{"as_of":"2026-08-10T14:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:259efdddd88af901dc11165afb963b826c5329b18184217499d226728c6f0fc3","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T19:44:17.278048Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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":"2026-07-02T19:44:47.733008Z","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":"2026-07-02T19:47:18.784816Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"cited_work":{"arxiv_id":"2603.01730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.01730","snapshot_observed_at":"2026-07-07T03:18:54.296089Z","title":"arXiv preprint arXiv:2603.01730 , year =","venue":null,"work_id":"7f34d355-e789-49d1-9e07-feca9d2a9df1","year":null},"citing_paper":{"arxiv_id":"2607.00173","last_updated":"2026-06-30T20:47:33Z","snapshot_observed_at":"2026-07-29T22:16:43.770651Z","submitted_at":"2026-06-30T20:47:33Z","title":"TallyTrain: Communication-Efficient Federated Distillation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-02T19:44:47.733008Z"},"links":{"cited_paper":"/paper/2603.01730","citing_paper":"/paper/2607.00173"},"observation_digest":"sha256:fe965341ac38949d29313f13e70f76c53df1e676d2727c7683cc6975a38312fb","observation_id":"42b2c74a-bae9-4e82-bb26-2bd2f91b8fa4","resolution":{"observed_at":"2026-07-07T03:18:54.296089Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2603.01730/citation-record","integrity":"/paper/2603.01730/integrity","json":"/paper/2603.01730/citation-record.json","paper":"/paper/2603.01730"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.418108Z","title":"Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.418108Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e7f7b6031ba07531f4e3b542fa623385a0751b3496e58c7dbc1a8e82c7659dd6","observation_id":"e317d730-dc85-47cb-841a-0fe3c19d3b64","resolution":{"observed_at":"2026-08-02T19:44:10.418108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.489745Z","title":"Decentralized federated learning: A survey on security and privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.489745Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:278d80bf7acba168500e80a1253d532d801a3bf83609e8895cb762b1ea9ba92a","observation_id":"d71a689e-aff2-4d24-bcc8-d6e3c8b7345f","resolution":{"observed_at":"2026-08-02T19:44:10.489745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.616031Z","title":"An innovative decentralized and distributed deep learning framework for predictive maintenance in the industrial internet of things,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.616031Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:93d82262bfc01589fc395d68528eab6ef61f7ad5a32d0cbc536b28d8fa431458","observation_id":"846bf843-a398-472e-8358-930fa7aefe99","resolution":{"observed_at":"2026-08-02T19:44:10.616031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.722461Z","title":"Decentralized navigation with heterogeneous federated reinforcement learning for uav- enabled mobile edge computing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.722461Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:10242ca0edcd3dbaf286e722db0e95144677bdd9b50f6977fa8c57d8a7113027","observation_id":"fe432c74-6201-4022-acb9-aa52cc109df4","resolution":{"observed_at":"2026-08-02T19:44:10.722461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.818316Z","title":"Federated learning-based energy fore- casting and trading platform for decentralized renewable energy markets,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.818316Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b72fdb684175073a0f69f99f18f0b9d4d37676f21551c689513396712bdb4a20","observation_id":"0e5faf2f-83d2-4131-b6d0-09b93103bebe","resolution":{"observed_at":"2026-08-02T19:44:10.818316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:10.923726Z","title":"Federated learning meets blockchain in decentralized data sharing: Healthcare use case,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:10.923726Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e3b6424b5b34711a992a7257778aebbe63a6e354fddb13dde398547876de9010","observation_id":"c41525aa-662b-4921-b44e-44d14ba71d19","resolution":{"observed_at":"2026-08-02T19:44:10.923726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.041923Z","title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.041923Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:196d71f5986d51644fe1fa6e6230fb567b5d12320aa12201f7229109c701a4e0","observation_id":"fbd0efca-23d6-404c-8f07-2b387cdb5bda","resolution":{"observed_at":"2026-08-02T19:44:11.041923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.106571Z","title":"Improving the model consistency of decentral- ized federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.106571Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:6a6f92e3f8b02d5801a1e2736f9bd8b0e4137ae2c97eb58d2ea473c22e1fd901","observation_id":"5afbc594-5f1c-4494-a792-78ee9a64692c","resolution":{"observed_at":"2026-08-02T19:44:11.106571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.161354Z","title":"Topology-aware generalization of decentralized