{"as_of":"2026-08-22T09:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae995147522ee0c7aba2ddbbd38497635aa1623190d32b362007a931d477a0f0","coverage":[{"denominator":83,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":83,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T11:23:55.713858Z","state":"measured"},{"denominator":83,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":83,"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/2509.02970/citation-record","integrity":"/paper/2509.02970/integrity","json":"/paper/2509.02970/citation-record.json","paper":"/paper/2509.02970"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:23:41.731228Z","title":"Dhillon, and Ufuk Topcu","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:41.731228Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:983f0b55db9227888aab54dd7110b348d687bb695b6387b3b860f66a0111e8fa","observation_id":"b1370a61-a29d-46d0-982a-7811f0c0add4","resolution":{"observed_at":"2026-08-05T11:23:41.731228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03246","last_updated":"2020-10-07T07:58:59Z","snapshot_observed_at":"2026-08-19T04:02:01.097498Z","submitted_at":"2020-10-07T07:58:59Z","title":"Optimal Gradient Compression for Distributed and Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03246","snapshot_observed_at":"2026-08-05T11:23:41.860206Z","title":"Optimal gradient compression for distributed and federated learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:41.860206Z"},"links":{"cited_paper":"/paper/2010.03246","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:8752a6798aa54a994fd01bb193c8780aac908bb7c0b59016f3313b816f906f57","observation_id":"485715b7-4778-4fe2-87bb-c0a67acf76ca","resolution":{"observed_at":"2026-08-05T11:23:41.860206Z","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":"2026-08-05T11:23:42.003701Z","title":"Alghunaim","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.003701Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:d6d745a287d54629546f472943be1aedb6b01931d988818dd5e754db2cec7fc6","observation_id":"0ef25e8a-1175-418d-9571-e87d1678b32f","resolution":{"observed_at":"2026-08-05T11:23:42.003701Z","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":"2026-08-05T11:23:42.103610Z","title":"QSGD: communication-efficient SGD via gradient quantization and encoding","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.103610Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:d19d8207da53fa9c7af824f138e1e407f2e9482ac4fc5240dcf1fde1fbf057a3","observation_id":"e3f345e1-d66c-4327-b5b8-e16dddb8c8c3","resolution":{"observed_at":"2026-08-05T11:23:42.103610Z","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":"2026-08-05T11:24:17.351737Z","title":"Byzantine stochastic gradient descent","venue":null,"work_id":"3a98bb26-f742-4a6e-924b-40b97d645268","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.239421Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:68b7a79526c26f0046e84aef6368d898bc1dda6b7e67b4cdcbd7ed47b5d4637c","observation_id":"a102c3cf-c1f6-423a-a0e7-d7df672ab9fb","resolution":{"observed_at":"2026-08-05T11:24:17.493227Z","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":"2026-08-05T11:24:17.093998Z","title":"Byzantine-resilient non-convex stochastic gradient descent","venue":null,"work_id":"32f03b7e-c4dc-4c6f-bfbe-34b1dda0fb12","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.475944Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:5d5bcd84a3a7b7e2680db1f79eb73a28e2e3dae2667e1ccc400d670966b00927","observation_id":"dc592d0f-b81a-4c98-b9f5-e02e210b07b5","resolution":{"observed_at":"2026-08-05T11:24:17.214599Z","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":"2026-08-05T11:24:16.796577Z","title":"Fixing by mixing: A recipe for optimal byzantine ML under heterogeneity","venue":null,"work_id":"16e3b6ce-9c02-40e8-b6c8-456c300b3717","year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.631526Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:7b08a25ca63662717bacef476a8fa014761ded77028abfdfdef9ce06e76da8bc","observation_id":"577cf430-5e55-40d9-852c-01717d02c355","resolution":{"observed_at":"2026-08-05T11:24:16.941805Z","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":"2026-08-05T11:24:16.627790Z","title":"Byzantine-robust federated learning: Impact of client sub- sampling and local updates","venue":null,"work_id":"dda0575a-bf03-47fe-a777-cca0d777c6e4","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:42.840648Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1db506a3847211a26313b38103e92dc2d32b705fe76886dc2f4cc48f6d7ab70d","observation_id":"0a26988a-48d4-4569-a0d5-8ffcffeecb97","resolution":{"observed_at":"2026-08-05T11:24:16.776825Z","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":"2026-08-05T11:24:16.296242Z","title":"A little is enough: Circumventing defenses for distributed learning","venue":null,"work_id":"6ce9fad4-4bd5-4ea6-aa1a-dd0624ff895c","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:43.053023Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:07b7e297524a6011b7a3be3096c9255b5f406d908df407829df931ad8f1e50ed","observation_id":"8cb45e5a-3e9f-41b9-8c5e-d557ed8d9a14","resolution":{"observed_at":"2026-08-05T11:24:16.460762Z","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":"2026-08-05T11:24:15.958048Z","title":"signsgd with majority vote is communication efficient and fault