{"as_of":"2026-08-22T23:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:24bb8a545e3b32ae458eb378bbffb3287340a78d5437985e3f0b0b766e72cc29","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:45:00.464443Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2504.17520/citation-record","integrity":"/paper/2504.17520/integrity","json":"/paper/2504.17520/citation-record.json","paper":"/paper/2504.17520"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:45:01.202469Z","title":"Differential ly private federated clustering over non-iid data,","venue":null,"work_id":"aea44a47-603f-47f3-963e-d69807ecb868","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.265584Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:e9a63647066e90bc63adfa72c3bfe2f4b3790199d74c1ea76ad5930a0e4d4dd8","observation_id":"3742700b-bb4b-40af-bc28-20379c6550dc","resolution":{"observed_at":"2026-08-16T10:45:01.208403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.185313Z","title":"Distributed Multi-View Sparse V ector Recovery,","venue":null,"work_id":"40083336-7465-41cb-9b5d-6d04ae50f20d","year":2023},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.270761Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:17a5a7a56db0f96dbce85da42e6654d4ffbdc8d420e44ac879438013c102d10f","observation_id":"fe7dfc43-72f2-4a56-9eff-0aa5cd51a56e","resolution":{"observed_at":"2026-08-16T10:45:01.191509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.167536Z","title":"Distributed Learning Over Networks With Graph-Attention-Based Person al- ization,","venue":null,"work_id":"4df02f24-ddb3-4815-bb55-61355e189b96","year":2023},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.275811Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:dc04ce440883f966b4211343050a63a8e1703545f6a1e5776c27bae25690353f","observation_id":"3274f754-4726-40f8-a457-f6f6bd6356e4","resolution":{"observed_at":"2026-08-16T10:45:01.173239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.149907Z","title":"Can decentralized algorithms outperform centrali zed algorithms? A case study for decentralized parallel stocha stic gradient descent,","venue":null,"work_id":"f005a236-ca60-4095-a15d-15ce566852df","year":2017},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.280900Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:398a6110697ccc0b7e3f1ae689a99c14717fe516beb0703751f0a76084f0614d","observation_id":"ac088f78-4439-44e9-ba07-0c4568fddb76","resolution":{"observed_at":"2026-08-16T10:45:01.155300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.133876Z","title":"Personalize d federated learning with theoretical guarantees: A model-a gnostic meta-learning approach,","venue":null,"work_id":"080d4c5f-00a9-4deb-b0ba-9aaa36d17206","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.285833Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:8a0804101eeecd6fe7a74c06dd161d3069cc79e835cb3bf1cca83ce13b939c7a","observation_id":"b89e6cd5-9577-48d9-b098-432b3fceb3f1","resolution":{"observed_at":"2026-08-16T10:45:01.138797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.118071Z","title":"Cluster-driven graph federated learning ov er multiple domains","venue":null,"work_id":"aea27804-1e11-4b52-97bf-3e2f7a04c0b3","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.290661Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:90196292d7944c5e466f558d0d8e7ec2e3ae47284dbf3cee30ec875a5bc160a3","observation_id":"f1f9f144-592d-42e7-836c-e3d1920675bb","resolution":{"observed_at":"2026-08-16T10:45:01.122876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.100683Z","title":"Federated optimization in heterogeneous networ ks,","venue":null,"work_id":"8337199d-e6b9-46f5-97fe-d0626aa4c8ff","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.296406Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:15defdef79780616e83ec01b4660ee5897893504b0fe29381f238ded1520162c","observation_id":"17137210-2274-4a9c-94ff-0e0d885b9733","resolution":{"observed_at":"2026-08-16T10:45:01.105514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.084073Z","title":"An efficie nt framework for clustered federated learning,","venue":null,"work_id":"3bb52734-8466-4111-8180-70a7a63276e2","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.300916Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:d355a7ddefe592f491b1535f51ce9fe57e2e0e6844e43572ecfdf17c77b7c102","observation_id":"3fb22eda-a91e-4bc0-aade-74d627cf5fb6","resolution":{"observed_at":"2026-08-16T10:45:01.089059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.068480Z","title":"Personalized federat ed learning with moreau