278385Z","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":"2026-08-07T12:45:43.851405Z","title":"Review of second-order optimization techniques in artificial neural networks backpropagation,","venue":null,"work_id":"2fe62935-6355-4d68-b844-abc739658235","year":2019},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.361843Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:f3e342abcbdf14026feaa2da86ec9f7ae29265ee238adfec57113bea27373156","observation_id":"a3c77e43-a95e-4227-8673-48cdcb2086cf","resolution":{"observed_at":"2026-08-07T12:45:43.961640Z","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":"2211.15596","last_updated":"2023-09-27T08:14:53Z","snapshot_observed_at":"2026-08-09T15:35:15.967381Z","submitted_at":"2022-11-28T17:50:14Z","title":"A survey of deep learning optimizers -- first and second order methods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.15596","snapshot_observed_at":"2026-08-07T12:45:31.457655Z","title":"A survey of deep learning optimizers–first and second order methods,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.457655Z"},"links":{"cited_paper":"/paper/2211.15596","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:171d09e46c6dd1642b02af79fefc4069cb695d45668c8c3b94fcff00089ef92b","observation_id":"3ea2d6ac-073c-4a98-a338-fb4af51b388d","resolution":{"observed_at":"2026-08-07T12:45:31.457655Z","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":"2026-08-07T12:45:43.569505Z","title":"A state-of-the-art survey on solving non-iid data in federated learning,","venue":null,"work_id":"4624ac16-5c93-4b0a-a5b1-eb8f45928b00","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.545468Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d533e4c318b374ac8da9051a3a9a271f942d458ba10c58da8bcadc428169350a","observation_id":"d2e9496a-096e-459b-a9f0-8dec0165a91a","resolution":{"observed_at":"2026-08-07T12:45:43.682224Z","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":"2026-08-07T12:45:43.308264Z","title":"Stochastic gradient descent,","venue":null,"work_id":"ba9b4ae6-d1a0-43c6-acba-4732b1d188a7","year":2017},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.620157Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:3f5fcca1f3d99634746cfa1eb3ba95be374d3554266e1cb3481f0cde6d4c9eb1","observation_id":"12ca4a03-1487-483f-b729-29983af033ab","resolution":{"observed_at":"2026-08-07T12:45:43.428451Z","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":"2110.08577","last_updated":"2022-01-29T21:25:27Z","snapshot_observed_at":"2026-08-09T08:11:04.053909Z","submitted_at":"2021-10-16T14:04:51Z","title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08577","snapshot_observed_at":"2026-08-07T12:45:31.716191Z","title":"Nys-newton: Nystr \\","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.716191Z"},"links":{"cited_paper":"/paper/2110.08577","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:8650a57c9ca1e5c0095d702fcadfad57c8266056cc0f11e570d2e933695373d4","observation_id":"7a627409-e68a-4db0-825b-ab0e5381f186","resolution":{"observed_at":"2026-08-07T12:45:31.716191Z","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":"2026-08-07T12:45:43.089496Z","title":"Second-order stochastic optimization for machine learning in linear time,","venue":null,"work_id":"03f70621-f071-43f2-83cd-9a5515cc7aba","year":2017},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.791426Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:be9337ceab8b3c50d98396f0403dad56c5dc2f39132be8425d7339771cf7a030","observation_id":"734069cc-652b-49d4-8c61-864ed35a7880","resolution":{"observed_at":"2026-08-07T12:45:43.197752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:31.895514Z","title":"Distributed estimation of the inverse hessian by determinantal averaging,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.895514Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:89c29fdb7714850b416c3e9fc3066e54fd28f23ba522e9ac55a6c2156b045839","observation_id":"2371cf0d-9d81-4e81-a4c6-85836820e127","resolution":{"observed_at":"2026-08-07T12:45:31.895514Z","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":"2026-08-07T12:45:42.847458Z","title":"Deep learning via hessian-free