{"as_of":"2026-08-14T02:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:583115d2b409a74fdfc0ca0a2e206762726730d1afe0eeae9f269bb2e7b6928f","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":"2026-08-09T00:13:44.715349Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-07T16:45:53.627922Z","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":"2026-05-11T23:31:17.598377Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"cited_work":{"arxiv_id":"2502.03958","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03958","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Non-convex composite federated learning with heterogeneous data","venue":null,"work_id":"0e6f5964-96c5-4292-b681-2af11ce50028","year":2025},"citing_paper":{"arxiv_id":"2604.25467","last_updated":"2026-04-28T10:12:57Z","snapshot_observed_at":"2026-07-06T23:11:21.433834Z","submitted_at":"2026-04-28T10:12:57Z","title":"Subspace Optimization for Efficient Federated Learning under Heterogeneous Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-07T16:45:53.627922Z"},"links":{"cited_paper":"/paper/2502.03958","citing_paper":"/paper/2604.25467"},"observation_digest":"sha256:a8805de3b3e9db122c5c6ebaf2fabe7f4a9cfa3d0983489684602f7cbaf87834","observation_id":"1a877e1e-b89c-41cb-adce-16f4c632a498","resolution":{"observed_at":"2026-05-11T23:31:17.605124Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.03958/citation-record","integrity":"/paper/2502.03958/integrity","json":"/paper/2502.03958/citation-record.json","paper":"/paper/2502.03958"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:13:45.762627Z","title":"Privacy-preserving and communication-efficient energy prediction scheme based on federated learning for smart grids","venue":null,"work_id":"959287f3-c2d7-416a-a490-cdf13dc30f1a","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.271657Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:8dc0fc15b27a103784a416a52c2ee0df1c58b764539d57d9367a0225b494dc7a","observation_id":"658092da-76ff-49d0-83d4-4b44473a0e2b","resolution":{"observed_at":"2026-08-09T00:13:45.767645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.748777Z","title":"Fast composite optimization and statistical recovery in federated learning","venue":null,"work_id":"02604d09-cefe-4d30-b9f7-f45402640af0","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.330687Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:343edc70343ef0f893c6276ba49fb9d3a058688dfad3ac1a6b5be05393440dc2","observation_id":"637bd418-395f-454f-ba6a-727fe14e9e3e","resolution":{"observed_at":"2026-08-09T00:13:45.753072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.376019Z","title":"A fast iterative shrinkage- thresholding algorithm for linear inverse problems","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.376019Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:e8a4822043418c43ed61ec9624294f4ed190e8dcf116506af911e2c6ba7a8e69","observation_id":"ebb1316e-0dee-46d7-93a2-aca82a88caa0","resolution":{"observed_at":"2026-08-09T00:13:44.376019Z","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":"2026-08-09T00:13:45.619688Z","title":"Online optimization of switched LTI systems using continuous-time and hybrid accelerated gradient flows","venue":null,"work_id":"6e22fbc7-4661-4cf7-a7d2-469cb8260637","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.420853Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:6fbc1b37af9feb7029832b5baa3d4c14b587a65c2c71a0b80f07a7dde67aa70f","observation_id":"90839fe7-70ee-4484-bcb6-7ed27621eb55","resolution":{"observed_at":"2026-08-09T00:13:45.624780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.605668Z","title":"Sparse linear regression from perturbed data","venue":null,"work_id":"fc5f7939-96ff-4c08-82b0-43d4510ffd17","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.443949Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:cef8ac14361ad9e9ba6794ae4dd3539639fbef0dd565bcd633f6bfe1be25d280","observation_id":"59e75279-c566-462d-b74a-40a6c179f22f","resolution":{"observed_at":"2026-08-09T00:13:45.610469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.590408Z","title":"Distributed networked real-time learning","venue":null,"work_id":"5dc60021-45ca-497b-8986-55a945f6fa64","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.448157Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:eb5e50f7445e5aa5b0e0b5ab4d17d65dee72487d92e9bc0977ff15254317288e","observation_id":"0d9240b8-7ee1-4198-be6f-b17e2f721632","resolution":{"observed_at":"2026-08-09T00:13:45.595997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.453081Z","title":"Mini- batch stochastic approximation methods for nonconvex stochastic composite optimization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.453081Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:a8657eb7b1f2de221ec3e0521718ac7355de7de1b2b71b79b102c537fae9b954","observation_id":"05cb3c08-afdd-4391-874b-5b8b65751231","resolution":{"observed_at":"2026-08-09T00:13:44.453081Z","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":"2026-08-09T00:13:45.566827Z","title":"A