envelopes,","venue":null,"work_id":"be5771c5-a317-49dc-b91e-12b2b9bc3476","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.306032Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:5e681bcde859289222c6fad6c31314ee0c30bef36908cd196e835fc5a6e48318","observation_id":"f0ad0e70-d28d-480b-b352-740ad0dbe5e1","resolution":{"observed_at":"2026-08-16T10:45:01.073226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.052349Z","title":"Group knowledge transfer: Federated learning of large cnns at the edge,","venue":null,"work_id":"15b7102b-24f5-417d-9f92-145800b8c1b1","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.310833Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:e5c38772132fbe731326591bf8690e0932bbc277c7e25f0c97c47d4817e678ca","observation_id":"49397b03-6b54-4c87-b56f-3c4952181ce4","resolution":{"observed_at":"2026-08-16T10:45:01.057885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.035952Z","title":"Distributed learning of deep ne ural network over multiple agents,","venue":null,"work_id":"13586069-e4e7-420e-ae2d-c341ebb067f8","year":2018},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.315550Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:77176fcf8f4805152a93c6222a3153e9d1d483ecd212da7bc73362ba62483f6c","observation_id":"6ef175f2-aee7-4721-a7bd-73e54f936a27","resolution":{"observed_at":"2026-08-16T10:45:01.041074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01264","last_updated":"2021-12-14T04:20:42Z","snapshot_observed_at":"2026-08-17T15:20:44.171027Z","submitted_at":"2020-10-03T02:55:33Z","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01264","snapshot_observed_at":"2026-08-16T10:45:00.321411Z","title":"Heterofl: Computation a nd communication efficient federated learning for heterogene ous clients,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.321411Z"},"links":{"cited_paper":"/paper/2010.01264","citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:2015b8db091bbcbcb6b311c8dbe28cd20195d9ad2a366d7209510a58c3536185","observation_id":"3a157ca3-0c6d-4c6e-a29f-24816950c5eb","resolution":{"observed_at":"2026-08-16T10:45:00.321411Z","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":"2026-08-16T10:45:01.017730Z","title":"Fjord: Fair and accurate federated lear ning under heterogeneous targets with ordered dropout,","venue":null,"work_id":"8f3c7e84-8a95-42b3-8c0a-72fe8e346cc8","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.326343Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:238104e2e03a40f81a23d589a05f694b083f330ffc2c56ba82b31f677eae9110","observation_id":"cd0a3ef8-6ff5-4fdf-91bc-83cc12bfaabf","resolution":{"observed_at":"2026-08-16T10:45:01.023772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:01.002223Z","title":"Fjord: Fair and accurate federated learning under heterog eneous targets with ordered dropout,","venue":null,"work_id":"b4c7c789-d4b9-47ac-a608-55650206e52b","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.330582Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:5d68c95e5fa090f12af02610a37ec6119acd5bcaf4f4f4038e293d5bff62c9cc","observation_id":"941103fc-ced8-4181-bc1b-3733e2e1ddb3","resolution":{"observed_at":"2026-08-16T10:45:01.007296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03371","last_updated":"2020-08-07T20:45:12Z","snapshot_observed_at":"2026-08-14T20:23:06.504001Z","submitted_at":"2020-08-07T20:45:12Z","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03371","snapshot_observed_at":"2026-08-16T10:45:00.335087Z","title":"Lotteryfl: Personalized and communication-efficient fede rated learning with lottery ticket hypothesis on non-iid dataset s,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.335087Z"},"links":{"cited_paper":"/paper/2008.03371","citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:a75c83776b2bc937497eb62c74f982212fa672069d77b3a832623e9efa5e13e2","observation_id":"5279db65-f9ce-4996-b09c-f2e35b9aef0e","resolution":{"observed_at":"2026-08-16T10:45:00.335087Z","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":"2026-08-16T10:45:00.986044Z","title":null,"venue":null,"work_id":"ce9cae7f-63e9-4739-a7b1-162d73577549","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.339493Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:cf40e8dbef3318d5a63bc6ec4a263e872dcc584cfaade63cf30db692152e4b43","observation_id":"07f76024-bbcd-4b47-9a1e-d24c635e2c1b","resolution":{"observed_at":"2026-08-16T10:45:00.990845Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.970369Z","title":"Model pruning enables efficient federate d learning on edge devices,","venue":null,"work_id":"eead7bb8-6261-4904-9ac5-1635e3a74f8a","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.343979Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:852199610bac9a8b5ace000c3f43f9b5cc49a620b35d71ce1a6614278a9c72e9","observation_id":"069e8770-ad9b-4af1-a50a-01a722d29b19","resolution":{"observed_at":"2026-08-16T10:45:00.975152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.14655","last_updated":"2022-05-26T09:46:40Z","snapshot_observed_at":"2026-08-22T10:15:55.515397Z","submitted_at":"2021-11-29T16:11:09Z","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.14655","snapshot_observed_at":"2026-08-16T10:45:00.348542Z","title":"Fedhm: Efficient federated learning for heterogene ous models via low-rank factorization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.348542Z"},"links":{"cited_paper":"/paper/2111.14655","citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:a2a9614a28d8614c598f651e4533510ab5ed19484f86c5d1931ca30330e7ce6b","observation_id":"a17f1608-40ba-4162-9107-0b1fe15d2106","resolution":{"observed_at":"2026-08-16T10:45:00.348542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.13141","last_updated":"2023-10-10T23:04:48Z","snapshot_observed_at":"2026-08-16T16:36:27.129345Z","submitted_at":"2022-08-28T05:17:03Z","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","version":3},"cited_work":{"arxiv_id":"2208.13141","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.13141","snapshot_observed_at":"2026-08-16T10:45:00.500030Z","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","venue":"cs.LG","work_id":"a4e31fbf-bc26-41e2-b257-401480885f24","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.353458Z"},"links":{"cited_paper":"/paper/2208.13141","citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:b419142d2d09bf7b55b79e2307b399d103a30c4b67c5d480d3494f01467a03ce","observation_id":"f37b6b9d-c8e2-4490-9f7b-8bd0611921d6","resolution":{"observed_at":"2026-08-16T10:45:00.506791Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.955851Z","title":"Resource-adaptive federated learning with all-in-one neural composition,","venue":null,"work_id":"a6a39f61-9a57-482c-8471-44aeaff44e6d","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.358164Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:c3f7170c8fe07298fb39df0327c6becdfeb700c0138c76fcaa5e5f87e131132d","observation_id":"ddd13d3c-bf40-40f4-a663-91f94189b94c","resolution":{"observed_at":"2026-08-16T10:45:00.960625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.940083Z","title":"Fully decent ralized joint learning of personalized models and collaboration gr aphs,","venue":null,"work_id":"584035ec-f934-4780-a4df-59550551b228","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.363291Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:e4b20f12b3c42a4ce7efc586567aab8b11d86050deb4a0a843724eff8c9f2b0d","observation_id":"3f9adcc0-384b-4242-8e99-c602f8c49584","resolution":{"observed_at":"2026-08-16T10:45:00.945072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.922930Z","title":"Enhancing Decentralized and Personalized Federated Learning with To pol- ogy Construction,","venue":null,"work_id":"b0366711-dc11-439d-91fe-9e93e529c6f7","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.368845Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:0622d2820af04efd955e09b95feb400c9a82681af83e7dea32c7f1d09bb0481d","observation_id":"19811ca3-fbaa-45e9-a2e9-f1df90813392","resolution":{"observed_at":"2026-08-16T10:45:00.928098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.904722Z","title":"DePRL: Achiev- ing Linear Convergence Speedup in Personalized Decentrali zed Learning with Shared Representations,","venue":null,"work_id":"024b12e0-d41e-455f-8e48-524fea7e7e6e","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.373713Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:6bdcf637e63cc4242feab8dd2084a10b54c1385ee148c2357817727ff35aa8b5","observation_id":"39800069-ab24-4cb9-a4c5-34f057cf8a1c","resolution":{"observed_at":"2026-08-16T10:45:00.910773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.884872Z","title":"Dispfl: Towards communication-efficient personalized federated learning via de- centralized sparse training,","venue":null,"work_id":"d8288120-2e23-434e-960e-f07f8cd1596c","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.378313Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:89a4631266e83bad589fae62063b4b29acf39f26f657c8a849621f0efc1fe000","observation_id":"3a421bd9-cb9d-409e-a7be-58ee7aad02ce","resolution":{"observed_at":"2026-08-16T10:45:00.889887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.867183Z","title":"Dlion: Decentralized distribu ted deep learning in micro-clouds,","venue":null,"work_id":"04b93a19-d067-4cff-a825-41fc93df9d62","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.382621Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:891190b11ba113bb5e0cb2d272d62b25d9315bb52a0d8746a4643987a6b8ea36","observation_id":"7b1b9699-677f-407f-ae72-d9d8e251b4b2","resolution":{"observed_at":"2026-08-16T10:45:00.872297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.849938Z","title":"Mitigating stragglers i n the decentralized training on