optimization","venue":null,"work_id":"8c2abf73-cc4f-4e82-8eb8-7af6db952f80","year":2010},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:31.984600Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:35346400d353f5d40340eacd5f8f85f669b8801871ee3600c5ed12b204189b03","observation_id":"4cae4526-c918-4e24-bb50-6b15feb0bf67","resolution":{"observed_at":"2026-08-07T12:45:42.973091Z","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":"2026-08-07T12:45:42.586786Z","title":"Hessian-free optimization for learning deep multidimensional recurrent neural networks,","venue":null,"work_id":"c538d159-74b9-4602-90f0-7e1706f01d90","year":2015},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.149953Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:4041dd44853fdb94db5e2693c7db13497044e693f50631dd2f8e05f963d149f5","observation_id":"aa9fd46d-6c13-46ac-a938-e8289561c5c6","resolution":{"observed_at":"2026-08-07T12:45:42.699217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:32.250343Z","title":"Communication-efficient dis- tributed optimization using an approximate newton-type method,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.250343Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:3c650471241fbbf7a518d77f81c8ef4c2a2afce5d333ce6da2ae36d68c5f4cac","observation_id":"825bbb58-c483-4b3b-be27-04103fdb5e88","resolution":{"observed_at":"2026-08-07T12:45:32.250343Z","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":"2026-08-07T12:45:42.269822Z","title":"Disco: Distributed optimization for self- concordant empirical loss,","venue":null,"work_id":"10ab8ce7-40c8-4ce3-bc2a-8b60196224f1","year":2015},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.329800Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:4fa05d5571116b46d8d01cf3b53210c7af9d353a5fc1e919126c1ed4d0c40da9","observation_id":"ef089ef0-00df-4854-9a3e-a092bd2d8f9c","resolution":{"observed_at":"2026-08-07T12:45:42.429305Z","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":"1608.06879","last_updated":"2016-08-24T16:04:12Z","snapshot_observed_at":"2026-07-06T05:08:01.620233Z","submitted_at":"2016-08-24T16:04:12Z","title":"AIDE: Fast and Communication Efficient Distributed Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06879","snapshot_observed_at":"2026-08-07T12:45:32.433055Z","title":"Aide: Fast and communication efficient distributed optimization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.433055Z"},"links":{"cited_paper":"/paper/1608.06879","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:46287a0a577bb17aabd0f3e8bd6362989e81e6e5b883ce0ffb32d6c82dda975f","observation_id":"7abcc974-bf83-4b32-8e63-fdae170055b2","resolution":{"observed_at":"2026-08-07T12:45:32.433055Z","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":"2026-08-07T12:45:41.848181Z","title":"Stochastic dual coordinate ascent methods for regularized loss,","venue":null,"work_id":"c0ee157c-45e3-4a49-bae3-c740cd4e43b8","year":2013},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.650499Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:97a92bfb8eff6d65ab30cc9c4aa0286beb3a5338cc414a3a5c78cf3c1af5c91e","observation_id":"9f35c250-ba4b-4a6b-9050-5bb131f8ac38","resolution":{"observed_at":"2026-08-07T12:45:41.965343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:32.762039Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.762039Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:137839fdd673aca31be83a6ed8a7acc06aa00306c9598ded5caf21830fa11b2b","observation_id":"735e093d-538c-4987-9b40-93235dcbae0c","resolution":{"observed_at":"2026-08-07T12:45:32.762039Z","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":"2026-08-07T12:45:41.629538Z","title":"Parallelized stochastic gradient descent,","venue":null,"work_id":"3f7fb739-1787-4264-88b5-90642882a2a0","year":2010},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.826722Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:8d2dbee91d1fbac0ce22db9accbd1588ec08ba2cbd3a9b2a5a2127f898ab2168","observation_id":"fa3e3d38-7747-4658-962a-0536b8a3502d","resolution":{"observed_at":"2026-08-07T12:45:41.721796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:32.876244Z","title":"Distributed optimization and statistical learning via the alternating direction method