strictly contractive Peaceman–Rachford splitting method for convex programming","venue":null,"work_id":"b6ca2bbe-adfd-48f5-b125-02f85120b387","year":2014},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.457232Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:d5d218014a53e7b7032643f07b4e3dba7755ee894326497b338cbc0a7dd8d1b5","observation_id":"57f0dbe5-4ec9-463b-b5b0-34628cda1b1c","resolution":{"observed_at":"2026-08-09T00:13:45.571808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.520593Z","title":"Distributed networked learning with correlated data","venue":null,"work_id":"66aeec02-208a-43c2-b114-b6f27b412a81","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.461883Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:91bcaec2409c05cf248f2e5fac974ea1c7881663458d4e02e3a97c811616efec","observation_id":"19dbe7b7-d585-400c-a002-24bf6b055280","resolution":{"observed_at":"2026-08-09T00:13:45.557618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.428288Z","title":"Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization","venue":null,"work_id":"12e3f1de-8557-48b3-8417-c2d2992b8614","year":2016},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.466284Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:f3fa65386deca240d9eeb9e8497c1caf6f5643f0c85b2ad9dc2774593e035b17","observation_id":"c4bcddcd-fa26-486c-8edd-daf268c4ff3b","resolution":{"observed_at":"2026-08-09T00:13:45.466054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.319867Z","title":"Linear convergence of gradient and proximal-gradient methods under the Polyak- Lojasiewicz condition","venue":null,"work_id":"5105cbc7-6499-4b80-9b68-ff959cea8d94","year":2016},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.470615Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:ada04bc6b47568c4b35c9bb71bd72ee7e7cd5d50418a767132014d935146c7a1","observation_id":"ce9b5f3b-169e-4332-b741-382b13416b7a","resolution":{"observed_at":"2026-08-09T00:13:45.354285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03606","last_updated":"2021-06-08T08:14:57Z","snapshot_observed_at":"2026-08-10T13:39:15.908251Z","submitted_at":"2020-08-08T21:55:07Z","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03606","snapshot_observed_at":"2026-08-09T00:13:44.474773Z","title":"Mime: Mimicking centralized stochastic algorithms in federated learning","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.474773Z"},"links":{"cited_paper":"/paper/2008.03606","citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:ae6978487a95330d8a39d119cce4188fa87b28b80ededb0477955e829c9d8d73","observation_id":"508eb73e-2bc2-47fa-87f1-34c61b29b067","resolution":{"observed_at":"2026-08-09T00:13:44.474773Z","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":"2026-08-09T00:13:45.297382Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":"e0c38726-28c1-4b11-ab18-d171dbe7cc4a","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.479355Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:5ad19096001809ffcc20ed580b128e15eed7422107d0d1cc641d13c1b29727dd","observation_id":"3cba474c-68aa-402c-ac68-228c7e491348","resolution":{"observed_at":"2026-08-09T00:13:45.301635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.283809Z","title":"Understanding notions of stationarity in nonsmooth optimization: A guided tour of various constructions of subdifferential for nonsmooth functions","venue":null,"work_id":"21148b48-0ada-475f-86b0-0bb2b39c587d","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.483460Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:b2f3053319b6c68d829104bf553fcb666cfdd35e566930a4a7c8f20e7c03a546","observation_id":"d287e0cc-5f1a-48cc-b9d2-ee6baf8b64c3","resolution":{"observed_at":"2026-08-09T00:13:45.288299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.270536Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":"5f22d3f9-9654-4f56-802b-15df6e79b03a","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.487362Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:167884ad0f7a1a274d1262d9071f78d0ae518881dc7ff9c9ed19e67abcd65950","observation_id":"971947f8-812d-48d0-8be1-4da76056af6d","resolution":{"observed_at":"2026-08-09T00:13:45.274731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.256950Z","title":"On the convergence of FedAvg on non-iid data","venue":null,"work_id":"92e7235e-a863-43cf-8224-91a504df7244","year":2019},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.491147Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:8671c4ddb96315cc0474b928b1f6629de46932437eab50e4ec4946b7623315d6","observation_id":"df9b9821-6837-4115-8396-11e8f34fc536","resolution":{"observed_at":"2026-08-09T00:13:45.261044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.242826Z","title":"Private non-convex federated learning without a trusted