heterogeneous clusters,","venue":null,"work_id":"586198df-9311-410a-8917-a9291f279cad","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.387028Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:973a5980851f241d713e7bce3f2f5ce0cfc5698fee8e8fc23a1df2355e82d893","observation_id":"5593758d-f740-4e7f-b04f-a93c80bb34a1","resolution":{"observed_at":"2026-08-16T10:45:00.854746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.835480Z","title":"Federated learni ng via over-the-air computation,","venue":null,"work_id":"04824637-e056-4ba1-a8a5-13c963cce587","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.391551Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:3f4ea4480045acb374b268f6f022f14bd4a328c990fdb94d2efcf313d906f5f4","observation_id":"2018bfa5-93cc-497b-9ae4-59afe35072ba","resolution":{"observed_at":"2026-08-16T10:45:00.839979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.820789Z","title":"Adaptive federated learning in resource constrained edge computing systems,","venue":null,"work_id":"3bfc578a-82a6-4241-b37c-5a92d2832b1a","year":2019},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.396265Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:9da44c1ae7eac484914e0c4428371ba690ad5e39e2eaa65609e7b327d720830f","observation_id":"6cd36656-2829-4be0-8172-aaecca9c7c02","resolution":{"observed_at":"2026-08-16T10:45:00.825384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.804562Z","title":"Communication-efficie nt fed- erated learning based on compressed sensing,","venue":null,"work_id":"a7a0caac-b5c3-4298-a34a-50f435764d0d","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.400738Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:9ce620ea6bdeeb8bac1e07fb7c1ce918e1b0f0b6312f85807b7673a609dc423f","observation_id":"a9f33cd3-d9d6-4465-b9ca-43412bac9280","resolution":{"observed_at":"2026-08-16T10:45:00.809445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.789091Z","title":"Privacy-preserving federated primal-dual learning for n on- convex and non-smooth problems with model sparsification,","venue":null,"work_id":"32649fec-4b23-4ec0-a60e-51625f4c6a58","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.405101Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:b6ac246d0b23f037ca94205de462262331f4f296ed46018e83db9ebc699a5532","observation_id":"746cd140-0f2f-42ba-9007-bace5fcaa61b","resolution":{"observed_at":"2026-08-16T10:45:00.793694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.773255Z","title":"Nonlinear perturbation-based non-convex optimiza tion over time-varying networks,","venue":null,"work_id":"286cf747-fbab-47fa-abad-f7487a49c21f","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.409622Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:32d58197777b7b4d6749b7dab2d0a8a8d7d698414f809114aecdbdb3ac096909","observation_id":"8274d6ff-9566-4aba-92ec-28b6663df62b","resolution":{"observed_at":"2026-08-16T10:45:00.778414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.757758Z","title":"Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learnin g from Distributed Data,","venue":null,"work_id":"20c77fe4-6ffd-417a-b0e2-2109ea6a104f","year":2025},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.414020Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:41a53f24f91b001c708d54dad14172a27a2b7f93adce2b51676109cb1c8b3602","observation_id":"90d7db2e-cce4-4af0-a201-dfd086505022","resolution":{"observed_at":"2026-08-16T10:45:00.762730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.742382Z","title":"Fedmas k: Joint computation and communication-efficient personaliz ed fed- erated learning via heterogeneous masking,","venue":null,"work_id":"9e263735-7067-42a8-9ddb-0ed8bd573188","year":2021},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.418755Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:d408470b1ddeaa802fcf75189546a7fca8969377ac84cd0e91fdfdead27a8ac5","observation_id":"387b255e-1f84-4e73-98e2-fcd05af7d3d6","resolution":{"observed_at":"2026-08-16T10:45:00.747726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.724812Z","title":"A lightweight an d secure deep learning model for privacy-preserving federated lear ning in intelligent enterprises,","venue":null,"work_id":"7d58f9a4-6011-4053-b7e8-f34e6ff6574e","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.423679Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:0fc69cd8e8d3d40dc882b4d896f5ee96e96e9c1a85bc9e13ce295f31bc5e08cf","observation_id":"841d3cd9-6ad3-4601-a20b-67ba7a050bd2","resolution":{"observed_at":"2026-08-16T10:45:00.730032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.709060Z","title":"Decentralized a nd robust privacy-preserving model using blockchain-enabled feder ated deep learning in intelligent