{"as_of":"2026-08-23T17:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a7f06200a87b166be4883a8cb3b5ca6dc90abd682f3c3f27bd59f541a25199f0","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T18:34:18.037926Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2508.14539/citation-record","integrity":"/paper/2508.14539/integrity","json":"/paper/2508.14539/citation-record.json","paper":"/paper/2508.14539"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.02749","last_updated":"2023-03-05T18:55:12Z","snapshot_observed_at":"2026-08-17T18:47:22.932000Z","submitted_at":"2023-03-05T18:55:12Z","title":"Revisiting the Noise Model of Stochastic Gradient Descent","version":1},"cited_work":{"arxiv_id":"2303.02749","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.02749","snapshot_observed_at":"2026-08-05T18:34:19.391521Z","title":"Revisiting the Noise Model of Stochastic Gradient Descent","venue":"cs.LG","work_id":"7eef719c-04af-4ce5-bef4-f833b7bcbad9","year":2023},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:13.237172Z"},"links":{"cited_paper":"/paper/2303.02749","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:028b0994fbeb59570033b36b8cf52ff911b5607c55ba9a154969c7af7621a3ac","observation_id":"687a966b-4720-4d53-a3a9-c762a390192e","resolution":{"observed_at":"2026-08-05T18:34:19.522226Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-16T19:49:29.879809Z","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":"2026-08-05T18:34:13.355653Z","title":"Leaf: A benchmark for federated settings","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:13.355653Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:256fb15c832f29b9f171a1c1a16d359125ae393f1dfff95f445bd11279d80490","observation_id":"1def8fc6-14b0-4eb2-afcf-436d1c3cb05f","resolution":{"observed_at":"2026-08-05T18:34:13.355653Z","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":"2026-08-05T18:34:24.584567Z","title":"On bridging generic and personalized federated learning for image classification","venue":null,"work_id":"4b363745-e0fc-45df-ab0f-b0048b9d208e","year":2021},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:13.563087Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:07ee6ed185fbb80ba13352d6c5b4cd8e93045f7b788b0e90d61d7b2bc22af8f1","observation_id":"e3d17583-9249-44f1-bc1c-a075b34c2407","resolution":{"observed_at":"2026-08-05T18:34:24.724994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:24.247451Z","title":"Towards understanding biased client selection in federated learning","venue":null,"work_id":"f4a6efd5-6213-43af-93e3-d0ee8d71ebb5","year":2022},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:13.755597Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:513bf408032e605c1fb884f53d755fd02b561db59c1a16f31def8185539a17c4","observation_id":"17c53088-d4d6-4abb-9b7a-aa90d25e8c29","resolution":{"observed_at":"2026-08-05T18:34:24.404809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:23.959261Z","title":"A general theory for client sampling in federated learning","venue":null,"work_id":"86355ccb-bee1-48ab-82dd-f1501fad697c","year":2022},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:13.892535Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:ffc9d29ef05faec64afb77914fa8a8cf767eb586fcc3b19dafa7bffd2bc38e79","observation_id":"69f4bd51-e30f-45e1-a679-2738c201afb6","resolution":{"observed_at":"2026-08-05T18:34:24.115839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.13246","last_updated":"2023-02-20T04:10:03Z","snapshot_observed_at":"2026-08-16T17:32:02.475519Z","submitted_at":"2021-12-25T14:58:52Z","title":"Towards Federated Learning on Time-Evolving Heterogeneous Data","version":3},"cited_work":{"arxiv_id":"2112.13246","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.13246","snapshot_observed_at":"2026-08-05T18:34:19.135460Z","title":"Towards Federated Learning on Time-Evolving Heterogeneous Data","venue":"cs.LG","work_id":"ad7275cc-8494-4231-821d-018f2211f090","year":2021},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.079531Z"},"links":{"cited_paper":"/paper/2112.13246","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:a803d41a0ae2931982c0d66e63294150549bb937cc3e79004896525250aad1a4","observation_id":"e1451c8f-06b6-4599-8e56-f7c59c864f43","resolution":{"observed_at":"2026-08-05T18:34:19.213610Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:14.230321Z","title":"The