{"as_of":"2026-08-10T05:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:644d419ab3d9e5299daa50d96905f896e970064abee35db13ab8e19b7c662a8f","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:30:47.029675Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T00:07:55.485589Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T10:51:22.663894Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"cited_work":{"arxiv_id":"2502.02727","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.02727","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Méthode générale pour la réso- lution des systemes d’équations simultanées.Comp","venue":null,"work_id":"1dcabac4-5ae9-4573-ad53-b3c2dce7434f","year":2025},"citing_paper":{"arxiv_id":"2604.12968","last_updated":"2026-04-14T17:01:36Z","snapshot_observed_at":"2026-07-06T23:01:05.634599Z","submitted_at":"2026-04-14T17:01:36Z","title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T15:16:58.221358Z"},"links":{"cited_paper":"/paper/2502.02727","citing_paper":"/paper/2604.12968"},"observation_digest":"sha256:7713ecc3d5ccd43f973bb2793905cd2c4d1f8003dd3f7d7caef023f10326df8b","observation_id":"6680cba9-cb6c-47b6-937a-807eeff0f985","resolution":{"observed_at":"2026-05-11T10:51:22.707348Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02727","snapshot_observed_at":"2026-07-12T00:07:55.485589Z","title":"arXiv preprint arXiv:2502.02727 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03763","last_updated":"2026-07-04T08:31:49Z","snapshot_observed_at":"2026-08-07T12:54:26.891354Z","submitted_at":"2026-07-04T08:31:49Z","title":"FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-07-12T00:07:55.485589Z"},"links":{"cited_paper":"/paper/2502.02727","citing_paper":"/paper/2607.03763"},"observation_digest":"sha256:bbdb11bf179d5f161e5714e9a1a681d9398164836bf50a6edfa38e74ba955e02","observation_id":"73cc9b2e-4a30-44c4-9445-dcd0b8f43a45","resolution":{"observed_at":"2026-07-12T00:07:55.485589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.02727/citation-record","integrity":"/paper/2502.02727/integrity","json":"/paper/2502.02727/citation-record.json","paper":"/paper/2502.02727"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T11:30:46.903517Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.903517Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:d6d69bbdafc3f647a681ce0c0c268514035bc3bfde415a0bd54f9c2a03ee6623","observation_id":"4c8a155e-e227-4d77-8a6b-143501608ee4","resolution":{"observed_at":"2026-08-09T11:30:46.903517Z","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":"2026-08-09T11:30:47.757713Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":"523cca6d-be73-4df8-9735-7af82d7b79c1","year":2021},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.907228Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:4f22303ef1ea014025e33490ac14ff34c3aa579b0fdc79c77f3fc3f9dcab0072","observation_id":"6c048ee6-7bba-4147-8035-89c45390ab5b","resolution":{"observed_at":"2026-08-09T11:30:47.761330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.747985Z","title":"Adaptive subgradient methods for online learning and stochastic optimization","venue":null,"work_id":"9106deaa-6073-4e5c-866b-cbe81eaaabf8","year":2011},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.910549Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:e1aed098eccc600daa304b1021acc1249c1937a98dcd76d6047b880698a4bbb1","observation_id":"d82de800-d688-479a-aa6e-9a3d9cb1972c","resolution":{"observed_at":"2026-08-09T11:30:47.751610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1308.0850","last_updated":"2014-06-05T16:04:02Z","snapshot_observed_at":"2026-08-05T10:16:44.137827Z","submitted_at":"2013-08-04T21:04:36Z","title":"Generating Sequences With Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.0850","snapshot_observed_at":"2026-08-09T11:30:46.914406Z","title":"Generating sequences with recurrent neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.914406Z"},"links":{"cited_paper":"/paper/1308.0850","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:dcc19521da3710585ce0951a9d5e1bb84baa0d56ff31834cdb2c3b5a3a725a57","observation_id":"8443b6fc-0f01-4f8e-8a18-792172bb17dd","resolution":{"observed_at":"2026-08-09T11:30:46.914406Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-09T11:30:46.918574Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.918574Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:b913b1b22ec174ee1b94e257906f42273e407032215b1360457664290c273080","observation_id":"725167c7-cba0-4d5b-a253-6e6fbbd8e425","resolution":{"observed_at":"2026-08-09T11:30:46.918574Z","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":"2026-08-09T11:30:47.738345Z","title":"Towards