server","venue":null,"work_id":"092b4c50-e166-4025-89db-8a7b908aa8f0","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.495432Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:e1fa92cd02fc33a8777479c6a1cbe8953f0b29a61deef1077615b9ed34d763ac","observation_id":"39c7b3c1-28e4-4ff7-98b7-f63028902ecd","resolution":{"observed_at":"2026-08-09T00:13:45.247646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.500512Z","title":"Error bounds and convergence analysis of feasible descent methods: a general approach","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.500512Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:401447675cd3c640d5846273f660a3d8b0c303856748a0a7362b303b7dfd3924","observation_id":"3d259f7c-3ca0-456d-9d9b-f65d2ed90384","resolution":{"observed_at":"2026-08-09T00:13:44.500512Z","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":"2026-08-09T00:13:45.220481Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":"7c171098-b952-4b9d-aab3-ab22df853825","year":2017},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.505252Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:9cfd07cde3f07628e54b977e923d0033095a86f32fbbf5290aa1682201f2995e","observation_id":"5f60a6ae-d5b4-4b1d-9061-58ac032afcea","resolution":{"observed_at":"2026-08-09T00:13:45.224836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.207149Z","title":"Gradient free cooperative seeking of a moving source","venue":null,"work_id":"024eb9fd-03f4-41d7-ad49-4138109b2c07","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.509964Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:5086c402632140143e92b79bf8ac5628403ec4b8cdff31da6f687150d43ad4a1","observation_id":"1125c4c6-9be6-490b-92e1-f0ddafd287db","resolution":{"observed_at":"2026-08-09T00:13:45.211563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.193381Z","title":"Primal-dual subgradient methods for convex problems","venue":null,"work_id":"78dfb2f2-0506-4b96-89ae-d4d84c432116","year":2009},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.513817Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:e9c6dad23c4687d05e1987453d9afcecadd0306a8df0836b3750d2ed0b72d4c6","observation_id":"00b07d0a-cedc-47a7-bc87-40840df2ded2","resolution":{"observed_at":"2026-08-09T00:13:45.198144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.177446Z","title":"Differentially private federated learning on heterogeneous data","venue":null,"work_id":"58f9f595-73f9-4090-9539-9d65a6437a6f","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.518042Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:3761401c85cd509431a9f94a49530e08b327dfd5234a4d45782aa688f536320c","observation_id":"a98d0910-2f4c-479e-b198-5824c420dd92","resolution":{"observed_at":"2026-08-09T00:13:45.182916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.160788Z","title":"FedSplit: An algorithmic framework for fast federated optimization","venue":null,"work_id":"57fd208d-9f63-4dfd-8a34-b24a31b6a9d3","year":2020},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.522390Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:e4077a02f2c3445ec77900c4eaf09f0e5e7dd2bbde975e1f43a8a0062bf88956","observation_id":"3ffb3126-e0e5-4ba9-90d0-f0f50997712e","resolution":{"observed_at":"2026-08-09T00:13:45.165644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.094599Z","title":"Local SGD converges fast and communicates little","venue":null,"work_id":"5805c68d-e7f3-4899-854e-66f2f90117ce","year":2018},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.526867Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:74b5475fae7a4e136e97b544b56bc7d8f0d96f7f9ee5490df18f397ea0a68757","observation_id":"450285ef-c433-43f2-af04-00220ebc4447","resolution":{"observed_at":"2026-08-09T00:13:45.130040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:45.015868Z","title":"FedDR–randomized Douglas-Rachford splitting algorithms for nonconvex federated composite optimization","venue":null,"work_id":"899988a6-cd1e-464c-b9fe-be2e4a6778d0","year":2021},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.531108Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:8f5d62ea3f48bd01421aa9c9f116ec7fdfae092338a03132d8cdbf21203bd710","observation_id":"69a438fe-33dc-4d34-a87e-7b5a78be1c57","resolution":{"observed_at":"2026-08-09T00:13:45.052239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.931740Z","title":"FedADMM: A federated primal-dual algorithm allowing partial participation","venue":null,"work_id":"5d2faa9b-1299-4abd-a41a-d868265965c3","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.535076Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:bf0eefaadf2e6045b5b8472b58c8ccfa22dafd4bae0843d5855e689939bec28b","observation_id":"b6bdb73c-d54e-461b-bf58-5a58d72874f2","resolution":{"observed_at":"2026-08-09T00:13:44.972740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.917687Z","title":"Decentralized nonconvex optimization with guaranteed privacy and accuracy","venue":null,"work_id":"c717eb28-e009-457c-9e0e-bc3fa4fcc068","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.538961Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:0d96837db735683e1847533ebcf5f6ba3015d528ea5b7e9e477ba3f18dfb97e5","observation_id":"600ea79b-8ff4-4d73-ad8e-ac93ce49ae9f","resolution":{"observed_at":"2026-08-09T00:13:44.922667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.543212Z","title":"On