of multipliers,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.876244Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:98d1d0f462b56ab375087496f79255fbb9141cf54744e0915f905eea1c413b1d","observation_id":"51b87bb1-5678-48b7-ad99-e87aa655dcb7","resolution":{"observed_at":"2026-08-07T12:45:32.876244Z","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":"2026-08-07T12:45:41.384008Z","title":"Quartz: Randomized dual coordi- nate ascent with arbitrary sampling,","venue":null,"work_id":"6f9299ce-04f6-4336-be55-0549b7e20182","year":2015},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:32.959039Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:f2163c069c69d4464f64fb3199da102b5a70935b675fd945d01e109df3db07d8","observation_id":"27ef09fc-5b00-4fa2-96a1-f8c7abb7ff78","resolution":{"observed_at":"2026-08-07T12:45:41.509016Z","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":"2026-08-07T12:45:41.128684Z","title":"A universal catalyst for first-order optimization,","venue":null,"work_id":"717cadd1-3b68-45da-a8b2-2077030e40ed","year":2015},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.000486Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:a72ff9898cfbb1204969189223e36ad50c5328f6d7076ff8ea335ac8e661680a","observation_id":"129a8fe0-4d54-46af-af43-e3e302f1faff","resolution":{"observed_at":"2026-08-07T12:45:41.248420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:33.055909Z","title":"Libsvm: a library for support vector machines,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.055909Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:c96d2ad1991cec2b1b2d0fbfc7b1816b5dd399b5078a204222dff81c34fb94cd","observation_id":"469006d8-52e8-45b1-815d-59c48d0396a4","resolution":{"observed_at":"2026-08-07T12:45:33.055909Z","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":"2026-08-07T12:45:40.933718Z","title":"Distributed optimization with arbitrary local solvers: Co- coa+ and beyond,","venue":null,"work_id":"42a5fec7-87c7-4a09-a7de-b038aba5f8c4","year":2016},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.114279Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:7f695d2ce7fddd22e7f3b2db889be2a8c09bbfebff8a8a722f83f26eec7ab9de","observation_id":"bb82be58-c482-4694-9d1d-ab4852684c8c","resolution":{"observed_at":"2026-08-07T12:45:41.013864Z","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":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-06T00:22:10.318064Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-07T12:45:33.167489Z","title":"Leaf: A benchmark for federated settings,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.167489Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:41e65cc5e8709b7fc7d23372c831d984402ef7a025fff867639958d9588e38bb","observation_id":"1ef97720-65ed-4097-b68a-4acfc473b56f","resolution":{"observed_at":"2026-08-07T12:45:33.167489Z","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":"2026-08-07T12:45:33.203083Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.203083Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:618fb0c637f30a0dae36b9495bb1ac8f27e01645b3451973d1d6da573429401e","observation_id":"8d18858a-0e3b-4fe2-9faa-772481bc15d5","resolution":{"observed_at":"2026-08-07T12:45:33.203083Z","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":"2026-08-07T12:45:33.301663Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.301663Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:eef6bb38836130620f999fb8bb01c8f80ce3c33682bc929d85b2b588473c7c3c","observation_id":"69ebaad9-1f65-4960-966d-caca1eb1f777","resolution":{"observed_at":"2026-08-07T12:45:33.301663Z","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":"2026-08-07T12:45:33.369256Z","title":"Nesterov, Introductory lectures on convex optimization: A basic course","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.369256Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:0a1e90136854f2cb159813575f54df0ac6e28755d22769680c843712cea7bfde","observation_id":"c51b3be7-f461-4dae-8059-dc6af0b73b1b","resolution":{"observed_at":"2026-08-07T12:45:33.369256Z","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":"2026-08-07T12:45:33.439585Z","title":"On the limited memory bfgs method for large scale optimization,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.439585Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:4695b1973e65c5febc1a5e67d978704672b988ff37d2854d599951cc0a356a01","observation_id":"b29a5435-78b2-4597-bf01-6e9ef20a295d","resolution":{"observed_at":"2026-08-07T12:45:33.439585Z","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":"2026-08-07T12:45:33.517810Z","title":"Conjugate gradient method,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.517810Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:13826dc52d34629291742c40e363198f305cfb3dbb4df8ba39009e4542b07d56","observation_id":"417aede5-1a2e-48e4-a71a-43e3a7d1070d","resolution":{"observed_at":"2026-08-07T12:45:33.517810Z","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":"2026-08-07T12:45:40.672107Z","title":"Classical iterative methods for linear systems,","venue":null,"work_id":"da07525c-17dd-4385-b042-ce2f5cbc6ffe","year":2009},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.551343Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:6b58e62a73e058b04651254dfabce98fe820b15c60c44a00e7538950f70ce227","observation_id":"262efced-12e0-49fe-a01b-343f63f26c3f","resolution":{"observed_at":"2026-08-07T12:45:40.771266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:33.610836Z","title":"Emnist: Extending mnist to handwritten letters,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.610836Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:82cf36e815b496d8f1f93570dca1862da6f02c467a688a4f812f0edcac3ec90d","observation_id":"36a06d16-c706-4fa8-8915-7a84552b90df","resolution":{"observed_at":"2026-08-07T12:45:33.610836Z","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":"2026-08-07T12:45:40.427389Z","title":"A public domain dataset for human activity recognition using smart- phones","venue":null,"work_id":"d21bb876-6650-457d-895a-f3ccbb425af3","year":2013},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.674742Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:8ce96422b98287c2204b190932745ae7acbe3614cb2288f87f0197dab87864f3","observation_id":"b794997c-d412-4ad7-9c9c-f4571591beda","resolution":{"observed_at":"2026-08-07T12:45:40.543834Z","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":"2026-08-07T12:45:40.216556Z","title":"Basis matters: Better communication-efficient second order methods for federated learning,","venue":null,"work_id":"80105819-672c-450c-80cf-9d158c7c6d6e","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.712300Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d2bd1e72e73215770207fffee7ff2994336f3a0b8d7da37b5360aabff7a77a4c","observation_id":"84a12788-1362-4ae5-938a-bf3ee4eb84e8","resolution":{"observed_at":"2026-08-07T12:45:40.299164Z","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":"2026-08-07T12:45:40.012023Z","title":"Fednew: A communication-efficient and privacy-preserving newton-type method for federated learning,","venue":null,"work_id":"c416f74b-e5cb-4638-a331-a2f5fe069029","year":2022},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.773512Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:caee1eb4927ee5d54a9a70199ff70bb6758f8866af060ccfc529d159ef27714f","observation_id":"1c9ac396-c4d2-4a34-bd69-cae1c2c74083","resolution":{"observed_at":"2026-08-07T12:45:40.091920Z","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":"2026-08-07T12:45:39.785403Z","title":"Shed: A newton- type algorithm for federated learning based on incremental hessian eigenvector sharing,","venue":null,"work_id":"55f41899-2093-435e-bc03-c2ceae09b41b","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.846972Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d654ca7d953e27bed5b545fbab217fe50bfa9272f1ca3000ebccacfdc7f10cd4","observation_id":"0c00a818-de6a-4cc7-bcec-dfaf70c6178e","resolution":{"observed_at":"2026-08-07T12:45:39.839316Z","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":"2026-08-07T12:45:39.576282Z","title":"Fedns: A fast sketching newton- type algorithm for federated