building the federatedgpt: Federated instruction tuning,","venue":null,"work_id":"b4bd83b2-c213-410a-8e16-3a05a34740d5","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.922146Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:065daefab500801a3f123836630187b15777248488ef90a10cca120eba1d626e","observation_id":"5037be44-78d3-4be4-af5f-0f9666cfccd5","resolution":{"observed_at":"2026-08-09T11:30:47.741863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.16504","last_updated":"2024-03-05T17:51:19Z","snapshot_observed_at":"2026-07-06T15:48:01.777256Z","submitted_at":"2023-06-28T18:52:27Z","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.16504","snapshot_observed_at":"2026-08-09T11:30:46.925580Z","title":"Momentum benefits non-iid federated learning simply and provably,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.925580Z"},"links":{"cited_paper":"/paper/2306.16504","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:3a2e156e67e0ed65ff0cf7c6d526562323c6229d3954e040216df506562c5f8d","observation_id":"fb649365-9285-45a0-bb78-5a07f0ef98de","resolution":{"observed_at":"2026-08-09T11:30:46.925580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00295","last_updated":"2021-09-08T23:37:17Z","snapshot_observed_at":"2026-07-06T09:01:12.515300Z","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":"2026-08-09T11:30:46.929104Z","title":"Adaptive federated optimization,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.929104Z"},"links":{"cited_paper":"/paper/2003.00295","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:83a035e8a82f1e1cf0d69f6e0c1615383080955ba5777756947ccc5bf508f768","observation_id":"a3c1fbdd-90a9-4cb0-b48f-c454583af325","resolution":{"observed_at":"2026-08-09T11:30:46.929104Z","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":"2026-08-09T11:30:47.728718Z","title":"Communication-efficient adaptive federated learning,","venue":null,"work_id":"bf2a71f3-5379-467b-b4d6-a833df5b586a","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.932477Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:b895d212b4ee4176869f0733b9d2806853a98cb58a4e42de7604fa8a611453a0","observation_id":"74c7907b-02c5-45fd-ba16-e901bbf78b2b","resolution":{"observed_at":"2026-08-09T11:30:47.732307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.720041Z","title":"Scaffold: Stochastic controlled averaging for federated learning,","venue":null,"work_id":"54b34029-3bef-405c-b877-527a30af0025","year":2020},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.935655Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:f395d0748d0eec8ed27a3be4334ac1b593a9e868221884702120ee5a43a32fc9","observation_id":"682a21c9-d4ac-41e5-88e0-ab184795f3fa","resolution":{"observed_at":"2026-08-09T11:30:47.722977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.711511Z","title":"Proxskip: Yes! local gradient steps provably lead to communication acceleration! finally!","venue":null,"work_id":"b1aa3d22-530f-4c25-86c5-377d9934abd0","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.938991Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:49033a79fcd6c3d6025ff526721273a01960ab345bcfad905580cacc86946722","observation_id":"d2423329-a093-4690-bbc9-b80b6d83c61a","resolution":{"observed_at":"2026-08-09T11:30:47.714538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:46.942600Z","title":"Next: In-network nonconvex optimization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.942600Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:ad74f243c96ed8257d8a778530b29509a4e875ca5aa846b626405d24d9835d60","observation_id":"69e76932-930f-46f1-8564-0680fe7da0eb","resolution":{"observed_at":"2026-08-09T11:30:46.942600Z","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":"2026-08-09T11:30:46.945568Z","title":"Achieving geometric convergence for distributed optimization over time-varying graphs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.945568Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:715dc70d7d343a205649d752944cb074e0d0968764f073cf0b17fef6edc70c40","observation_id":"5ed85afe-82c2-40f7-88f9-f616b75a54a3","resolution":{"observed_at":"2026-08-09T11:30:46.945568Z","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":"2026-08-09T11:30:47.691393Z","title":"Asy-sonata: Achieving linear convergence in distributed asynchronous multiagent