sgd,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.161354Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:3b7790c01dd4f1b210862c1463f8228c40ff26ae5fc8397ef276c0f1362acc4c","observation_id":"4340a924-59b7-48cb-9f29-d33f2b678e88","resolution":{"observed_at":"2026-08-02T19:44:11.161354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.263845Z","title":"Decentralized optimiza- tion with edge sampling,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.263845Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:73815cee606ab9f6033bb2c60c23d9f53128213a344d000590aa4873fa182159","observation_id":"227b8c1e-1bfd-4142-bfd2-122873bfe284","resolution":{"observed_at":"2026-08-02T19:44:11.263845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.338929Z","title":"De V os, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.338929Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:8c7486712872f941b6e638444627b9be21cedbf1629cc14a64a2e4d4f72ffbc6","observation_id":"2e081d8a-c13e-4aef-ab90-a36f6f9d27d1","resolution":{"observed_at":"2026-08-02T19:44:11.338929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04460","last_updated":"2024-07-05T12:10:54Z","snapshot_observed_at":"2026-07-06T18:41:57.207738Z","submitted_at":"2024-07-05T12:10:54Z","title":"Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04460","snapshot_observed_at":"2026-08-02T19:44:11.431561Z","title":"Smart sam- pling: Helping from friendly neighbors for decentralized federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.431561Z"},"links":{"cited_paper":"/paper/2407.04460","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:d21979bf1736d9a8f9c59e7303aec6231a49471abbaac1ed12cda617fdb0eec3","observation_id":"a2e9a098-82b5-4599-b2a1-21dfed5009a8","resolution":{"observed_at":"2026-08-02T19:44:11.431561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.502705Z","title":"Personalized decentralized federated learning: A privacy-enhanced and byzantine-resilient approach,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.502705Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:79a4c1d7daa3d70234564120d4f9395a6473b85d9c0d037fa0a7fa26b89fdd2a","observation_id":"fee3b85f-ee23-447a-815b-6590546d16d8","resolution":{"observed_at":"2026-08-02T19:44:11.502705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.609249Z","title":"Distributed subgradient methods for multi-agent optimization,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.609249Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:4100db5feb74b2561f669e3493222a9fab8dbedb05f3884c0720facdabe45cb1","observation_id":"44bd6a92-fbe4-4ea5-bf9c-a895109d4180","resolution":{"observed_at":"2026-08-02T19:44:11.609249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.705029Z","title":"Com- munication compression for decentralized training,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.705029Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:436c598cac025bb3b871314de340013ca486b103b3992570c17b4dacacdf07db","observation_id":"0e93380b-2867-4772-9116-ce1d12c661e4","resolution":{"observed_at":"2026-08-02T19:44:11.705029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.846193Z","title":"The convergence of spar- sified gradient methods,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.846193Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b628fa14b08dba4bf940fc7910e54125d9061b73129b7e85a01bedef994e0fe0","observation_id":"bb35fc2b-7b3d-4503-9044-00456717a207","resolution":{"observed_at":"2026-08-02T19:44:11.846193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:11.963659Z","title":"Sparse decen- tralized federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:11.963659Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:2cc0d631ec74086ce08dc874dde2acb2f8943178631fd9d52dde7d905afd93d5","observation_id":"d0132d68-9777-418b-82e1-a64869dcbf85","resolution":{"observed_at":"2026-08-02T19:44:11.963659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.116235Z","title":"Decentralized learning with unreliable communications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.116235Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:8cca9be9217bd79be8f7fa1e230207845b7282d2a02acfe60fc44276117dfc69","observation_id":"acf84ca3-5627-4c76-9cda-a39fb841289d","resolution":{"observed_at":"2026-08-02T19:44:12.116235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.212981Z","title":"Decentralized multi-client functional encryption for in- ner product with applications to federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.212981Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b514c772e4c565e8fb535ff1af66db9b33ded6e19d0bb232cce218f2c50de602","observation_id":"64a6e3d2-31c4-489c-ab82-eb5f8165e58d","resolution":{"observed_at":"2026-08-02T19:44:12.212981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.363322Z","title":"Securing decentral- ized federated learning: cryptographic mechanisms for privacy and trust,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.363322Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:074e852ec097865ce9e49a866eca4257ad5d5f8c642e8f5f321c327a65ddf6aa","observation_id":"fdd04d28-4fd7-4aa0-9f0f-44883eafd0f3","resolution":{"observed_at":"2026-08-02T19:44:12.363322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.447568Z","title":"Decentralized nonconvex