movielens datasets: History and context","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.230321Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:668b66c323f73047c663017f94e7dc30ccf9a20119885918b4dcbb78b42ca900","observation_id":"92bcbbfa-5289-4f13-83a3-63237a2d8ada","resolution":{"observed_at":"2026-08-05T18:34:14.230321Z","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":"2026-08-05T18:34:23.530264Z","title":"The non-iid data quagmire of decentralized machine learning","venue":null,"work_id":"93a400f9-d507-407b-a7a7-f39d06f518e5","year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.423579Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:887393d6d6f1a24e327b6c0c33632a6594fa01d774bf680a4b4187f0b925e396","observation_id":"7a4d97ce-5fd6-47e0-b81a-f28ea70a45f4","resolution":{"observed_at":"2026-08-05T18:34:23.722332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-16T05:00:17.345539Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-05T18:34:14.625464Z","title":"Measuring the effects of non-identical data distribution for federated visual classification","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.625464Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:3f10795d25918c7df4e05dee5af9ca6fdc3eee17503972812112f7550a9d2b32","observation_id":"4d551abd-097f-4d12-b2cf-19f3ae248e29","resolution":{"observed_at":"2026-08-05T18:34:14.625464Z","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":"2026-08-05T18:34:14.738987Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.738987Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:1cdabdc8bb2c49a5d1a2f4c591259e0a1586d0e57f96f031d7df7e250a1ef95d","observation_id":"2459a83c-9c3d-4e13-9951-686aa94c549b","resolution":{"observed_at":"2026-08-05T18:34:14.738987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.06378","last_updated":"2021-04-09T16:21:59Z","snapshot_observed_at":"2026-08-20T06:04:09.590602Z","submitted_at":"2019-10-14T18:49:20Z","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.06378","snapshot_observed_at":"2026-08-05T18:34:14.899492Z","title":"Reddi, Sebastian U","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:14.899492Z"},"links":{"cited_paper":"/paper/1910.06378","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:984e8b82221907e88ed20521dcc4202f06fe2c854fc4b8687251db225c69c543","observation_id":"5cabc0f7-7e3c-479d-b4a2-e72f2cfcd7ab","resolution":{"observed_at":"2026-08-05T18:34:14.899492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-05T18:34:15.045006Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.045006Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:6f1908fe2fb34069f43a3e5f21450cc876ab5889f6594c05b0c701e0fd7f8d7f","observation_id":"a87f1516-6b91-4dd1-ac09-cc17a69fd8ff","resolution":{"observed_at":"2026-08-05T18:34:15.045006Z","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":"2026-08-05T18:34:23.148171Z","title":"Brownian motion in a field of force and the diffusion model of chemical reactions","venue":null,"work_id":"82ea8001-c4fa-483a-a8af-dc9c60b979be","year":1940},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.199171Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:4d4c54b77b9df61b6e6f2d1c16bf40d45fb75eb63495af34efd2e85da170d34a","observation_id":"27d2cde6-cd9a-4cfb-a0e9-effd8c7e60b4","resolution":{"observed_at":"2026-08-05T18:34:23.335566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:15.336631Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.336631Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:dfb0ecf481ef67d579d22aa26756050bbffe9285f0d1ef114e5f0d55e5748cbd","observation_id":"bc94ebc3-817f-47b3-aae0-2f5819ef0d5e","resolution":{"observed_at":"2026-08-05T18:34:15.336631Z","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":"2026-08-05T18:34:22.841528Z","title":"Federated learning: Challenges, methods, and future directions","venue":null,"work_id":"b56e2e2e-cc59-46cb-bb34-825b1479040f","year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.504147Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:5d93ffb10278d22b2c28fdf581ecfb0329f96b3aec0b5560ab38096253a5cb03","observation_id":"976bc449-5f8e-4758-b6c6-511dfe7dcf4b","resolution":{"observed_at":"2026-08-05T18:34:22.960045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.06127","last_updated":"2020-04-21T18:58:23Z","snapshot_observed_at":"2026-08-15T01:11:14.928056Z","submitted_at":"2018-12-14T19:28:29Z","title":"Federated