optimization,","venue":null,"work_id":"91305ba2-2fdd-458f-8236-b01b8c314e14","year":2018},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.948541Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:015e17e0ad7677ba0873375ebb466360780a9e3414c874c9af2841ea164d1fbf","observation_id":"95695845-0e8b-4626-9075-923114e3b276","resolution":{"observed_at":"2026-08-09T11:30:47.695186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.666655Z","title":"An improved analysis of gradient tracking for decentralized machine learning,","venue":null,"work_id":"3240f346-caaf-4ab8-8309-ae52cebacc93","year":2021},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.951461Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:f81eacbdfa8955274ff5cc7ce9b4aecb7aca3e33af86e213dd11fffd3e2a65c9","observation_id":"9fb96d92-2abc-456b-b6e6-4336c6a476e0","resolution":{"observed_at":"2026-08-09T11:30:47.684873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.632308Z","title":"Gtadam: Gradient tracking with adaptive momentum for distributed online optimization,","venue":null,"work_id":"aaa7f176-f9a7-4bc3-a434-a85a20386b99","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.955284Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:cff54464c6b57e55897e619d56f3992616d1ca80df645f38c0392385aa46bdf4","observation_id":"906d4d50-6f7e-4526-842e-6dd91daea907","resolution":{"observed_at":"2026-08-09T11:30:47.652976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15505","last_updated":"2023-09-24T05:10:47Z","snapshot_observed_at":"2026-08-09T01:14:22.166775Z","submitted_at":"2022-09-30T14:51:19Z","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","version":2},"cited_work":{"arxiv_id":"2209.15505","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.15505","snapshot_observed_at":"2026-08-09T11:30:47.151002Z","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","venue":"cs.LG","work_id":"ca8f7062-d07e-48d3-9ca7-6c9d379c94c0","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.958679Z"},"links":{"cited_paper":"/paper/2209.15505","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:c7f752fef21929defdc8b31a732d483ee7e74965fc38d54ec837c52b0686b95a","observation_id":"1a7b79cb-6b83-4f9e-8bca-d2d6f86833e1","resolution":{"observed_at":"2026-08-09T11:30:47.154659Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.591231Z","title":"Momentum-based distributed gradient tracking algorithms for distributed aggregative optimization over unbalanced directed graphs,","venue":null,"work_id":"1b41cdba-557b-40a2-a04b-e6f6397df546","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.963237Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:b23abd74da729d73175e909a3f2be92a81eebd3566c5128dd1ca584241ce0f23","observation_id":"57c66aa1-084d-407a-8b6d-ee1f93ec0dcd","resolution":{"observed_at":"2026-08-09T11:30:47.608918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.539310Z","title":"Towards optimal communication complexity in distributed non-convex optimization,","venue":null,"work_id":"c6638075-82ce-4993-b228-791efd6ba2fa","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.966827Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:63ea16b18c3202c28d22d5a4480262ea8e4decd3a40581bd362c8cc7b1b93812","observation_id":"a9a98f34-37e3-4d97-854d-b88e19d975c1","resolution":{"observed_at":"2026-08-09T11:30:47.561630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.01313","last_updated":"2023-01-03T19:06:41Z","snapshot_observed_at":"2026-07-06T14:37:13.024150Z","submitted_at":"2023-01-03T19:06:41Z","title":"Decentralized Gradient Tracking with Local Steps","version":1},"cited_work":{"arxiv_id":"2301.01313","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.01313","snapshot_observed_at":"2026-08-09T11:30:47.136962Z","title":"Decentralized Gradient Tracking with Local Steps","venue":"math.OC","work_id":"b2c537cf-b68a-4227-bbae-fd9eecba185a","year":2023},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.970682Z"},"links":{"cited_paper":"/paper/2301.01313","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:0db5546736e58e9573684a74edb72b27b955e6a0382e56f2fcfc5148cf4d2619","observation_id":"51afbb62-e875-47cd-839b-2b46fda3ee8e","resolution":{"observed_at":"2026-08-09T11:30:47.140518Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01537","last_updated":"2023-02-03T04:23:40Z","snapshot_observed_at":"2026-07-06T14:47:56.365341Z","submitted_at":"2023-02-03T04:23:40Z","title":"Gradient and Variable Tracking with Multiple Local SGD for Decentralized Non-Convex Learning","version":1},"cited_work":{"arxiv_id":"2302.01537","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.01537","snapshot_observed_at":"2026-08-09T11:30:47.123594Z","title":"Gradient and Variable Tracking with Multiple Local SGD for Decentralized Non-Convex