learning,","venue":null,"work_id":"e3845630-a558-4c29-8a50-35e744ddeddd","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.921804Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:4d7d4425c6121b52a7189f0e73d28db5ab9f53b67b9239d5373010da25780793","observation_id":"41f71537-ffc3-4575-9e10-03efdfebccab","resolution":{"observed_at":"2026-08-07T12:45:39.657153Z","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":"2026-08-07T12:45:39.444848Z","title":"Distributed second order meth- ods with fast rates and compressed communication,","venue":null,"work_id":"f1d4383b-a68d-4414-9c16-d11ae2352240","year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:33.990127Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:ea6eacd4c9184c00efb46cce8153b2d7e8eebdb449a1655aec5786e1fc5d9207","observation_id":"43e01e03-a6bc-4886-b34d-5d6f0740fb0e","resolution":{"observed_at":"2026-08-07T12:45:39.512491Z","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":"2026-08-07T12:45:39.291311Z","title":"Distributed learning with compressed gradient differences,","venue":null,"work_id":"d26087e0-2f37-4ed4-8c4c-dfccbfef8020","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.032026Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:3e139f91112fb7091a88fc12a8c07a8c14fac35d97eaa2df1ebf6544b21caa5b","observation_id":"b89b3554-9151-4b02-a2de-fe46311b352e","resolution":{"observed_at":"2026-08-07T12:45:39.370888Z","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":"2002.11364","last_updated":"2020-06-25T21:36:17Z","snapshot_observed_at":"2026-08-04T18:47:26.712070Z","submitted_at":"2020-02-26T09:03:23Z","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.11364","snapshot_observed_at":"2026-08-07T12:45:34.096395Z","title":"Acceleration for compressed gradient descent in distributed and federated optimization,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.096395Z"},"links":{"cited_paper":"/paper/2002.11364","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:ab8b3aa78f9ba1ea7d5e470a00afd46df680f05f6e280a96731ec30b19575a71","observation_id":"89058f18-f7fb-4377-beb1-e3b909821eaa","resolution":{"observed_at":"2026-08-07T12:45:34.096395Z","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":"2026-08-07T12:45:39.110379Z","title":"Local sgd: Unified theory and new efficient methods,","venue":null,"work_id":"cbd37bc8-1972-4636-a397-a8901894e11a","year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.167230Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:62e4c09a5895d0f150ae844dfd54ddebc05509433bbf89cb4ca0fb5cbfa3c0c8","observation_id":"4cf7675d-c7e0-43a9-9af2-346e20ec8e5e","resolution":{"observed_at":"2026-08-07T12:45:39.175730Z","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":"2026-08-07T12:45:38.930097Z","title":"Dingo: Distributed newton-type method for gradient-norm optimization,","venue":null,"work_id":"7c792a0e-e90a-47bf-ae0e-f13c55309238","year":2019},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.195292Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:18b4408462f3550057eab81e82f897db26301ebad0570f1fcabe66f8f90eabb3","observation_id":"70c52783-d691-40f6-96c0-5409e7d639d6","resolution":{"observed_at":"2026-08-07T12:45:38.997858Z","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":"2026-08-07T12:45:38.663481Z","title":"Stephen j,","venue":null,"work_id":"9cd42293-3580-41cf-9695-9b77bcab22ec","year":2006},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.255524Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:d5924ab4187bc0335592f591f867dfc684dce4f80e5c9d9673f9d9e19e736c40","observation_id":"1b436ac3-24e3-480b-b0ee-190a6f531777","resolution":{"observed_at":"2026-08-07T12:45:38.834809Z","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":"2501.10877","last_updated":"2025-01-18T20:59:07Z","snapshot_observed_at":"2026-08-10T18:50:18.867929Z","submitted_at":"2025-01-18T20:59:07Z","title":"Distributed Quasi-Newton Method for Fair and Fast Federated Learning","version":1},"cited_work":{"arxiv_id":"2501.10877","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.10877","snapshot_observed_at":"2026-08-07T12:45:36.010974Z","title":"Distributed Quasi-Newton Method for Fair and Fast Federated