tolerant","venue":null,"work_id":"8e6d14a9-ef88-4920-8ee7-94b395ffec9d","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:43.213035Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:ae0d5ca85d88641308b35063d670fa6a3476d2107a999534d2024e04997b79c5","observation_id":"81fe7fd3-a964-48e0-b8a9-bbcdfcdcb38e","resolution":{"observed_at":"2026-08-05T11:24:16.124112Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:23:43.623262Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:43.623262Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:3d6e1c00d50b9b6014d0aa80ce57521ce9c15d24332e0518fde307d030a4c5db","observation_id":"f28dd4be-cc77-4e79-b4e8-160b875710f0","resolution":{"observed_at":"2026-08-05T11:23:43.623262Z","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":"2026-08-05T11:24:15.597316Z","title":"Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H","venue":null,"work_id":"1450adf5-71a3-400d-aae5-da26e0d7260f","year":2017},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:43.843993Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:0d61d85722ab1bd48047ea070e24b3649ecae59d164ed020c4c74e6e73137a04","observation_id":"96ced9cb-825e-405f-a740-9427090f734d","resolution":{"observed_at":"2026-08-05T11:24:15.765928Z","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":"2026-08-05T11:24:15.219184Z","title":"Curtis, and Jorge Nocedal","venue":null,"work_id":"663793c3-4d9a-45b4-9179-86316865f46b","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.031054Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:57371fb86862eaf1ca0f3199c8e1642a7a10f3dd813182642084de3b8a1cdfac","observation_id":"1327acbf-9020-44a7-97c0-b6a925e9cd1a","resolution":{"observed_at":"2026-08-05T11:24:15.427094Z","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":"2026-08-05T11:24:14.884890Z","title":"Charles, and Dimitris S","venue":null,"work_id":"cb68a0e0-9d0d-4562-b2b2-90dc978b2e53","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.187520Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:feb507b9d95c96bcb5645810fcc7431996d3c5a4987963393b4b90e5db131887","observation_id":"68d3d23b-1573-4ed6-b3ae-af8497a5a442","resolution":{"observed_at":"2026-08-05T11:24:15.045415Z","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":"2026-08-05T11:24:14.517924Z","title":"Optimal client sampling for federated learning","venue":null,"work_id":"e4237e12-47c8-4bac-ab24-ef230fdd218e","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.353367Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:74d3eed6f5900ab10e181c2d3b9173b10d723411ba311e0db409b561ed5aac3a","observation_id":"d68bc301-7db6-434f-8399-ef0077c6c57c","resolution":{"observed_at":"2026-08-05T11:24:14.731768Z","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":"2026-08-05T11:24:14.143050Z","title":"Momentum benefits non-iid federated learning simply and provably","venue":null,"work_id":"f4b0f79a-61aa-4190-89fe-999454a1ec0a","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.518778Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:74c356d6873af7d68dbde46e637318eb6b3247c26e331b463c2cf06095de0b33","observation_id":"07a2b45d-7ee9-48a6-9a0b-8a5f6f6e42fe","resolution":{"observed_at":"2026-08-05T11:24:14.302888Z","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":"2010.01243","last_updated":"2020-10-03T01:04:17Z","snapshot_observed_at":"2026-08-21T23:56:30.228378Z","submitted_at":"2020-10-03T01:04:17Z","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01243","snapshot_observed_at":"2026-08-05T11:23:44.736995Z","title":"Client selection in federated learning: Con- vergence analysis and power-of-choice selection strategies","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.736995Z"},"links":{"cited_paper":"/paper/2010.01243","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:e77637e1facc9ffefc16090858b855b0436180f6b04023bd54a8b9d339a682d2","observation_id":"f49d9020-f650-4893-a74c-8e7e947e773c","resolution":{"observed_at":"2026-08-05T11:23:44.736995Z","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":"2026-08-05T11:24:13.834415Z","title":null,"venue":null,"work_id":"ab156951-460f-435c-8e99-50d86ace5e10","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.847116Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:28c353f0c492e44136ee0ff9f267a77c7df40ead47a1fe49a332faeb9f4149d7","observation_id":"f159b582-6125-44c5-ae29-a2416feefd46","resolution":{"observed_at":"2026-08-05T11:24:14.000102Z","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":"2026-08-05T11:24:13.536744Z","title":"Fault tolerant ML: efficient meta-aggregation and syn- chronous training","venue":null,"work_id":"3112d61f-ae80-46bc-a2b9-f0a6b1568b98","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:44.989941Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:2b5e11a3aae0a2db882b2badfc67a0763418fd8fef761f023f1e697d788bf475","observation_id":"4b5e03f7-d3f8-4524-8bf0-bbae541cae2d","resolution":{"observed_at":"2026-08-05T11:24:13.681976Z","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":"2026-08-05T11:24:13.214554Z","title":"AGGREGATHOR: byzantine machine learning via robust gradient