Learning","venue":"math.OC","work_id":"a4861cf5-5db1-4cd4-9e63-dbb0fe014dcd","year":2023},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.974311Z"},"links":{"cited_paper":"/paper/2302.01537","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:bd1cb8ddf5937ac603c7edcc05b428716b81d9670fe8ce5b7bfb9af7e9bad2c7","observation_id":"2af15478-6794-4df5-8524-787c48a77282","resolution":{"observed_at":"2026-08-09T11:30:47.127336Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14289","last_updated":"2023-11-24T06:13:04Z","snapshot_observed_at":"2026-07-06T15:07:49.009949Z","submitted_at":"2023-03-24T22:14:31Z","title":"Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization","version":2},"cited_work":{"arxiv_id":"2303.14289","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.14289","snapshot_observed_at":"2026-08-09T11:30:47.109332Z","title":"Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization","venue":"math.OC","work_id":"7e7f13bf-5089-4382-916c-b5000da450f8","year":2023},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.977508Z"},"links":{"cited_paper":"/paper/2303.14289","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:29d1f6ec057de7ba1095eba76200330929f9ea3263bb4eb3e757c2a43a1d9bd5","observation_id":"e25e76b3-55f0-45bf-8ab1-a815db76f3b8","resolution":{"observed_at":"2026-08-09T11:30:47.113270Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.493825Z","title":"Local exact-diffusion for decentralized optimization and learning,","venue":null,"work_id":"9e94a741-2bdc-4a15-88ac-aea65a62b23a","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.981718Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:50734ab5154e30d59a597f75e2c9e115e33217cbebfa5a288024b58c2d68ae69","observation_id":"d8f6e3ce-487e-450a-959e-244315ea8dae","resolution":{"observed_at":"2026-08-09T11:30:47.512646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.434611Z","title":"Taming subnet-drift in d2d-enabled fog learning: A hierarchicalgradienttrackingapproach,","venue":null,"work_id":"afeb964e-a376-45ec-af6a-9c7f874473b3","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.985829Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:229e5efdff08185c471cf6ce36bb9b0741a8c230ba4bf593929ffd9f9a67e519","observation_id":"5900930e-92ab-4d82-8f72-1670a0ede5d7","resolution":{"observed_at":"2026-08-09T11:30:47.471276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.392408Z","title":"Hierarchical federated learning with multi-timescale gradient correction,","venue":null,"work_id":"4538ae84-dffb-49d3-965f-55e49ce32f44","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.989241Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:a226916b0835e6e6a4ab8b8b2e09a1344e2bdd3e29701f583bb7e1e8a71092fc","observation_id":"e5545712-4f78-49ee-ac18-f9dc29ee2285","resolution":{"observed_at":"2026-08-09T11:30:47.411781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-09T11:30:46.992796Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.992796Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:8bd418a39b2544a3d6832db24e4b6f823bd63aae46bd238aa744261522cfbea0","observation_id":"14f04332-0425-433e-b36b-d5067586ae2e","resolution":{"observed_at":"2026-08-09T11:30:46.992796Z","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":"2026-08-09T11:30:47.361815Z","title":"On the overlooked pitfalls of weight decay and how to mitigate them: A gradient-norm perspective,","venue":null,"work_id":"2434d3a8-6e58-4b7d-8630-e5691436ae4a","year":2024},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:46.996148Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:a592f6cfb746787b5271d11a450d2fd993c3b4e63b750022e78d40f289edc4de","observation_id":"0f45ad9a-74b4-4d26-852f-9ce372673d16","resolution":{"observed_at":"2026-08-09T11:30:47.376116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.09030","last_updated":"2020-12-05T00:26:57Z","snapshot_observed_at":"2026-08-07T10:14:22.814385Z","submitted_at":"2019-11-20T16:58:40Z","title":"Local AdaAlter: Communication-Efficient Stochastic Gradient Descent with Adaptive Learning Rates","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.09030","snapshot_observed_at":"2026-08-09T11:30:47.000250Z","title":"Local adaalter: Communication-efficient stochastic gradient descent with adaptive learning