opti- mization with guaranteed privacy and accuracy,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.447568Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:7935ed09c67fce85e78976243f17f6b57f2fb5c479ff79f4e803b55f4f9c5345","observation_id":"f7110104-433c-413b-943b-967118060ac2","resolution":{"observed_at":"2026-08-02T19:44:12.447568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.516797Z","title":"Differentially private linearized admm algorithm for decentralized nonconvex optimization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.516797Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:0ea62428eff82426dab7dabd6a6671c53191d941bf55c8208c53a09eab9759b4","observation_id":"361f2988-14a1-4e58-b86d-94eba9ee8427","resolution":{"observed_at":"2026-08-02T19:44:12.516797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.550996Z","title":"Dp-norm: Differential privacy primal-dual algorithm for decen- tralized federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.550996Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:d38e7aca73230683556079c1def82bf06f812ed7f1c477eabe383d701ec5e544","observation_id":"2624b4ed-b919-431a-9a7c-f327a7a81cf0","resolution":{"observed_at":"2026-08-02T19:44:12.550996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.618024Z","title":"Federated learning via inexact admm,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.618024Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:bafbc3e4de2e66b3fe66c41bd0a330468538051b93d49e1edbf6e80e4e9db791","observation_id":"94778d74-2ee5-44a6-bf90-13a622de9f44","resolution":{"observed_at":"2026-08-02T19:44:12.618024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.714632Z","title":"Decentralized federated averaging,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.714632Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b36035d6d99233f82b71808340b371557ca743f8bc023ac6d07f34e1fc2ef6a5","observation_id":"f6440328-ffe3-4b4d-a2f3-7e31e97b0808","resolution":{"observed_at":"2026-08-02T19:44:12.714632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.786151Z","title":"Decentralized feder- ated learning: Balancing communication and computing costs,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.786151Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:5fb9b219f571ddd073559df657b74c264308d956e604e70fcaf084fcc1218f37","observation_id":"98a6c711-a798-49b2-b074-1d4300390a66","resolution":{"observed_at":"2026-08-02T19:44:12.786151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.844298Z","title":"De- centralized deep learning with arbitrary communication compression,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.844298Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:c9698837e11a5d1c3a9cc6920bf65fe8a97017a8eaec1fc8c985d637ec4e466a","observation_id":"29c7e558-67e5-4842-aaec-f5c8fab44104","resolution":{"observed_at":"2026-08-02T19:44:12.844298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.908459Z","title":"Squarm- sgd: Communication-efficient momentum sgd for decen- tralized optimization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.908459Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:cdce968412e8138a3a38f7b665d27949dd8993e042c60f2172cac6c549dbb657","observation_id":"304b8965-43b8-477c-af3c-49e83ecf9e61","resolution":{"observed_at":"2026-08-02T19:44:12.908459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:12.974697Z","title":"Beer: Fasto(1/t)rate for decentralized nonconvex optimiza- tion with communication compression,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:12.974697Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:419aab27d8f830f5041b5f4058120dd214062d6749c985900f1ee0ba91392c54","observation_id":"71222f06-90fd-4d96-8520-34721017bb3c","resolution":{"observed_at":"2026-08-02T19:44:12.974697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.073574Z","title":"Decentralized sum-of- nonconvex optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.073574Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:7a174bf675856afe85fe264257098b4a6ea226f85e8173afd84a017fa95c3118","observation_id":"1110c756-9885-449c-b1b5-d39b9bfbdcc0","resolution":{"observed_at":"2026-08-02T19:44:13.073574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.156569Z","title":"A decentralized proximal- gradient method with network independent step-sizes and separated convergence rates,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.156569Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e85431a852aab7c8753aa15279ebddc03e52766e2cde4a915fe3c551b73cc346","observation_id":"eabae8b9-e2db-4274-a8c3-87c50490e754","resolution":{"observed_at":"2026-08-02T19:44:13.156569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.221766Z","title":"Finite-bit quantization for distributed algorithms with linear con- vergence,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.221766Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:dcc83147c504e16548dfa7d4165190ef52e2e292f7cc546049e2a00482bf0644","observation_id":"39ba6f39-08df-4b37-9c3b-65a2e18d5935","resolution":{"observed_at":"2026-08-02T19:44:13.221766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.321436Z","title":"Private and communication-efficient edge