ag- gregation","venue":null,"work_id":"8bcd3d02-4cc8-4633-b809-8e43de511d5b","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:45.200625Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:7ed1267f6b7504582cc6f47bc42907c5ba4806baa85a7d6deaaa9aa4002ee74d","observation_id":"2c1d23d9-f6fd-4a94-a6ec-9394289f2514","resolution":{"observed_at":"2026-08-05T11:24:13.367407Z","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":"2026-08-05T11:24:12.928324Z","title":null,"venue":null,"work_id":"d4074868-71f6-490d-8d6e-a2ac9f420483","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:45.436807Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:76ef1eecce4f48f735175e43b086e8688898246bb79db9b0a43e53fa086d77d5","observation_id":"ea11b799-8482-4fe7-a0bb-3ab2464b21d6","resolution":{"observed_at":"2026-08-05T11:24:13.060816Z","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":"2026-08-05T11:24:12.575238Z","title":null,"venue":null,"work_id":"5838baf5-6b5d-4edb-9587-72f8bc343998","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:45.593868Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:77b99e6bc001cddaa25f00b4839082ca2f64eb18ee1d98656e7703df3a8c137f","observation_id":"18021cd3-c0d5-4f51-a48d-04e145103ceb","resolution":{"observed_at":"2026-08-05T11:24:12.753647Z","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":"2026-08-05T11:24:12.274277Z","title":null,"venue":null,"work_id":"92724aa3-f11e-4fcb-a822-2f191e71542c","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:45.760131Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:67ad3596a320b35e2ec7b45d11d55f6323d28ea7aa8d7c732c3a95de4c18b7a0","observation_id":"0d066537-10c0-487e-81af-a81321161930","resolution":{"observed_at":"2026-08-05T11:24:12.442187Z","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":"2026-08-05T11:24:11.920068Z","title":"On the ineffectiveness of variance reduced optimization for deep learning","venue":null,"work_id":"a94cb1bd-814c-4cd9-8069-e4d0b66639d2","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:45.927329Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:3e0475d3f934de0788de1303b1a07f3b9a75221c464a3a01582d56b664f1a143","observation_id":"08dec243-6414-4c5d-b073-172a61de58a5","resolution":{"observed_at":"2026-08-05T11:24:12.091894Z","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":"2026-08-05T11:24:11.639966Z","title":"Collaborative learning in the jungle (decentralized, byzantine, heterogeneous, asynchronous and nonconvex learning)","venue":null,"work_id":"c85252a8-be37-49ef-9b6f-0194835ae01a","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:46.117307Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:8a7d0bceabae136f1ae776f35a2fba72d367724863bc570e16ca73e92b3046d6","observation_id":"0ace34bf-0632-4186-a15f-0873e99207bd","resolution":{"observed_at":"2026-08-05T11:24:11.778910Z","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":"2026-08-05T11:24:11.299619Z","title":"Byzantine machine learning made easy by resilient averaging of momentums","venue":null,"work_id":"f90eb62d-eb7f-4a63-aa7a-40855c00eb94","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:46.277264Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:01db0c2ab966887421ecf5bd365a71fcd38d9a4fed554b5289002bdc450536d3","observation_id":"2158c081-d56b-4311-83e3-15452261901d","resolution":{"observed_at":"2026-08-05T11:24:11.460305Z","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":"2026-08-05T11:24:10.936109Z","title":"Momentum provably improves error feedback! In Advances in Neural Information Processing Systems, 2023","venue":null,"work_id":"2ffac9ba-8a49-4a63-8ef9-90e3c6ac261f","year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:46.423119Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1dc0fc01849226c05eaff0b05d34d767ed7f8a53d087676534519cb04c5d939b","observation_id":"1f10bda6-94fa-431e-beaa-74c3b0e80a45","resolution":{"observed_at":"2026-08-05T11:24:11.105566Z","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":"2026-08-05T11:24:10.588905Z","title":"Clustered sampling: Low- variance and improved representativity for clients selection in federated learning","venue":null,"work_id":"31e3e8bd-56c9-4678-a362-a533e520b92a","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:46.662340Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:57ba12c54c98d8acd272dd93fd706933eb65b57e55204ad032da01b84649436f","observation_id":"7a8a3261-8b5a-41c0-9bf1-76ad135bba83","resolution":{"observed_at":"2026-08-05T11:24:10.751357Z","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":"2026-08-05T11:24:10.254213Z","title":"A general theory for client sampling in federated learning","venue":null,"work_id":"715aabd4-04ef-4d25-bc94-e3397256bd39","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:46.875338Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:916cb078d388b5c7655bce2eb81fbc68d90a67a90cc0fe933ba5c057296829a2","observation_id":"25395992-b295-4b02-8ed0-f0356daf0543","resolution":{"observed_at":"2026-08-05T11:24:10.401740Z","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":"2301.11235","last_updated":"2024-03-09T13:28:29Z","snapshot_observed_at":"2026-08-19T11:16:43.629164Z","submitted_at":"2023-01-26T17:18:36Z","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11235","snapshot_observed_at":"2026-08-05T11:23:47.017667Z","title":"Handbook of convergence theorems for (stochastic) gradient methods","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.017667Z"},"links":{"cited_paper":"/paper/2301.11235","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:f8d9edcabbb1d6cd89dbe81d33f9d172c2c8523db6b6dca66dfdd582c22c919f","observation_id":"ec767131-6bda-4a23-a6bb-eae9d86ff5bf","resolution":{"observed_at":"2026-08-05T11:23:47.017667Z","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":"2026-08-05T11:24:09.931574Z","title":"Stochastic first- and zeroth-order methods for nonconvex stochastic programming","venue":null,"work_id":"d0f3b990-d122-4fbe-86cd-2c32b9d84dca","year":2013},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.143735Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:0c0abad3ded8e645a2b11724673c0de9cc286a9725655f39e051250ff0e66038","observation_id":"475b0cf8-3893-4501-ad2b-146b0fbc16ca","resolution":{"observed_at":"2026-08-05T11:24:10.103225Z","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":"2026-08-05T11:24:09.622119Z","title":"Byzfl: Research framework for robust federated learning, 2025","venue":null,"work_id":"b7705bd3-8d1d-4f27-a279-098da3cecf09","year":2025},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.359626Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:e218605d2ae3acf76fa69ca9296dfa2f6a92fd7205a90585ac4a8421647f3cb4","observation_id":"9ec2be07-1d1f-4b5f-91f8-b99493d917da","resolution":{"observed_at":"2026-08-05T11:24:09.789208Z","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":"2026-08-05T11:24:09.297255Z","title":"Variance reduction is an antidote to byzantines: Better rates, weaker assumptions and communication compression as a cherry on the top","venue":null,"work_id":"ed955cc1-43ed-4594-b63f-6d8331fcc800","year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.504253Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:b9578b26dd8829f385495a9e92ab245e3d386d943b5e7606fb1ede5fda732fea","observation_id":"810e1df8-6570-4000-bbd5-316c6d9ae907","resolution":{"observed_at":"2026-08-05T11:24:09.427024Z","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":"2026-08-05T11:24:09.004797Z","title":"Fast federated learning in the presence of arbitrary device unavailability","venue":null,"work_id":"eb84ae71-a921-4d80-8e2e-ce5b1405746f","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.661317Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:5308c4e38677bfe66bc66b7482ea2cfb9fd019b9831942be5d175c0152c288c6","observation_id":"777f1750-62f4-4d5b-a7c2-d9e8416dd1d3","resolution":{"observed_at":"2026-08-05T11:24:09.149770Z","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":"2026-08-05T11:24:08.723072Z","title":"New proximal point algorithms for convex minimization.SIAM J","venue":null,"work_id":"07040165-d22b-4b14-a01f-e61da6ba501f","year":1992},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.752946Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:c2222eb4a50b2f60212ac22a95eff03727ec555a9e3bca3681193ec9ba4928e5","observation_id":"05466b24-1507-4e9c-9673-ceddda1910e8","resolution":{"observed_at":"2026-08-05T11:24:08.853960Z","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":"2026-08-05T11:24:08.394383Z","title":"Federated learning with compression: Unified analysis and sharp guarantees","venue":null,"work_id":"06887421-f825-4033-b78b-ce2ac455d02b","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:47.913868Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:b9b7994a64c541c34f83a83f9606a6929adc36d9ee3cfee60ee1fc3e7d2b4d72","observation_id":"0c2ea599-3048-4ef1-bc13-ec5c35c42c3c","resolution":{"observed_at":"2026-08-05T11:24:08.574232Z","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":"2202.01545","last_updated":"2023-04-20T15:22:15Z","snapshot_observed_at":"2026-08-16T17:23:53.342388Z","submitted_at":"2022-02-03T12:04:36Z","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01545","snapshot_observed_at":"2026-08-05T11:23:48.108536Z","title":"Byzantine-robust decentralized learning via clippedgossip","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.108536Z"},"links":{"cited_paper":"/paper/2202.01545","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:6dc6d89704b5045964a2eff2f835dcd8f28a238634219a88a8ca007097f66828","observation_id":"327f5350-a7b0-4d6d-8155-a930c272742a","resolution":{"observed_at":"2026-08-05T11:23:48.108536Z","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":"2026-08-05T11:24:07.816267Z","title":null,"venue":null,"work_id":"52543ae6-3ce9-4341-b58a-987ab5bbd0bc","year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.267528Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:35c8d13375b438eb4d5117d0accb3944584842f3829b88e0c8f8b23f1b0d152e","observation_id":"1ba70bfc-5b93-440f-999b-10c0fd9ea66b","resolution":{"observed_at":"2026-08-05T11:24:08.210716Z","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":"2026-08-05T11:24:07.459424Z","title":null,"venue":null,"work_id":"b3686648-d87b-4c8a-a955-4886e2073bff","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.411261Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:561702efb0589e52e37dcd9657b0886eb78258fefa558443c244d93bcd2228e2","observation_id":"b5cef083-6b4f-48ab-9621-b059958a67d7","resolution":{"observed_at":"2026-08-05T11:24:07.640464Z","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":"2026-08-05T11:24:07.305691Z","title":"Brendan McMahan, Brendan Avent, Aur ´elien Bellet, Mehdi Bennis, Ar- jun Nitin Bhagoji, Kallista A","venue":null,"work_id":"bf4cc26a-2245-4d46-aca7-05894649d869","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.563625Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:f3628da0385a8ba380841069af7edc8e6c321a537cbb9d9f1d0ed5211c1a5a81","observation_id":"0c46f1d7-f930-485a-8eec-dfdb2d9af3b6","resolution":{"observed_at":"2026-08-05T11:24:07.372934Z","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":"2008.03606","last_updated":"2021-06-08T08:14:57Z","snapshot_observed_at":"2026-08-18T14:46:29.950624Z","submitted_at":"2020-08-08T21:55:07Z","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03606","snapshot_observed_at":"2026-08-05T11:23:48.769342Z","title":"Mime: Mimicking centralized stochastic algo- rithms in federated learning","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.769342Z"},"links":{"cited_paper":"/paper/2008.03606","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:143e86eaccabbcb359c0d9e10f536596f43f429043dd4c05a78c6f39856655a0","observation_id":"35b018fc-3de1-4c02-9112-5fa910202634","resolution":{"observed_at":"2026-08-05T11:23:48.769342Z","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":"2026-08-05T11:24:07.068760Z","title":"Reddi, Sebastian