rates,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.000250Z"},"links":{"cited_paper":"/paper/1911.09030","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:b8e8bcb3e7eaaf25b0f2a6ff367803a80a29a2c31e317d5da95a1258edbfd3d5","observation_id":"e4f397d0-9a74-49d4-9382-e4cb94b5c768","resolution":{"observed_at":"2026-08-09T11:30:47.000250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00522","last_updated":"2023-07-30T14:53:21Z","snapshot_observed_at":"2026-08-08T17:57:03.380671Z","submitted_at":"2023-07-30T14:53:21Z","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","version":1},"cited_work":{"arxiv_id":"2308.00522","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.00522","snapshot_observed_at":"2026-08-09T11:30:47.072227Z","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","venue":"cs.LG","work_id":"db247c9b-9e8d-4df9-b277-a2b0916d9f92","year":2023},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.004225Z"},"links":{"cited_paper":"/paper/2308.00522","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:6d483e08418e13d8858876bc3d0422f0bb5fbc86b708502f65ce00182a3dac84","observation_id":"59fe363b-9fac-445a-903e-6a2625c9f48e","resolution":{"observed_at":"2026-08-09T11:30:47.078482Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.351636Z","title":"A sufficient condition for convergences of adam and rmsprop,","venue":null,"work_id":"002af52c-3da0-4dc4-89e9-3b6959ef172b","year":2019},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.007954Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:cf7e80196d9727a2a952e20bbb75e20046db3dc03dc3adaca43ca2e70850ffcb","observation_id":"fbf36c00-be84-4aed-b13a-747cbaaa51b4","resolution":{"observed_at":"2026-08-09T11:30:47.355185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.330904Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"001f3cb0-24b7-4c4a-9bea-918fb004404f","year":2009},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.011732Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:0e057ba33d96c203cb8b6069ae21b6eca18500111545301bb4f13d65ab486e0f","observation_id":"0befee3f-02f5-4ebd-9c82-60f7a9b59120","resolution":{"observed_at":"2026-08-09T11:30:47.345272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.014982Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.014982Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:4c22e7ce97bb037f72fa66a874b029590c08f5ae188cf3b30b3d4d429b49b02c","observation_id":"76eb9631-134c-4442-8747-b2cb69579ac5","resolution":{"observed_at":"2026-08-09T11:30:47.014982Z","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":"2026-08-09T11:30:47.282301Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":"6b2bcce9-7dbd-4606-b7dc-07afc7ef404e","year":2022},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.017875Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:a94933278e7e55193098ee7ce61fe3df7b15002e3fad42759b2d8d83a90e95f1","observation_id":"b2aa42e8-c509-4e75-ad37-707142b2dd54","resolution":{"observed_at":"2026-08-09T11:30:47.302456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.239192Z","title":"Language models are unsupervised multitask learners,","venue":null,"work_id":"5f750135-5873-42d7-ac0c-034bd2ed7cef","year":2019},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.021587Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:a12a882791b7bc599771bd8248d154b7131d9b048940924052fb6795eb26e598","observation_id":"1023862d-efcd-4ae9-a297-97bf429e09d8","resolution":{"observed_at":"2026-08-09T11:30:47.257458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T11:30:47.198022Z","title":"Newsweeder: Learning to filter netnews,","venue":null,"work_id":"391ba14d-8a9a-497a-b098-252c30991c66","year":1995},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.025501Z"},"links":{"citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:a4a4f9fd606b9abbb833f1d6ed5a20f7db2c02f8d506d53c2b1c920bb4133273","observation_id":"799a9b87-ff15-4a8b-814f-647653a3de0a","resolution":{"observed_at":"2026-08-09T11:30:47.215877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-07-06T06:34:26.609892Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-09T11:30:47.029675Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T11:30:47.029675Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2502.02727"},"observation_digest":"sha256:454d087df6fa0ba6b6819f3ead9dce1438742815c89d1f6b9673709174ad1691","observation_id":"87564f78-904d-4caa-8b7e-18fadf24f796","resolution":{"observed_at":"2026-08-09T11:30:47.029675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.02727","last_updated":"2025-05-18T02:48:18Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T15:46:49.443216Z","submitted_at":"2025-02-04T21:21:30Z","title":"Gradient Correction in Federated Learning with Adaptive Optimization"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":5,"verified_fuzzy":20},"total_outbound_references":36},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2502.02727."}