enterprises,","venue":null,"work_id":"c8e4829d-6544-4b26-ad3b-de5c2cf845ae","year":2024},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.428257Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:ac23a7fd754333aef34132a17d93244baf908e24be0128c7b2f4758923a45bc3","observation_id":"48d9bc06-4c86-4ca7-a1e1-cd4ac7980fd8","resolution":{"observed_at":"2026-08-16T10:45:00.713847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.692890Z","title":"Deconstructing lottery tickets: Zeros, signs, and the supermask,","venue":null,"work_id":"d54d5d85-454b-4654-9abf-9a5a001a3926","year":2019},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.433254Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:64096f4de5a060fd49701359cf290e307fd8b00b67421630cd8210177545e2d9","observation_id":"d6025daf-ac5e-44c6-a1b4-aae889de0cca","resolution":{"observed_at":"2026-08-16T10:45:00.697904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.676751Z","title":"Proving the lottery ticket hypothesis: Pruning is all you n eed,","venue":null,"work_id":"f9157c66-ec29-403d-81be-4644d0c8fbb0","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.437766Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:a5b8fb0addb0ffd28f9add3e5bc0c4a6a484fd48a9a136e273e6748857dad104","observation_id":"7de2c797-46f5-4215-998c-bfb6beee6b78","resolution":{"observed_at":"2026-08-16T10:45:00.681609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.660059Z","title":"The Lottery Ticket Hypothes is: Finding Sparse, Trainable Neural Networks,","venue":null,"work_id":"be1947a1-5fe0-47e8-903a-2a9790cfe58f","year":2018},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.442241Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:854f2c94557dc26c34a6c43736363b2458378761ac31e051aac7e954fc938854","observation_id":"564dd627-f186-4c80-80b8-3f9ee8c4b5c1","resolution":{"observed_at":"2026-08-16T10:45:00.665584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.642618Z","title":"What’s hidden in a randomly weighted neural network?,","venue":null,"work_id":"81008f67-12c2-4f89-9d7e-b78e5d1d9b22","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.446698Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:a950c2fdf8b21809b4febbd2066051240b553cf66d189b2edaaddfdebaa637cd","observation_id":"d537f98a-0d82-4971-9d20-fdca916d3949","resolution":{"observed_at":"2026-08-16T10:45:00.648506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.624482Z","title":"Optimal lottery tickets via subset sum: Logarit hmic over-parameterization is sufficient,","venue":null,"work_id":"64d21082-0782-4fe5-af69-23c4102fe6a4","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.450980Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:655f38596f6daefa226212b79bae0d26468d790c40ec743975338979fb3ed94d","observation_id":"779a771b-a0f9-4d02-844f-7161053d34a2","resolution":{"observed_at":"2026-08-16T10:45:00.630261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.605775Z","title":"Proving the stro ng lottery ticket hypothesis for convolutional neural networ ks,","venue":null,"work_id":"f9946557-b624-4183-a79f-ef3b28063eb4","year":2022},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.455546Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:256804746e1d176e3c6f9e894f8b77086569a1dad1b1d816f87631c69f2e0db7","observation_id":"33e2125a-2e18-44cb-9710-b7d7a6fda912","resolution":{"observed_at":"2026-08-16T10:45:00.612284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.587405Z","title":"Group sparse regularization for deep neural networks,","venue":null,"work_id":"872a9821-5663-4421-a058-402c6b5777bf","year":2017},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.460034Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:f705fc108e338e7ddabe3ce1bb41c12124ea5d66b1453f62a4fc78adc4dd6c46","observation_id":"0c26851d-6a6b-4ff7-9638-4a2358f1d888","resolution":{"observed_at":"2026-08-16T10:45:00.593098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T10:45:00.570363Z","title":"Hierarchical grou p sparse regularization for deep convolutional neural networks,","venue":null,"work_id":"7f4e44ad-021a-432a-8f90-3fbc1f90c472","year":2020},"citing_paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T10:45:00.464443Z"},"links":{"citing_paper":"/paper/2504.17520"},"observation_digest":"sha256:acd88d91ec39a16d3296fce9933f6e4e2a4c93d2c843b41033bf733a0897357b","observation_id":"03ac337e-e536-4c4d-9724-dd7449860a36","resolution":{"observed_at":"2026-08-16T10:45:00.576408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.17520","last_updated":"2025-04-24T13:02:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-22T10:16:00.361191Z","submitted_at":"2025-04-24T13:02:54Z","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":38},"total_outbound_references":43},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2504.17520."}