U","venue":null,"work_id":"512b2574-8845-4340-bca7-14548cc0f9fa","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:48.919867Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:11db5563945d3ac1b749216ea0664127ff5d781cec3fd3e416b4cdf6c499a3ef","observation_id":"40b858b9-5dc8-445d-b7e3-7364d2235071","resolution":{"observed_at":"2026-08-05T11:24:07.192502Z","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":"2026-08-05T11:24:06.849359Z","title":"Learning from history for byzantine robust optimization","venue":null,"work_id":"08be57b1-ed25-4c5e-ba93-021741aa6030","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.037344Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1495e6d3a426bd419ee0ee0111cceae5a8ecaf2c6d59d9b015cf1f26840122ca","observation_id":"83ebbadd-9f91-46f0-865c-9a7e3edd6472","resolution":{"observed_at":"2026-08-05T11:24:06.954523Z","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":"2026-08-05T11:24:06.632781Z","title":"Byzantine-robust learning on hetero- geneous datasets via bucketing","venue":null,"work_id":"3f148e80-1d84-4bed-bfa5-1e4227d1f1e6","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.193303Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:acdba552eb3c27b9b6a600a6aaa2ae7014b7fab3eaec133e92f27dba1eaa0206","observation_id":"221e4cbe-80ce-42b0-9618-86868a03be8f","resolution":{"observed_at":"2026-08-05T11:24:06.720338Z","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":"1806.06573","last_updated":"2018-11-29T14:57:17Z","snapshot_observed_at":"2026-08-18T20:13:48.035341Z","submitted_at":"2018-06-18T09:37:39Z","title":"Distributed learning with compressed gradients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.06573","snapshot_observed_at":"2026-08-05T11:23:49.357820Z","title":"Distributed learning with compressed gradients","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.357820Z"},"links":{"cited_paper":"/paper/1806.06573","citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:8c065aeec74ed054e9e48c1be5359bd8fdb49d6a0c9855062da52bf89f5dc770","observation_id":"243eac7d-0bad-4998-8947-9f6a2b8c8e19","resolution":{"observed_at":"2026-08-05T11:23:49.357820Z","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":"2026-08-05T11:24:06.463675Z","title":null,"venue":null,"work_id":"5bacf2af-2319-4915-9f79-1e36d97bfe4c","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.537763Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:e0e0e4498fee345465a0b134785068ed5e7a195448e68e7137884d20d9316220","observation_id":"f90e9e2c-1c03-414f-9278-314710c45286","resolution":{"observed_at":"2026-08-05T11:24:06.552341Z","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":"2026-08-05T11:24:06.225802Z","title":"Stich, and Martin Jaggi","venue":null,"work_id":"5d84e627-001a-44a1-97b4-bec6934ccefc","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.692262Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:2b4e5e3765d2165b890a877e5e78b987157cfe9eace4e3c66592101f6b383175","observation_id":"e8d40eca-82e0-4b0f-b88b-928e4d6ff6cd","resolution":{"observed_at":"2026-08-05T11:24:06.316284Z","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":"2026-08-05T11:24:06.027237Z","title":"Gasnikov, and Gesualdo Scutari","venue":null,"work_id":"702188a8-3b3c-4515-b203-e25d304d3c4d","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:49.852729Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:73795fa2acef34a6e40e0164ddc4931a397d76b3a86e8398dbd71122c657f963","observation_id":"8a0ce6fb-9bd0-48e6-aa1f-9a4a9aa7e825","resolution":{"observed_at":"2026-08-05T11:24:06.127450Z","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":"2026-08-05T11:24:05.829936Z","title":"Shostak, and Marshall C","venue":null,"work_id":"7f2065da-5bc6-4655-b396-0f543a3c5e89","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.043376Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:3eb7611e902f3b0a18752a7b98254424a8e11aace77a7c428e62a398122049ac","observation_id":"1b22bc2c-f3c7-4f76-b6c6-3fc741bb91c1","resolution":{"observed_at":"2026-08-05T11:24:05.922659Z","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":"2026-08-05T11:24:05.625653Z","title":"First-order and stochastic optimization methods for machine learning","venue":null,"work_id":"2230f41b-f1d1-42f7-999b-78b70b87aed2","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.201362Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:75b8d40efe08157b094569b5d5352ece387baad6f2c1e7460b9f464a8d18cda2","observation_id":"117ee066-6da6-4232-b6f4-97704e416d3c","resolution":{"observed_at":"2026-08-05T11:24:05.721505Z","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":"2026-08-05T11:24:05.418426Z","title":"Giannakis, and Qing Ling","venue":null,"work_id":"2f5a9ea8-e6ed-446b-b52b-a4ebc34239b0","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.390559Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:50a678d78c37ee7cf0993459685616e65768a6e768e16766fd12c8e294917164","observation_id":"2142b774-bf49-437c-83e4-4112e75bde4b","resolution":{"observed_at":"2026-08-05T11:24:05.549658Z","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":"2026-08-05T11:24:05.227699Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":"b069c2fb-8fb2-40ec-81d9-b26db129fe35","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.553348Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:4b1d47baada065f487956b1dac4e3aa82272abc336d450c6838b4d7cb8e0717e","observation_id":"973d5637-4982-4e4c-9923-3f0c6bb3c769","resolution":{"observed_at":"2026-08-05T11:24:05.315135Z","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":"2026-08-05T11:24:05.014172Z","title":"PAGE: A simple and optimal probabilistic gradient estimator for nonconvex optimization","venue":null,"work_id":"57e69d48-2294-48db-81b9-4576d0816281","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.773223Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:132d3ead82a343d92876d41e0771ac6711ff3e15bdf05741a6693db3872fec8c","observation_id":"95560e34-8912-48c4-8140-e8cd42f61033","resolution":{"observed_at":"2026-08-05T11:24:05.119872Z","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":"2026-08-05T11:24:04.828373Z","title":"A universal catalyst for first-order opti- mization","venue":null,"work_id":"fc7eabcd-1e06-46ff-85ac-776c5d080485","year":2015},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:50.952662Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1f1941f4faf064f45d3703566e148ef7efb2906b49b3dc3d7b4988e45c4e6991","observation_id":"ef161e42-99d6-4242-a1e0-eaeae3517b62","resolution":{"observed_at":"2026-08-05T11:24:04.914992Z","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":"2026-08-05T11:24:04.668303Z","title":"Byzantine ro- bustness and partial participation can be achieved at once: Just clip gradient differences","venue":null,"work_id":"5fb28a6f-faf1-47c9-b70c-5e8b47cad546","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:51.167173Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:a8282fd27a422ceb3a99fd93ba39c4041d4e6a25e02126ba04383d368140e6c5","observation_id":"38816875-f62c-4f4b-83e1-638a70b993c5","resolution":{"observed_at":"2026-08-05T11:24:04.755939Z","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":"2026-08-05T11:24:04.493928Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"189cbba3-7ac2-4162-9f89-87daf1c25b79","year":2017},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:51.353768Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:6d4cf902ae07113a0e539c8ad43609c7312c5cb7ca5b0a1739f3ec4563e0c591","observation_id":"1abf519d-ae37-45d1-b7b8-b6cba3fc27c9","resolution":{"observed_at":"2026-08-05T11:24:04.586718Z","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":"2026-08-05T11:24:04.340795Z","title":"The hidden vulnerability of distributed learning in byzantium","venue":null,"work_id":"d170ffde-1f08-42c4-aca7-599ad35d8db6","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:51.615117Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:c3330320a5dca083314d9841f1ead9bb2ed8944e9cecbd896bbcc85d9fde65ac","observation_id":"11a12552-3d13-4e4b-98ad-70c05c3af652","resolution":{"observed_at":"2026-08-05T11:24:04.398320Z","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":"2026-08-05T11:24:04.133846Z","title":"Distributed momentum for byzantine-resilient stochastic gradient descent","venue":null,"work_id":"befbb5d1-55f6-4cd1-90c5-249eacc96555","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:51.781127Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:e4dfc0cab0f953bd12f3fd5dd54ba0a005aa1c202c5f1fdda13abb823a7be77f","observation_id":"d1cf6f58-e4f4-4f91-aa12-4a9ba80c77b9","resolution":{"observed_at":"2026-08-05T11:24:04.229568Z","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":"2026-08-05T11:24:03.980409Z","title":"Bach, Mathieu Even, and Blake E","venue":null,"work_id":"23ce851a-5b59-4fb5-ac1d-5537de3c4f9d","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:51.969157Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:bf6fb5908f06dbf0a0274e35a199e836514536a14f89b51d59fe5b579370e019","observation_id":"f9bc657d-5dfd-477e-80e0-3c39d28c8c11","resolution":{"observed_at":"2026-08-05T11:24:04.050712Z","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":"2026-08-05T11:24:03.811031Z","title":"Distributed learning with compressed gradient differences","venue":null,"work_id":"1686661e-5eec-41b2-857c-10b8fd879535","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.062288Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:67488edb01b6ca266a80c1b77f6cea602abdb671249ccf4af9c97280b0c9b839","observation_id":"e85fd7a1-3720-4e0d-9fbc-3317b31db6cf","resolution":{"observed_at":"2026-08-05T11:24:03.877273Z","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":"2026-08-05T11:24:03.649062Z","title":null,"venue":null,"work_id":"f9340247-05fc-47b1-a9c3-470bf705b462","year":2013},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.235349Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:6bb8756b34f899b590f2c3dce2a7784018803d1e1a66d92e4a52c6c1052bd7be","observation_id":"ec55e135-eb39-429e-9ea2-2b0d1620ad9f","resolution":{"observed_at":"2026-08-05T11:24:03.713860Z","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":"2026-08-05T11:24:03.363981Z","title":"Lectures on convex optimization","venue":null,"work_id":"589ae177-2902-47c2-9718-15de9afe6817","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.399957Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:ca4013827ace8781119dee6d5f176d28759991c1d2c499df6fc577c005fc89da","observation_id":"3e40cb19-1ac3-47a8-a0bc-dd550899f861","resolution":{"observed_at":"2026-08-05T11:24:03.481129Z","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":"2026-08-05T11:24:03.205138Z","title":"Billion-scale federated learning on mobile clients: a submodel design with tunable