{"as_of":"2026-08-19T12:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:acee8fe0693d5704846b8476950c1e823217d41d52b7963c53b6ff669c9b9a99","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T18:59:48.229923Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2509.09534/citation-record","integrity":"/paper/2509.09534/integrity","json":"/paper/2509.09534/citation-record.json","paper":"/paper/2509.09534"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T18:59:48.135951Z","title":"Communication-Efficient Learning of Deep Networks from Decentral- ized Data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.135951Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:e01adb988a7f78370a2c5b920225c43be13d232b7e16204c26358c52d06870b8","observation_id":"93d29e1d-5203-4d41-8044-6047194cac74","resolution":{"observed_at":"2026-08-04T18:59:48.135951Z","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":"2026-08-04T18:59:48.139415Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.139415Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:e54230cb3de05d536e2f05b1805de73be8e715f989776c195a73094bf811390b","observation_id":"635b0bbe-8683-4678-a1ce-52a6b13f3277","resolution":{"observed_at":"2026-08-04T18:59:48.139415Z","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":"2026-08-04T18:59:48.142274Z","title":"Survey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.142274Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:1ca1851d1af3701205cc12811c31cd7e84470c4460118b326f3d0f8c7bd4aefd","observation_id":"97749618-7d4f-4674-910f-4abba780cfd8","resolution":{"observed_at":"2026-08-04T18:59:48.142274Z","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":"2026-08-04T18:59:48.145203Z","title":"Heterogeneous federated learning: State-of-the-art and research challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.145203Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:4be13e94dc05425f78154dc1b9f1f1fd82094170b90779b14978bea2b1b1f335","observation_id":"b45d609a-f6e1-4d44-941e-a378dc981d4b","resolution":{"observed_at":"2026-08-04T18:59:48.145203Z","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":"2026-08-04T18:59:48.148508Z","title":"The byzantine generals prob- lem,","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.148508Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:d36aac5a68f21d6c6cd0ecc511bb01ccb6b91126ba145a951fe84c183687e923","observation_id":"5bccc6ca-6f82-4786-aeed-f273dee8d3a5","resolution":{"observed_at":"2026-08-04T18:59:48.148508Z","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":"2026-08-04T18:59:48.151287Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.151287Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:2f37f4617e36f36eb1f33a98ed48dd0021da83f42ddb68f0f335b92afa237a80","observation_id":"4f0bf615-9626-43c0-b20b-c49095690d9b","resolution":{"observed_at":"2026-08-04T18:59:48.151287Z","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":"2026-08-04T18:59:48.154354Z","title":"Byzantine-robust dis- tributed learning: Towards optimal statistical rates,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.154354Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:033d780d323e091bba2e1b1d5228c916195d2576f3be76b09648244989ad6b42","observation_id":"8158da77-6e8f-498e-a597-def10eb0f511","resolution":{"observed_at":"2026-08-04T18:59:48.154354Z","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":"2026-08-04T18:59:48.156922Z","title":"Distributed statistical machine learning in adversarial settings: Byzantine gradient descent,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.156922Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:85b5f0ae76a8cbff7c73d9e04ecc5676525dd2149e5bb0ce5505dc7c504e2a99","observation_id":"4cc03cef-461a-4bb8-9f4d-53c94ba08885","resolution":{"observed_at":"2026-08-04T18:59:48.156922Z","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":"2026-08-04T18:59:48.159539Z","title":"Robust aggregation for federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.159539Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:c7f240fefb3d17c0d533f5283b4fa15a35e2bb9b4c44a11fd729a18ab65dbbfd","observation_id":"cb8436b6-9837-4268-b903-ed985233cea2","resolution":{"observed_at":"2026-08-04T18:59:48.159539Z","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":"2026-08-04T18:59:48.162187Z","title":"Learning from history for byzantine robust optimization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.162187Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:f1d9047f3e9e47f3b1c2107c55ef1e50ddcb7d7fb4e27723dc45f5b3ddfd4afa","observation_id":"4f561f3a-7716-4a55-a633-927b8e1356b2","resolution":{"observed_at":"2026-08-04T18:59:48.162187Z","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":"2026-08-04T18:59:48.164896Z","title":"The hidden vulnera- bility of distributed learning in byzantium,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.164896Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:ba0281cc10bdce94bc925ab8adcf864113573271b5b72043933b19121d7f59f9","observation_id":"6bd5b8b1-0f08-4f8e-b712-7c84a49bfb5c","resolution":{"observed_at":"2026-08-04T18:59:48.164896Z","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":"2026-08-04T18:59:48.167529Z","title":"Faba: An algorithm for fast aggregation against byzantine attacks in distributed neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.167529Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:0db165ff6f18edad39079db20389550505cfddcbe686316a75efc0596ce8025a","observation_id":"4a9b1aff-8d8f-4906-8dc4-c60b6e8af0cf","resolution":{"observed_at":"2026-08-04T18:59:48.167529Z","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":"2026-08-04T18:59:48.170408Z","title":"Understanding distributed poisoning attack in federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.170408Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:bd5849ee1f90b67ecd78c1965998ae820dd593d0dc2062ff18c7a739fe73ee07","observation_id":"c6a9624f-ea58-42b0-a38a-e8235c52d79d","resolution":{"observed_at":"2026-08-04T18:59:48.170408Z","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":"2026-08-04T18:59:48.173406Z","title":"Byzantine-robust federated learning through spatial-temporal analysis of local model updates,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.173406Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:c840f2341e11513bad27ee9590b4628ae92cc4e94636741c7ca40210f0f2fce7","observation_id":"f1aea167-2ece-46d7-8067-e19d6d2c23e1","resolution":{"observed_at":"2026-08-04T18:59:48.173406Z","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":"2026-08-04T18:59:48.176171Z","title":"On the byzantine robustness of clustered federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.176171Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:da15d98af4d86315be7d68021ef1830aa33ce3f28f76afff9ae79eff100f05e2","observation_id":"ea1e547a-1cf6-43fe-8bb7-562d3928c982","resolution":{"observed_at":"2026-08-04T18:59:48.176171Z","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":"2026-08-04T18:59:48.178731Z","title":"An experimental study of byzantine- robust aggregation schemes in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.178731Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:3cbc4782ec7d6d3cc77b09a5107299038aa4a90485ad41c3dd2f860c2b3ec8b8","observation_id":"bc437b0c-9e2a-4f3a-90d5-e7e7d72df3d7","resolution":{"observed_at":"2026-08-04T18:59:48.178731Z","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":"2026-08-04T18:59:48.181179Z","title":"Zeno: Distributed stochastic gradient descent with suspicion-based fault-tolerance,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.181179Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:cbb924990481076536847550a8873db4effaca15a2bed1cbdee45003b9d2d717","observation_id":"3dfb91f8-b5b9-4197-aec9-460e8c9fc5ca","resolution":{"observed_at":"2026-08-04T18:59:48.181179Z","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":"2026-08-04T18:59:48.183866Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.183866Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:b297db3600179043d0cc9436abf35e9069c00599302db3e1b59a780ebe10c754","observation_id":"81cf7288-6e81-4940-a366-c624b9c8ead2","resolution":{"observed_at":"2026-08-04T18:59:48.183866Z","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":"2026-08-04T18:59:48.187831Z","title":"Fedgt: Identification of malicious clients in federated learning with secure aggregation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.187831Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:97f1563f1667a77e9cf93b8e0cd08b3288a8636850ad0ec27c72a2036f426c16","observation_id":"4c7253ad-aabb-47e7-9fe8-7c0f060d603e","resolution":{"observed_at":"2026-08-04T18:59:48.187831Z","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":"2026-08-04T18:59:48.190335Z","title":"Fixing by mixing: A recipe for optimal byzantine ml under heterogeneity,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.190335Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:99bb486b39f894b647d7cd6baea5d2a7aa88d6e3f985d176724576782e221931","observation_id":"3ff916cd-f595-419e-b3c7-94671dada584","resolution":{"observed_at":"2026-08-04T18:59:48.190335Z","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":"2026-08-04T18:59:48.193078Z","title":"Byzantine-robust learning on heterogeneous datasets via bucketing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.193078Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:aa7cc45aaf2255aef0691af6aa3a0b6337e122a625d89f6eb2a0adf582566f83","observation_id":"7971d503-701d-4c2c-bb92-5c193d882c46","resolution":{"observed_at":"2026-08-04T18:59:48.193078Z","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":"2026-08-04T18:59:48.196016Z","title":"Distributed momentum for byzantine-resilient stochastic gradient descent,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.196016Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:40d19b034ab7fefbaa70de595b42f82fc6cc742b720e08cc97fd517f80b94b3e","observation_id":"8092c607-9f49-4cad-8d4a-b242ccf6c92a","resolution":{"observed_at":"2026-08-04T18:59:48.196016Z","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":"2026-08-04T18:59:48.198484Z","title":"A little is enough: Circumvent- ing defenses for distributed learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.198484Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:0221f045bc0ac01bbf4e807f223c8b3906fed3d8ec7767ebe04a6d3c4ed0e7d4","observation_id":"8966dfcf-d88f-48e2-8d12-0d16c6b07b49","resolution":{"observed_at":"2026-08-04T18:59:48.198484Z","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":"2026-08-04T18:59:48.201009Z","title":"Fall of empires: Breaking byzantine- tolerant sgd by inner product