learning: A sparse differ- ential gaussian-masking distributed sgd approach,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.321436Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:1a5be388f0fccabd16ee2f2804fe6b92c1435ef50d07d94d4b0fdcdeec32a669","observation_id":"63a44a53-a2f4-402d-b4a5-c714b2c35988","resolution":{"observed_at":"2026-08-02T19:44:13.321436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.378804Z","title":"Federated learning with sparsified model perturbation: Improving accuracy under client-level differential privacy,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.378804Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:de5e9c54fd2313b517a2625c2e23183adcadb3656a9f21c10e1a87a20b94023b","observation_id":"1c5b90d1-6125-426d-832f-6aaad24d8921","resolution":{"observed_at":"2026-08-02T19:44:13.378804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07708","last_updated":"2026-07-31T12:22:01Z","snapshot_observed_at":"2026-08-05T23:09:17.473397Z","submitted_at":"2024-05-13T12:52:58Z","title":"Communication-Efficient Secure Aggregation in Decentralized Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07708","snapshot_observed_at":"2026-08-02T19:44:13.483395Z","title":"Secure aggregation meets spar- sification in decentralized learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.483395Z"},"links":{"cited_paper":"/paper/2405.07708","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:fba0a368d169cedc76f313099b84bfd19e42b0407132070f2df56ae258232d35","observation_id":"f72c6d89-e6d7-4d8a-9583-1990487e4095","resolution":{"observed_at":"2026-08-02T19:44:13.483395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.571358Z","title":"Numerical optimization,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.571358Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:f012e829c47e95920fcae439f8d4988da5159ad83bf7cba1fb0b10124228ec2a","observation_id":"319a436d-7a04-4b57-95df-b5b192e12852","resolution":{"observed_at":"2026-08-02T19:44:13.571358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.08326","last_updated":"2020-02-18T15:04:38Z","snapshot_observed_at":"2026-08-10T00:59:37.461571Z","submitted_at":"2016-09-27T09:22:03Z","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.08326","snapshot_observed_at":"2026-08-02T19:44:13.735205Z","title":"Asynchronous stochastic gradient descent with delay compensation for distributed deep learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.735205Z"},"links":{"cited_paper":"/paper/1609.08326","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:35aeaecf662439a4dceb57c39ad3013e95e7d6561ba8e3e41ad499b260ff13f8","observation_id":"5344d6cd-06ea-42b2-b472-d010634e1085","resolution":{"observed_at":"2026-08-02T19:44:13.735205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:13.864880Z","title":"Parallel restarted sgd with faster convergence and less communication: Demystify- ing why model averaging works for deep learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:13.864880Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:667fbf2085fd63785be3a8a1f3a05117b18126dabf2a6a6760bd9f25360a5982","observation_id":"60d1e45d-4a15-4326-8bba-459faee91731","resolution":{"observed_at":"2026-08-02T19:44:13.864880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.060519Z","title":"Cooperative sgd: A unified framework for the design and analysis of local-update sgd algorithms,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.060519Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:2000bc875a2d8d58975515f08a163ca7308fc650b116c0cfb9bf6322c7321c2a","observation_id":"e40e6986-627a-4445-9258-6a7db098ba00","resolution":{"observed_at":"2026-08-02T19:44:14.060519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.181024Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.181024Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:1d60effbc44cd4b6a2132572dec63616a26544ee665858f3daeb1968934c7f85","observation_id":"ee6d1cc0-115e-4293-856f-55720fcfaa93","resolution":{"observed_at":"2026-08-02T19:44:14.181024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02189","last_updated":"2020-06-25T06:45:52Z","snapshot_observed_at":"2026-08-06T15:26:37.394053Z","submitted_at":"2019-07-04T02:04:56Z","title":"On the Convergence of FedAvg on Non-IID Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02189","snapshot_observed_at":"2026-08-02T19:44:14.314881Z","title":"On the convergence of fedavg on non-iid data,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.314881Z"},"links":{"cited_paper":"/paper/1907.02189","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:010f24a89747088bc26d0b04ef863ff5c9c046785c9cd4732dcb2fa2bf299d42","observation_id":"ad3bd8f1-5e8d-41e9-9ed5-6780b3adddfd","resolution":{"observed_at":"2026-08-02T19:44:14.314881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.432735Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.432735Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:89e3d7f7e1ab1a30379478c640a0e389854c22aa65d299a73a9a94d3fe59bf79","observation_id":"800f2dfe-690f-4e0e-a2a9-bd5b74ed2c30","resolution":{"observed_at":"2026-08-02T19:44:14.432735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.561578Z","title":"Fedgia: An efficient