privacy","venue":null,"work_id":"df01b1b8-3304-4fd0-9a1f-36c08e163047","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.575385Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:cef4e315656161e25842bd0cd41058b547d3039f14b5cfc6fe0392662992ffd8","observation_id":"363aeb61-5dc3-41db-b894-060b509c5cf0","resolution":{"observed_at":"2026-08-05T11:24:03.285479Z","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":"2026-08-05T11:24:02.730492Z","title":"Woodworth, Brian Bullins, and Nati Srebro","venue":null,"work_id":"e432fc1c-c63a-466b-883a-9e797b146f75","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.738141Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:2e9ab3643d8117958212bf20c9c404d03efbb4c75335272e7a8d75c87a73db84","observation_id":"256af660-00be-4c29-bcb2-89fbbe2e5cda","resolution":{"observed_at":"2026-08-05T11:24:02.982404Z","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":"2026-08-05T11:24:02.409249Z","title":"Kakade, and Za ¨ıd Harchaoui","venue":null,"work_id":"3aa51c8f-9af9-4552-9dc4-21908ecc00a7","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:52.918896Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1af65d8278e01bad02007bd213dc4a67580a593c5aae73c726b4e5e61b8e9650","observation_id":"080a50e7-92d5-442a-82e8-690d70a2ee05","resolution":{"observed_at":"2026-08-05T11:24:02.576939Z","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":"2026-08-05T11:24:02.056785Z","title":"Distributed stochastic gradient tracking methods","venue":null,"work_id":"31ac68e3-b68f-48dd-b762-ef6879543d3d","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:53.097222Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:89950076a9679b51905322d1ddaf832b1e3272212a23817d49a2c56235c4d115","observation_id":"4701573c-2323-43e4-ae60-c0edd3107f99","resolution":{"observed_at":"2026-08-05T11:24:02.214574Z","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":"2026-08-05T11:24:01.657646Z","title":"Charles, and Dimitris S","venue":null,"work_id":"bad9d12f-7006-4018-a0a7-d110d77919e1","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:53.329441Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:5fd0dc30e6496670c39c987af54d29816aab2056f017448f49fc7d27d1cb2207","observation_id":"6c77cbe6-9282-4ccc-97d2-bf905fdf145d","resolution":{"observed_at":"2026-08-05T11:24:01.891777Z","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":"2026-08-05T11:24:01.260299Z","title":"Communication compression for byzantine robust learning: New efficient algorithms and im- proved rates","venue":null,"work_id":"2ef984ba-f1da-4832-a4f9-52fe84d868ff","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:53.482369Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:c4c603b50a0651ff36e659b1b387865fa5c99292c6461a4001dd982460d556e8","observation_id":"8cf24a2a-a2ff-4647-9773-6d82bd624917","resolution":{"observed_at":"2026-08-05T11:24:01.417405Z","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":"2026-08-05T11:24:00.894548Z","title":"On the byzantine robustness of clustered federated learning","venue":null,"work_id":"daec4ed0-0728-4e19-b218-4f7d55bbe1aa","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:53.724136Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:0d92349059d574813d4323186dddb89a8de275f3decafef9f11c342b709c93a6","observation_id":"291140bb-d824-416e-a393-5454701972c0","resolution":{"observed_at":"2026-08-05T11:24:01.094519Z","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":"2026-08-05T11:24:00.463496Z","title":"Ordered momentum for asynchronous SGD","venue":null,"work_id":"d76d4df9-838b-49da-a41d-f5debe468298","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:53.878085Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:ad790a5e707430074479468ee450fd927468e4711ef4a8c9e975b251286250fe","observation_id":"017ffac4-b42c-4c7c-ae82-26d4ca85334f","resolution":{"observed_at":"2026-08-05T11:24:00.644224Z","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":"2026-08-05T11:24:00.141566Z","title":"Stich, Jean-Baptiste Cordonnier, and Martin Jaggi","venue":null,"work_id":"c35490c7-965c-4e84-ac23-bae9a83e4f2c","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.027089Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:9cc32bbb158126468fb9406c416ed8e79d87f58534b591e72c5d84deeea093b5","observation_id":"d663735f-a515-4b8a-9ec1-d839ad7d06b9","resolution":{"observed_at":"2026-08-05T11:24:00.298878Z","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":"2026-08-05T11:23:59.764257Z","title":"Momentum track- ing: Momentum acceleration for decentralized deep learning on heterogeneous data","venue":null,"work_id":"d17097ca-6f58-4529-859a-efdc75a0db26","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.260927Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:a2560da52d473a86c51f4be4e5ea2b9150b86a4b4ae72ccd4f1f6f9b06211784","observation_id":"6712f1d3-56fd-4404-84b8-0a16818aaedd","resolution":{"observed_at":"2026-08-05T11:23:59.925222Z","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":"2026-08-05T11:23:59.504223Z","title":"Vincent Poor","venue":null,"work_id":"fa9a44ff-a442-4557-ac36-d1eaadd3ef10","year":2020},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.423381Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:10d3aa520a54d5095a23f5f8751cf9bdacb900681989b23c60b4a17fd806bf42","observation_id":"1ec7a478-5337-4518-bc78-c48952e50597","resolution":{"observed_at":"2026-08-05T11:23:59.647402Z","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":"2026-08-05T11:23:59.191072Z","title":"A unified analysis of federated learning with arbitrary client