Optimization in Heterogeneous Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.06127","snapshot_observed_at":"2026-08-05T18:34:15.615200Z","title":"Federated Optimization in Heterogeneous Networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.615200Z"},"links":{"cited_paper":"/paper/1812.06127","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:1898ca5328d3f283b1ceabca8ca16b8c9cafac91df80686f8ec0c256706ca54c","observation_id":"1048e8be-0ed4-4b73-b7b3-1fbbd43301ac","resolution":{"observed_at":"2026-08-05T18:34:15.615200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.07217","last_updated":"2020-02-17T11:42:10Z","snapshot_observed_at":"2026-08-14T18:38:32.170609Z","submitted_at":"2018-08-22T04:50:55Z","title":"Don't Use Large Mini-Batches, Use Local SGD","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.07217","snapshot_observed_at":"2026-08-05T18:34:15.742186Z","title":"Don't use large mini-batches, use local sgd","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.742186Z"},"links":{"cited_paper":"/paper/1808.07217","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:aa0280d39245a7511d2c4ea982c5c48b3136bb1ccd2d9dc05435adc70dca995b","observation_id":"0d287e8a-3764-4b8c-a97f-7fb385c4c884","resolution":{"observed_at":"2026-08-05T18:34:15.742186Z","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":"2026-08-05T18:34:22.467250Z","title":"Ensemble distillation for robust model fusion in federated learning","venue":null,"work_id":"54a30307-f932-48db-9953-b7014bd855ba","year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:15.922760Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:b45f3e989d78b834ac7dadf7221f08bc6c45b1aa884f50407b3b60487720f98b","observation_id":"8ee6a2df-6145-4286-9019-c5a8fe517447","resolution":{"observed_at":"2026-08-05T18:34:22.651313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:22.190873Z","title":"Eine neue herleitung des exponentialgesetzes in der wahrscheinlichkeitsrechnung","venue":null,"work_id":"0c28a5d0-51dc-495f-b23a-fee586b537ee","year":1922},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.088851Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:ddde4e51a59db3f9033fa67c731d2c12615dba6020bdef90ffd1c48ff68dc1c7","observation_id":"df127d46-07d4-4c32-b855-7cc9b9439c0d","resolution":{"observed_at":"2026-08-05T18:34:22.310202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:21.844237Z","title":"Stochastic gradient descent as approximate bayesian inference","venue":null,"work_id":"129fa9ae-1fcb-4c5b-bda4-590bef269d89","year":2017},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.210697Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:a324d846aa90fabab1c3f98142a4ba7ea85d1e3b6c69f545d086f0de13d3f3a9","observation_id":"f5b23b8c-6f0a-4244-934f-2a67eecc1765","resolution":{"observed_at":"2026-08-05T18:34:22.013009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.05629","last_updated":"2023-01-26T22:54:08Z","snapshot_observed_at":"2026-08-17T13:07:20.583520Z","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":"2026-08-05T18:34:16.323624Z","title":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Ag \\\"u era y Arcas","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.323624Z"},"links":{"cited_paper":"/paper/1602.05629","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:57714b5c6b9e2497e2709fb4df47adc3c26db90f5d12eb9f6da0cac944658db0","observation_id":"5ac481e1-5ed1-4374-85fd-3c014cfa345d","resolution":{"observed_at":"2026-08-05T18:34:16.323624Z","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":"2026-08-05T18:34:21.570880Z","title":"Fedfast: Going beyond average for faster training of federated recommender systems","venue":null,"work_id":"9940026d-9471-43db-acd3-3ffc0df0e30d","year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.384142Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:0b9e6d3fab3add0aa5a8c9549530b867555c7dc209efbd5eb405be55aeec5ce5","observation_id":"554b0590-0f32-4d4c-93b6-40b0f83c20c6","resolution":{"observed_at":"2026-08-05T18:34:21.671460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00295","last_updated":"2021-09-08T23:37:17Z","snapshot_observed_at":"2026-08-13T06:06:10.844945Z","submitted_at":"2020-02-29T16:37:29Z","title":"Adaptive