hybrid algorithm for federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.561578Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:9898cf6c23566803f8cfdbbc00ae48ad0c9e00dc45ee9b7bb757dd535047aae9","observation_id":"70d04a0f-a8d4-47b3-8d2d-bf9b23b43ecf","resolution":{"observed_at":"2026-08-02T19:44:14.561578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.697937Z","title":"The sparse vector technique, revisited,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.697937Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:9df286fffba1df9c4522dab5b2d525bc5dc7eeb7be2e184eca3d75b560cc1165","observation_id":"cf4f2841-1ac9-411e-80cf-ab2156e68a21","resolution":{"observed_at":"2026-08-02T19:44:14.697937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:14.814181Z","title":"Improving sparse vector tech- nique with renyi differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:14.814181Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:1086709db56785b790ed8ecf06a6230b3536649775a6fc719c13051247eb2ff7","observation_id":"294daf0e-c19b-48c9-a71c-5d2c865687bc","resolution":{"observed_at":"2026-08-02T19:44:14.814181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.008735Z","title":"Secure federated averaging algorithm with differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.008735Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:d0bd9adec42d505e2be11d1a2263f711dde875cf6e4d51161c0d4c2b7f065964","observation_id":"a6c94fa2-8306-4b37-90a6-1247c5842f47","resolution":{"observed_at":"2026-08-02T19:44:15.008735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.12284","last_updated":"2022-04-26T13:10:37Z","snapshot_observed_at":"2026-08-03T06:37:04.994748Z","submitted_at":"2022-04-26T13:10:37Z","title":"Federated Stochastic Primal-dual Learning with Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.12284","snapshot_observed_at":"2026-08-02T19:44:15.177413Z","title":"Federated stochastic primal-dual learning with differential privacy,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.177413Z"},"links":{"cited_paper":"/paper/2204.12284","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:17cae3f7d73815d32485ab480f093fd1fdd3bcb4689872a95d19f55fb67730ae","observation_id":"ad5e005d-8525-446e-b767-a0ba58e55ab3","resolution":{"observed_at":"2026-08-02T19:44:15.177413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-02T19:44:15.320107Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.320107Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:2e9b071ef4d0c89063fa7252e6799e538f23acc62b8675ac494825622487118a","observation_id":"c89e36ad-1808-4ff5-8bdc-0fca144ac977","resolution":{"observed_at":"2026-08-02T19:44:15.320107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.488134Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.488134Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:139b3bfb41d24ae98ca8f982eebdcbad9be1109182f09f58ee335c449074bd87","observation_id":"ff3b4b19-4113-4434-9224-e135f745f058","resolution":{"observed_at":"2026-08-02T19:44:15.488134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.635415Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.635415Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:9ecb58b3f166189b710f67519124fe3f632ef640d443842be49a14e8b6d43b39","observation_id":"b02239fb-fa11-4900-b9e3-d2cc7c8022b8","resolution":{"observed_at":"2026-08-02T19:44:15.635415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.736620Z","title":"This is adopted for analytical convenience without loss of generality","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.736620Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:c675cebce241ee9799852350ba20c3a552ee33c6a827156628e40a5a94f0e136","observation_id":"55366b6d-5c09-4016-84ce-af9eeb8c26bc","resolution":{"observed_at":"2026-08-02T19:44:15.736620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.871601Z","title":"That is, at every iteration, nodeiselects the same number of neighbor nodes to join in the training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.871601Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e55a3a4350b75cdd54af363eff2488b7124030ff034aa04c7702b566210f1aa6","observation_id":"ab17072d-bd76-40af-adf2-821e5fa38ca6","resolution":{"observed_at":"2026-08-02T19:44:15.871601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:15.989933Z","title":"Again, this is adopted for analytical convenience without loss of generality","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:15.989933Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e1cc2ace34978a5deccb88624434e3a4ca5de433d316d96aead630de9f212260","observation_id":"9836d4c0-ad13-4844-b730-ec1807e673c8","resolution":{"observed_at":"2026-08-02T19:44:15.989933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.158492Z","title":"wk iℓ − 1 r X j∈N k i,ℓ wk jℓ !2 λk i,ℓ =r # +P(λ k i,ℓ = 0)E h (wk iℓ −w k iℓ)2 λk i,ℓ = 0 i = tiX r=1 P(λk i,ℓ =r)E","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.158492Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b2a10106cbd5760af55a1e5fa0fedceaf779457574fef4072aa303c3d96f5659","observation_id":"0dcc4eff-5f34-4424-a07a-931750f19c7c","resolution":{"observed_at":"2026-08-02T19:44:16.158492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.307389Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.307389Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:4e3e45bbb29145ade9a02b8ed3bd927095e6499dca36ff67ac2af324fd1ec028","observation_id":"1ec003d7-8810-4f7e-99be-5438e2d79fc0","resolution":{"observed_at":"2026-08-02T19:44:16.307389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.444253Z","title":"Proof.Since 1) has been shown in Lemma 3, we only prove 2)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.444253Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:bb79c1afa9e8a57ec2083bba209e9c6c3d985b5d29ce5504f9fbebe3e1d38af8","observation_id":"69fd5488-e515-4f53-94e7-6e9c881531b6","resolution":{"observed_at":"2026-08-02T19:44:16.444253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.583610Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.583610Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:f40fba497090a6691c062124e35d866ffdaa489495804e6249b16702614f832c","observation_id":"4002e7f2-c091-41a9-b914-653aeccc28ff","resolution":{"observed_at":"2026-08-02T19:44:16.583610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.671674Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.671674Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:6ba876ae5a3c023d64426fffb6ee8bfeabb83ffb56d487c0ba60ceb53ced05f8","observation_id":"d2728ad6-2197-451f-8e24-ab5edc567075","resolution":{"observed_at":"2026-08-02T19:44:16.671674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.752234Z","title":"Proof.1) By the triangle inequality and Cauchy-Schwarz: ∥Ewk+1 −Ew k∥ ≤E∥wk+1 −w k∥ ≤ q E∥wk+1 −w k∥2 ≤ c γk/2","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.752234Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:170c5e9f085eb74e6986beeb3dde7f832bd072227ef4f6302c71c582958f6f1b","observation_id":"a8fd5d4a-8a5f-4608-96dd-0ac4df236f9e","resolution":{"observed_at":"2026-08-02T19:44:16.752234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.836477Z","title":"This implies that there is a constantc >0such that |f(w k)−f(w ∞)| ≤c∥wk −w ∞∥","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.836477Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b5dc7fe3f164b321376621cc976be834377cd82f331dfa73a99dfebd0e19ba29","observation_id":"1c0c8556-5887-4ea9-b2c0-f5e879c438f7","resolution":{"observed_at":"2026-08-02T19:44:16.836477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:16.918147Z","title":"We first showlim N→∞ ∆N = 0","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:16.918147Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:4c7495c0043eeb1627be9b3203e16c4e847ec9113a841ae881aafc9e92faa6fa","observation_id":"a97cb2a7-caa5-4d6d-a14e-a5f0f747549f","resolution":{"observed_at":"2026-08-02T19:44:16.918147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:17.031119Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:17.031119Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:b14389613b09144bf5b3bdf8421758a638be8e3013c086edc1acecd3704951cc","observation_id":"c65d6cd7-3f14-4568-bd50-8f784f7286f5","resolution":{"observed_at":"2026-08-02T19:44:17.031119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:17.093131Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:17.093131Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e623b496a739f443c04e1ab082ae0842cafcd94ce5ed366db525f78b4d9ff847","observation_id":"1ef97ead-80c7-46f7-badd-350516c3e562","resolution":{"observed_at":"2026-08-02T19:44:17.093131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:17.148277Z","title":"Proof.1) From (75) and (74), sequence{ eH k}is non-increasing and bounded from below","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:17.148277Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e650ab31c1dab06d7386a510aefd84ca9199e74e2b46adc8e682e1ad7d4e1904","observation_id":"d9180cca-c463-4718-9698-2c356009f791","resolution":{"observed_at":"2026-08-02T19:44:17.148277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:17.216349Z","title":"It is easy to checkϖ k ∈N(2δ) for allk≥0","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:17.216349Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:e703e935159fa3b699800a85423c70df4de5db81672d8041f62fac6d9e9c2b53","observation_id":"24b0aa7e-2471-494c-a7c4-de3a5518fa6a","resolution":{"observed_at":"2026-08-02T19:44:17.216349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:44:17.278048Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-02T19:44:17.278048Z"},"links":{"citing_paper":"/paper/2603.01730"},"observation_digest":"sha256:451ec7c391151e57c04f8bf6ebadb699756c7b6e3a95404fd326cc4ce2012443","observation_id":"88ae75f1-27bf-4814-bcb2-18ed97f10658","resolution":{"observed_at":"2026-08-02T19:44:17.278048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.01730","last_updated":"2026-07-08T10:21:36Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T01:47:37.793326Z","submitted_at":"2026-03-02T10:57:18Z","title":"Decentralized Federated Learning by Partial Message Exchange"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":66,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":66},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 1 inbound Pith citation observation for arXiv:2603.01730."}