participation","venue":null,"work_id":"cc54b8df-9550-404d-a4ef-cd95318a8982","year":2022},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.552540Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:107a5ef7d9935534b2621bc4be296c9ccbba0c5f244170ede457cee22bee8dae","observation_id":"30bea42c-8c71-417d-8520-dc6d72cb76d7","resolution":{"observed_at":"2026-08-05T11:23:59.344160Z","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":"2026-08-05T11:23:58.792358Z","title":"Fall of empires: Breaking byzantine- tolerant SGD by inner product manipulation","venue":null,"work_id":"a396f184-584c-4db1-be72-875374f8a4bc","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.660711Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:f093e98d583359949f985c600e6d20a5af05627933c1066bb4fdbed4f315f3eb","observation_id":"6ee99e30-a692-4d52-b53b-e948a2673b65","resolution":{"observed_at":"2026-08-05T11:23:58.971338Z","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":"2026-08-05T11:23:58.403943Z","title":"Zeno: Distributed stochastic gradient descent with suspicion-based fault-tolerance","venue":null,"work_id":"3e6ef30c-c13b-49d3-bc6b-d0433a0d674a","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.790841Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:665012ff8a5c29fcbea553554e6e39202861b88fee8abda426a6044d095c5dde","observation_id":"711d9244-25c2-45e7-a519-2089a4695366","resolution":{"observed_at":"2026-08-05T11:23:58.587048Z","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":"2026-08-05T11:23:58.007620Z","title":"Federated optimization under intermittent client availability","venue":null,"work_id":"1d153925-02ed-48d4-af2b-63beede5721a","year":2024},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:54.906122Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1b4787730e1e05828de72c7a16d21ad93f32d031076e4276c1f6446da33d7fa3","observation_id":"ecc309ce-6d46-4acd-9b25-16b69cf30768","resolution":{"observed_at":"2026-08-05T11:23:58.195008Z","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":"2026-08-05T11:23:57.639089Z","title":"Achieving linear speedup with partial worker participation in non-iid federated learning","venue":null,"work_id":"8de79190-bc27-4315-b576-04ebf37d1b2f","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.044951Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:3223f9551869d2feafa7dca01e6aa8ed064142a52e62325916d840f12ef367d8","observation_id":"7e26784b-37f6-4b0f-b0b1-d947d6745ec4","resolution":{"observed_at":"2026-08-05T11:23:57.795257Z","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":"2026-08-05T11:23:57.355081Z","title":"BASGD: buffered asynchronous SGD for byzantine learning","venue":null,"work_id":"e8a261ce-d849-4c2b-b610-903dac1bea7e","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.165779Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:e5776217e807e4f680063e63bb9d95320c06442f4309166d0161aeb8621cb920","observation_id":"0688a384-cadb-4923-9522-9b6645e1d012","resolution":{"observed_at":"2026-08-05T11:23:57.483980Z","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":"2026-08-05T11:23:57.026658Z","title":"Bartlett","venue":null,"work_id":"e81bcace-dbb6-48ba-bb15-347573a92daf","year":2018},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.297291Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:dab6ba53216991fe305aa202b803cbf214da956e117f9673c6ff31540a2bd4da","observation_id":"2a2228a3-a23e-4f7f-8c53-3fd96bce662a","resolution":{"observed_at":"2026-08-05T11:23:57.196225Z","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":"2026-08-05T11:23:56.652055Z","title":"Parallel restarted SGD with faster convergence and less communication: Demystifying why model averaging works for deep learning","venue":null,"work_id":"0c258911-a1d4-4a3d-8d12-41314b1ae618","year":2019},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.455602Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:aedebf2d44305c285f17509008f05326bb26f99b3c2558d22dd0454417467a21","observation_id":"67f48b82-8e72-4509-bce0-b50e3e2e8347","resolution":{"observed_at":"2026-08-05T11:23:56.864763Z","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":"2026-08-05T11:23:56.209285Z","title":"Dhople, Wotao Yin, and Yang Liu","venue":null,"work_id":"1e506382-46d1-4f0f-ae73-e72b79220cc0","year":2021},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.609414Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:1df84d4d166f80be2d176194c233f187b9a96c16363fa0a1a0fdabece9306309","observation_id":"8a625610-ca03-4047-af7e-1572d4d2efb3","resolution":{"observed_at":"2026-08-05T11:23:56.361763Z","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":"2026-08-05T11:23:55.931446Z","title":"true gradient momentum","venue":null,"work_id":"83502a69-1895-47db-b4fd-82782075bd1f","year":2023},"citing_paper":{"arxiv_id":"2509.02970","last_updated":"2026-05-29T09:37:19Z","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T11:23:55.713858Z"},"links":{"citing_paper":"/paper/2509.02970"},"observation_digest":"sha256:7637dc63879989c4521d8e5821f42d63ac70f7a590446f190ee424c294c49e7c","observation_id":"6f3040af-6672-45ac-8e76-64098a093088","resolution":{"observed_at":"2026-08-05T11:23:56.059750Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2509.02970","last_updated":"2026-05-29T09:37:19Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T20:36:33.119369Z","submitted_at":"2025-09-03T03:14:58Z","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation"},"reference_resolution":{"displayed":83,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":64},"total_outbound_references":83},"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 83 of 83 outbound references and 0 inbound Pith citation observations for arXiv:2509.02970."}