Learning","venue":"cs.LG","work_id":"19b73355-f0d4-462d-9452-87452c97a6cc","year":2025},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.307124Z"},"links":{"cited_paper":"/paper/2501.10877","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:cf9e7763ba863ff2b4018eebc251bb863d5208b7caa58b4e5cf83c622dea1321","observation_id":"f853cdc8-1234-4659-9073-1121517d2cab","resolution":{"observed_at":"2026-08-07T12:45:36.133511Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:34.354154Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.354154Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:41b6af019fe071c728ad54fc1feaf6507362b11e702a4f536318c09b8fbaac3b","observation_id":"3f2c0269-b24a-4772-a164-dc418fc9c702","resolution":{"observed_at":"2026-08-07T12:45:34.354154Z","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":"2026-08-07T12:45:38.391959Z","title":"Federated accelerated stochastic gradient descent,","venue":null,"work_id":"480c3f96-7f9f-4312-b385-471a46931e0b","year":2020},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.444648Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:c999c5f784321b571fcc5fba96ca072f5b3f2ff5ca7deb626621dc7fd59ac72f","observation_id":"2e9d8ae5-9d2f-4329-9210-9e1bde5e309c","resolution":{"observed_at":"2026-08-07T12:45:38.461724Z","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":"2003.00295","last_updated":"2021-09-08T23:37:17Z","snapshot_observed_at":"2026-07-06T09:01:12.515300Z","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":"2026-08-07T12:45:34.551914Z","title":"Adaptive federated optimization,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.551914Z"},"links":{"cited_paper":"/paper/2003.00295","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:54d614c7c337b89d9397be9f1c2a31ecc49d0e8867fb77cb32ce4c2233677975","observation_id":"837ad19f-3b89-4d20-bbd9-6e8fa8bd9669","resolution":{"observed_at":"2026-08-07T12:45:34.551914Z","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":"2026-08-07T12:45:42.106484Z","title":"Feddane: A federated newton-type method,","venue":null,"work_id":"f57d2061-9dcb-4435-8687-1808e16dc4c3","year":2019},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.605321Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:cc0bbf62659f2d643ae6a366d92bb534c1d536f4183690aa37319c57b9d7eded","observation_id":"637e7a52-e486-4ebc-b75d-df62b2de42ab","resolution":{"observed_at":"2026-08-07T12:45:42.178754Z","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":"2026-08-07T12:45:38.239549Z","title":"Algorithms for multicriterion optimization,","venue":null,"work_id":"4be0866d-9886-4497-94f9-2aa891171c9c","year":2003},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.683605Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:0c1f60de96801557fe8efa14947a3389fcd13a5557f4ab46d076081f4a843fe8","observation_id":"aa8c6a64-54d2-4fc8-9661-059ea1fb13a3","resolution":{"observed_at":"2026-08-07T12:45:38.301472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:45:34.739280Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.739280Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:829d63980e9e7cf76f133336d87552ca67be37e223663d41a29a409634628167","observation_id":"e5336fbd-84b5-4db8-9c3e-50d0aa64f3de","resolution":{"observed_at":"2026-08-07T12:45:34.739280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.03505","last_updated":"2018-10-02T21:20:09Z","snapshot_observed_at":"2026-08-07T01:38:08.346703Z","submitted_at":"2018-10-02T21:20:09Z","title":"CINIC-10 is not ImageNet or CIFAR-10","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.03505","snapshot_observed_at":"2026-08-07T12:45:34.806195Z","title":"Cinic-10 is not imagenet or cifar-10,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.806195Z"},"links":{"cited_paper":"/paper/1810.03505","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:1601686869e7f2c558374f20224cb2351f6f541ac145d589a9fc33cddc306122","observation_id":"042027fe-c359-492d-99cd-154f2eeba8b0","resolution":{"observed_at":"2026-08-07T12:45:34.806195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.14937","last_updated":"2021-06-16T16:30:15Z","snapshot_observed_at":"2026-08-09T09:33:31.273841Z","submitted_at":"2021-04-30T12:02:03Z","title":"Federated Learning with Fair Averaging","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.14937","snapshot_observed_at":"2026-08-07T12:45:34.890436Z","title":"Federated learning with fair