Federated Optimization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.00295","snapshot_observed_at":"2026-08-05T18:34:16.473704Z","title":"Adaptive federated optimization","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.473704Z"},"links":{"cited_paper":"/paper/2003.00295","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:98d530f2a1c5d47ac9472397f3a376951f0e8507344e778f1c09beb0a1882fc3","observation_id":"a914f633-5fdd-4b53-8ec1-6eececf4d58b","resolution":{"observed_at":"2026-08-05T18:34:16.473704Z","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":"2026-08-05T18:34:16.615389Z","title":"A tail-index analysis of stochastic gradient noise in deep neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.615389Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:a2a5295002101571c9b37bf6129b4ce0b89d1f1359b02fff68622c4d56892108","observation_id":"29a05c9c-f804-4ff9-86f5-5c5073afa0a1","resolution":{"observed_at":"2026-08-05T18:34:16.615389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03824","last_updated":"2023-06-06T16:12:35Z","snapshot_observed_at":"2026-08-16T15:26:06.749968Z","submitted_at":"2023-06-06T16:12:35Z","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","version":1},"cited_work":{"arxiv_id":"2306.03824","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.03824","snapshot_observed_at":"2026-08-05T18:34:18.752882Z","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","venue":"cs.LG","work_id":"208a2124-0150-4ad9-9066-4559ec829011","year":2023},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.748343Z"},"links":{"cited_paper":"/paper/2306.03824","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:86fca82be32f032a666b67d377c39a3c3844013133c50b5acfaf5422a300e8fe","observation_id":"6a72657a-1331-4fd4-aca6-6c2025ecc79f","resolution":{"observed_at":"2026-08-05T18:34:18.896031Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:21.266522Z","title":"On the noisy gradient descent that generalizes as sgd","venue":null,"work_id":"53c0a49e-141a-4886-a453-1d8b6e57e123","year":2020},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:16.887409Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:b55ae94fae332739d4d333735996feaf97b13bdbab4c2298974e717c70ffbe37","observation_id":"ddbc2761-6207-43a1-8b16-3261fcfe8659","resolution":{"observed_at":"2026-08-05T18:34:21.421915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02021","last_updated":"2018-03-06T05:01:37Z","snapshot_observed_at":"2026-08-14T19:39:12.132907Z","submitted_at":"2018-03-06T05:01:37Z","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02021","snapshot_observed_at":"2026-08-05T18:34:17.015864Z","title":"Understanding short-horizon bias in stochastic meta-optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.015864Z"},"links":{"cited_paper":"/paper/1803.02021","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:2e4af2c0388979b004d0d8941f86abde63755d638bd2e89cc98d47df45df38c6","observation_id":"28f14951-1895-4f87-926f-18dd21acc06b","resolution":{"observed_at":"2026-08-05T18:34:17.015864Z","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":"2026-08-05T18:34:20.945091Z","title":"A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima","venue":null,"work_id":"07affba2-3edd-44e6-8b49-5ab5b4c75139","year":2021},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.142829Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:a7219e4907f0ee513d7ea545fdd03f625e5e9cb75b6847c29ae9c52ffa7e2d25","observation_id":"6542ec94-46c2-478e-bb2f-b39789bcf182","resolution":{"observed_at":"2026-08-05T18:34:21.069031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08234","last_updated":"2020-12-16T06:26:36Z","snapshot_observed_at":"2026-08-17T19:12:58.376722Z","submitted_at":"2019-10-18T03:17:22Z","title":"Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating","version":3},"cited_work":{"arxiv_id":"1910.08234","doi":null,"metadata_source":"pith","pith_arxiv_id":"1910.08234","snapshot_observed_at":"2026-08-05T18:34:18.569126Z","title":"Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating","venue":"cs.LG","work_id":"45d0bd6e-c7be-40b5-93db-f47e3bb2bc34","year":2019},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.276255Z"},"links":{"cited_paper":"/paper/1910.08234","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:c4e4acba7c49c753a493d192a2dee6496a0c2767f5c38b9baa364034bb7f05f6","observation_id":"e1c9b0ea-19f5-42aa-8b25-d9c3655b85d0","resolution":{"observed_at":"2026-08-05T18:34:18.649125Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:20.725396Z","title":"Lookahead