manipulation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.201009Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:6b0f59bcd4c32f3eb75af8f7fb2d1171d44af88b716c977d8de344da1c36d456","observation_id":"bb46a260-09c4-4b4c-b49e-a94be97b978f","resolution":{"observed_at":"2026-08-04T18:59:48.201009Z","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":"2026-08-04T18:59:48.203684Z","title":"Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning ,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.203684Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:174bbf2072016a4ac78f2a0dfa8e49df5417993351d4f70e051a327cbebac44b","observation_id":"fbe6d0f9-19ff-43ab-9e1b-771c4997cad7","resolution":{"observed_at":"2026-08-04T18:59:48.203684Z","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":"2026-08-04T18:59:48.206654Z","title":"The sybil attack,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.206654Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:f3ce46763331caf831b9daca33cdb3d2875603e43fb176b2df0c0f9f74f88ec4","observation_id":"bf2f4c20-35fc-47a1-8341-43423989f62a","resolution":{"observed_at":"2026-08-04T18:59:48.206654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.04866","last_updated":"2020-07-15T15:35:17Z","snapshot_observed_at":"2026-08-18T14:49:43.852586Z","submitted_at":"2018-08-14T19:20:35Z","title":"Mitigating Sybils in Federated Learning Poisoning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.04866","snapshot_observed_at":"2026-08-04T18:59:48.209198Z","title":"Mitigating sybils in federated learning poisoning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.209198Z"},"links":{"cited_paper":"/paper/1808.04866","citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:a0a91c3bccdc38110e382eeaf0e31222f4105b58c3df2d792d3503af82794216","observation_id":"4a94c6ea-2422-41d3-a72e-eacf9fb64fba","resolution":{"observed_at":"2026-08-04T18:59:48.209198Z","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":"2026-08-04T18:59:48.212047Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.212047Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:0c928ac78b53809b4a65eada3018bf59686b754932a3bdaffd47c017cf4b183d","observation_id":"ee25cb69-a873-43a7-8c41-12bf7a2937d1","resolution":{"observed_at":"2026-08-04T18:59:48.212047Z","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":"2026-08-04T18:59:48.214812Z","title":"Scaffold: Stochastic controlled averaging for federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.214812Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:496d152e47766ed43ff9a75986ea676fd04c9b2a8b386221a1122519b0e7de0b","observation_id":"9d675746-072d-4b78-81ef-3f1f40e05320","resolution":{"observed_at":"2026-08-04T18:59:48.214812Z","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":"2026-08-04T18:59:48.217587Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.217587Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:e4a4fd70da59e812420f873361911ced734123803996a35b4457c32bee4f5f69","observation_id":"3b8c6507-84f4-4e1d-810c-3864949bdf23","resolution":{"observed_at":"2026-08-04T18:59:48.217587Z","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":"2026-08-04T18:59:48.220025Z","title":"Leaf: A benchmark for federated settings,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.220025Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:c07ce8e3d51f88a2f065ebc26e52b3d0a965d4c72fb33c4074f9661f6ae0b0ed","observation_id":"5f823f68-bd07-4737-abe6-1aff69f0c920","resolution":{"observed_at":"2026-08-04T18:59:48.220025Z","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":"2026-08-04T18:59:48.222525Z","title":"Ensemble distillation for robust model fusion in federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.222525Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:627b5f0ea273d3febecb847b1b422c0892e0d018570e124f7033300c630ec6d7","observation_id":"7295f497-2516-4d5f-a850-6339475a2a94","resolution":{"observed_at":"2026-08-04T18:59:48.222525Z","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":"2026-08-04T18:59:48.224942Z","title":"Adaptive gradient clipping for robust federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.224942Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:0261732c169cddff6a2efb96df7937dcb76356b39c88bcd3eb7f4d341e7fadf5","observation_id":"1afe9ce8-7ed5-42dd-937f-a7c73b408c6e","resolution":{"observed_at":"2026-08-04T18:59:48.224942Z","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":"2026-08-04T18:59:48.227415Z","title":"Byzantine- resilient non-convex stochastic gradient descent,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.227415Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:18c2ccbdfaf473e8952f54307d72d5cff8bd42f863d91159945c934fa46c4b96","observation_id":"93a1acaf-7a17-4434-9742-f1e7af0ad24d","resolution":{"observed_at":"2026-08-04T18:59:48.227415Z","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":"2026-08-04T18:59:48.229923Z","title":"Manipulating the byzantine: Op- timizing model poisoning attacks and defenses for federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:48.229923Z"},"links":{"citing_paper":"/paper/2509.09534"},"observation_digest":"sha256:3cb546796bd03d70e61ba21bea55f7ea1fec820675cfdfe09c4fbb41b1b50af4","observation_id":"aaa4d25c-232c-4179-864b-516a05e78603","resolution":{"observed_at":"2026-08-04T18:59:48.229923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09534","last_updated":"2025-09-11T15:25:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T10:53:04.537116Z","submitted_at":"2025-09-11T15:25:59Z","title":"ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":35},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2509.09534."}