averaging,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.890436Z"},"links":{"cited_paper":"/paper/2104.14937","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:5a2a1c2a545d0ea02cb15fc84f86b095523e5c5fd348fe2eb6a14a8cebb22800","observation_id":"8e889ea8-c40a-4316-ad23-d16f1202447f","resolution":{"observed_at":"2026-08-07T12:45:34.890436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06440","last_updated":"2020-02-15T20:09:24Z","snapshot_observed_at":"2026-08-06T14:46:34.371139Z","submitted_at":"2020-02-15T20:09:24Z","title":"Federated Learning with Matched Averaging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06440","snapshot_observed_at":"2026-08-07T12:45:34.984741Z","title":"Federated learning with matched averaging,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:34.984741Z"},"links":{"cited_paper":"/paper/2002.06440","citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:c57d104afd5493fc611d09a46ee800bddf2f2ac4018a47ab9dcf138a644e42da","observation_id":"3eedfa64-3e34-48d6-94b1-64156f2b7833","resolution":{"observed_at":"2026-08-07T12:45:34.984741Z","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":"2026-08-07T12:45:35.083460Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:35.083460Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:0952c1b641df83de9545c645e40e988b0a149fb4ba3819060a55217be82a4469","observation_id":"ffecdc73-a257-433a-ade0-b75792c8120a","resolution":{"observed_at":"2026-08-07T12:45:35.083460Z","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":"2026-08-07T12:45:38.089211Z","title":"Federated optimization with linear-time approximated hessian diagonal,","venue":null,"work_id":"679db632-63ca-45c5-a8bc-374b3e837363","year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:35.178697Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:e762ffdb72b3651539ad6ec13dcedbab0ad03b19ab19ec1b8b9715e6934e647d","observation_id":"d9c58ee7-54f0-4b06-812c-27dfe75db371","resolution":{"observed_at":"2026-08-07T12:45:38.171151Z","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":"2026-08-07T12:45:37.947141Z","title":"Robust federated learning under statistical heterogeneity via hessian-weighted aggregation,","venue":null,"work_id":"dc4067cd-ea0e-481b-b8f7-3a50e9eaede1","year":2023},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:35.249638Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:edde036c0c3a3da2a167866ec068dd9aae1f3288b441446627b9786c3f5ddd0e","observation_id":"35a49397-52e5-43e9-8f42-8d0ef2e6e81e","resolution":{"observed_at":"2026-08-07T12:45:38.004326Z","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":"2026-08-07T12:45:37.722223Z","title":"Fed-sophia: A communication-efficient second-order federated learning algorithm,","venue":null,"work_id":"b77c228f-24ba-400c-a512-ab62688a17a9","year":2024},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:35.351380Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:9be9d93ebc20475bb1b11c7372e5692e08123b0eb2c1bba4eb7536770b9bf412","observation_id":"c3bdacc9-a17a-406a-b1b5-cbcc14cb7195","resolution":{"observed_at":"2026-08-07T12:45:37.813887Z","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":"2026-08-07T12:45:37.522203Z","title":"An estimator for the diagonal of a matrix,","venue":null,"work_id":"b49c070d-b137-4115-a259-4ee474f0dd48","year":2007},"citing_paper":{"arxiv_id":"2505.23588","last_updated":"2025-05-29T16:00:34Z","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:35.436548Z"},"links":{"citing_paper":"/paper/2505.23588"},"observation_digest":"sha256:f9ac36afb17ca0f059a602e9057e656ff44442302a176e6935f03898252705c5","observation_id":"f62ba3dd-bb8a-465b-95d3-b71fade0f26a","resolution":{"observed_at":"2026-08-07T12:45:37.601155Z","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":"2505.23588","last_updated":"2025-05-29T16:00:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T02:21:13.828072Z","submitted_at":"2025-05-29T16:00:34Z","title":"Accelerated Training of Federated Learning via Second-Order Methods"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":2,"verified_fuzzy":41},"total_outbound_references":106},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 106 outbound references and 0 inbound Pith citation observations for arXiv:2505.23588."}