optimizer: k steps forward, 1 step back","venue":null,"work_id":"557ee0a6-1d54-4c36-a53c-0eaf9483f42f","year":2019},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.417629Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:40080cd161ad59490c7f1188ce1e5060b99b09e202fb7fd178b2ac2a45023713","observation_id":"b9325a8b-f735-416a-91ad-d1d917b55273","resolution":{"observed_at":"2026-08-05T18:34:20.830275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-08-20T14:11:46.485424Z","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":"2026-08-05T18:34:17.507842Z","title":"Federated Learning with Non - IID Data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.507842Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:39bb067380b0814e7b74e2ba1e2991dbd0123b9942fad44f0b8e2f966936c6fa","observation_id":"bd50ba79-12cf-4f16-8927-0d5caa48ea66","resolution":{"observed_at":"2026-08-05T18:34:17.507842Z","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":"2026-08-05T18:34:20.374166Z","title":"Deep interest network for click-through rate prediction","venue":null,"work_id":"a47f1de5-9ad6-4d65-bf73-4eb935718f7c","year":2018},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.570572Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:36f39a84edd396f7c2b191171943a7d4c2336e334aff407d889e79e13f85a284","observation_id":"2299e7b7-a089-4333-9c29-4559f7161bd3","resolution":{"observed_at":"2026-08-05T18:34:20.575603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:20.010559Z","title":"Diurnal or nocturnal? federated learning of multi-branch networks from periodically shifting distributions","venue":null,"work_id":"056339cc-282c-438f-8dea-4210f8f70c29","year":2022},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.688349Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:04c16b3c80a989502a61b3a69f1d0d7db447c2e46420b66b88d35bbae25ff113","observation_id":"60ccadaf-5e0d-4db8-a4b1-e284bb03807c","resolution":{"observed_at":"2026-08-05T18:34:20.187966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:34:19.706459Z","title":"The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects","venue":null,"work_id":"b643ca56-4e2d-40d4-8b13-171b0ee5fafa","year":2019},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:17.845167Z"},"links":{"citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:50c90de43dc570fff515a69482e56c6f7bde2c38cfd1e7a7cca767380f139177","observation_id":"c9b49445-bc9c-44b3-ad47-c54cb10d049c","resolution":{"observed_at":"2026-08-05T18:34:19.888717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05375","last_updated":"2022-03-08T09:00:56Z","snapshot_observed_at":"2026-08-16T18:46:31.875605Z","submitted_at":"2021-02-10T10:38:55Z","title":"Strength of Minibatch Noise in SGD","version":3},"cited_work":{"arxiv_id":"2102.05375","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.05375","snapshot_observed_at":"2026-08-05T18:34:18.251185Z","title":"Strength of Minibatch Noise in SGD","venue":"cs.LG","work_id":"18527f83-6fc6-49c5-a166-e2161a22f487","year":2021},"citing_paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-05T18:34:18.037926Z"},"links":{"cited_paper":"/paper/2102.05375","citing_paper":"/paper/2508.14539"},"observation_digest":"sha256:f3339383aeb2c5d7f4a54a801feef6284a7e355f8efe126c6bea3725791e1e30","observation_id":"db44e10b-980a-41bf-9c1e-3e0d37f81c46","resolution":{"observed_at":"2026-08-05T18:34:18.342578Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.14539","last_updated":"2025-08-20T08:42:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T02:54:16.078361Z","submitted_at":"2025-08-20T08:42:34Z","title":"FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":5,"verified_fuzzy":16},"total_outbound_references":35},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2508.14539."}