stochastic gradient and subgradient methods with adaptive steplength sequences","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.543212Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:c1da1d9a1772eeb7ad7019bf9f4021f328da444e79813f13e4c664ff6e9e7d0a","observation_id":"bc41d7a9-e468-49ff-9812-d8657b02de01","resolution":{"observed_at":"2026-08-09T00:13:44.543212Z","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":"2026-08-09T00:13:44.894447Z","title":"Federated composite optimization","venue":null,"work_id":"f327c2c4-1561-4374-ba20-2baad3eee80e","year":2021},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.547410Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:e556f179cbdf45a2783a81160f88930398a2fa487652cd01b4d53b8fc83c966c","observation_id":"2a9be6b5-d13f-49fd-b150-b4c29d04535b","resolution":{"observed_at":"2026-08-09T00:13:44.899341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.880476Z","title":"On convergence of FedProx: Local dissimilarity invariant bounds, non-smoothness and beyond","venue":null,"work_id":"53b144b6-4158-49b7-a612-fda3af613a41","year":2022},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.551407Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:2cca3b5f9905b4bf4b1fe11822af49d8497edff1fc99405a78bd67c518c6e364","observation_id":"209f087d-6c86-43d8-852e-92a1a622fb4b","resolution":{"observed_at":"2026-08-09T00:13:44.884765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.866507Z","title":"A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo–Tseng error bound property","venue":null,"work_id":"d9258166-84d7-4ed4-85d8-fb3909f810f4","year":2019},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.554913Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:8862b303b287065fd802182d47bf6d14313dd9cb0e5c6ead66ff9807d757cd51","observation_id":"a42a7844-26da-4314-a8ce-1b3d6a322e6f","resolution":{"observed_at":"2026-08-09T00:13:44.871029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.852736Z","title":"Secure and decentralized federated learning framework with non-iid data based on blockchain","venue":null,"work_id":"d896e6f9-854a-4730-bd42-10af6bf54eca","year":2024},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.591822Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:152c0b48ed820a096c8d15b63f7d25b839acb73d5a0ea5e6e67acefb3f63f7a5","observation_id":"edb25e29-0be7-440d-9841-3674abc0d2f2","resolution":{"observed_at":"2026-08-09T00:13:44.857205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01795","last_updated":"2023-09-04T20:22:57Z","snapshot_observed_at":"2026-08-13T10:20:34.767177Z","submitted_at":"2023-09-04T20:22:57Z","title":"Composite federated learning with heterogeneous data","version":1},"cited_work":{"arxiv_id":"2309.01795","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.01795","snapshot_observed_at":"2026-08-09T00:13:44.791164Z","title":"Composite federated learning with heterogeneous data","venue":"cs.LG","work_id":"170fe0bd-d75d-478d-a1c5-052b73474df8","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.643543Z"},"links":{"cited_paper":"/paper/2309.01795","citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:eec0b646d898775db216c970fd8757e03270d3eb0409a5d301d3a405a92190ba","observation_id":"0cdffba4-1911-43c5-8dab-b18ef72019b7","resolution":{"observed_at":"2026-08-09T00:13:44.797770Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.838940Z","title":"Fedaudio: A federated learning benchmark for audio tasks","venue":null,"work_id":"395d04a1-e666-4617-8702-efd27dc9f0fc","year":2023},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.678813Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:a774d7547dc8047f3fa1eab45dcf907e74da800b8c7e4435a98ac427998351de","observation_id":"79ca0553-7448-47a1-8bf6-7a6c78fa8014","resolution":{"observed_at":"2026-08-09T00:13:44.843402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-09T00:13:44.823907Z","title":"FedPD: A federated learning framework with adaptivity to non-iid data","venue":null,"work_id":"b04f3b02-9ccf-4c56-81f6-865d1f77e39b","year":2021},"citing_paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T00:13:44.715349Z"},"links":{"citing_paper":"/paper/2502.03958"},"observation_digest":"sha256:05d39779c8219f73c1613deaf6f2d4d014abee3f4a759b373de9561e04c7f728","observation_id":"038bfac5-927b-4d0c-b6d6-4cb69464c6ae","resolution":{"observed_at":"2026-08-09T00:13:44.829429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03958","last_updated":"2025-02-06T10:49:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T03:17:00.881975Z","submitted_at":"2025-02-06T10:49:03Z","title":"Non-convex composite federated learning with heterogeneous data"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":1,"verified_fuzzy":29},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2502.03958."}