{"as_of":"2026-08-17T08:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:66510fa4dd84af7c67fdd95e3ce23734e65289d07d3bdce0ebeefb0e4c425151","coverage":[{"denominator":119,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:39:29.682066Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T20:42:08.155262Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-13T01:22:01.911536Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.06684","snapshot_observed_at":"2026-08-03T20:42:08.155262Z","title":"Fnbench: Benchmarking robust federated learning against noisy labels.arXiv preprint arXiv:2505.06684, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.18894","last_updated":"2026-07-27T01:44:57Z","snapshot_observed_at":"2026-08-16T19:51:00.973740Z","submitted_at":"2025-11-24T08:51:02Z","title":"Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels","version":6},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T20:42:08.155262Z"},"links":{"cited_paper":"/paper/2505.06684","citing_paper":"/paper/2511.18894"},"observation_digest":"sha256:b78fe09647625749850db35a55a5b9759d5f39b9fdcceb9345a6b7b937aa016e","observation_id":"357db11f-f594-431d-9e45-9486538f6f1b","resolution":{"observed_at":"2026-08-03T20:42:08.155262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"cited_work":{"arxiv_id":"2505.06684","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.06684","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fnbench: Benchmarking ro- bust federated learning against noisy labels","venue":null,"work_id":"1e7c6ccc-ff1e-4248-b638-d2b9b8f6b44e","year":2025},"citing_paper":{"arxiv_id":"2605.11060","last_updated":"2026-05-11T17:18:45Z","snapshot_observed_at":"2026-08-12T16:57:53.566813Z","submitted_at":"2026-05-11T17:18:45Z","title":"SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-13T01:19:23.208576Z"},"links":{"cited_paper":"/paper/2505.06684","citing_paper":"/paper/2605.11060"},"observation_digest":"sha256:fbfb66e9fbedef97f33e17550c437d4a7651bc8a6bac28687aeb086333022e58","observation_id":"ecac8589-a3ea-4c15-b5ec-e5535ff74ea4","resolution":{"observed_at":"2026-05-13T01:22:01.913516Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.06684/citation-record","integrity":"/paper/2505.06684/integrity","json":"/paper/2505.06684/citation-record.json","paper":"/paper/2505.06684"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:39:29.241589Z","title":"Tackling noisy clients in federated learning with end-to-end label correction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.241589Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:d0751830749fdda0dc95f70e028b93e3f6a2ee0107abf550309e4c880b164274","observation_id":"e3b69c5e-eda0-4335-a521-4dd33f5e290f","resolution":{"observed_at":"2026-08-15T22:39:29.241589Z","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":"2026-08-15T22:39:29.246066Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.246066Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:c83fc00230693381ff93cb068c66bdc1d83cf8f409bb83abbe931f3bd2957630","observation_id":"e7a48d28-6eaf-4307-849b-12437e368e21","resolution":{"observed_at":"2026-08-15T22:39:29.246066Z","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":"2026-08-15T22:39:29.249703Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.249703Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:29f6bca1d2b0739cf7d5f04eac3ffea78e8c874de7c3c8feca8d9014f81bf6cc","observation_id":"0ffbd01c-ad87-40c4-9243-08c498bba58b","resolution":{"observed_at":"2026-08-15T22:39:29.249703Z","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":"2026-08-15T22:39:29.258504Z","title":"Fedeye: A scalable and flexible end-to-end federated learning platform for ophthalmology,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.258504Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:204815653681a3b7d5bce70eda031563c0137bf945ac189641ee2fceaba51358","observation_id":"d95f7318-bf1c-4f61-b2aa-763d7577ffd6","resolution":{"observed_at":"2026-08-15T22:39:29.258504Z","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":"2026-08-15T22:39:29.261844Z","title":"Fednoro: Towards noise-robust federated learning by addressing class imbalance and label noise heterogeneity,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.261844Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1401c8340c82d4e4727d57146c59021d31941811c4ac3a5ec55b899af9def7e7","observation_id":"407799a5-3e7f-4578-9218-5dc4f1d8234b","resolution":{"observed_at":"2026-08-15T22:39:29.261844Z","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":"2026-08-15T22:39:29.265762Z","title":"A knowledge transfer- based semi-supervised federated learning for iot malware detection,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.265762Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:454fe4334b45c2106d31c0fc35b91e586e18f6849ed5f8b37ab2bddd292c80c3","observation_id":"75ba35e3-c63b-40c3-8288-4e5e2677e31e","resolution":{"observed_at":"2026-08-15T22:39:29.265762Z","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":"2026-08-15T22:39:29.273132Z","title":"Spotting anomalies at the edge: Outlier exposure-based cross-silo federated learning for ddos detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.273132Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:0dcd60c0470a024ddde1d743bca6cb82411ea08b3461177ad0276dcd4366433c","observation_id":"a401375a-1d07-44e7-9536-5e61b71df3ee","resolution":{"observed_at":"2026-08-15T22:39:29.273132Z","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":"2026-08-15T22:39:29.279882Z","title":"Fedict: Federated multi-task distillation for multi-access edge computing,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.279882Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:c3c91123f2a58026d1d9b9c6ca8eb177bb0df041203be606df164af98e48a511","observation_id":"f085f9d0-4eda-4771-8d50-854201459a90","resolution":{"observed_at":"2026-08-15T22:39:29.279882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10616","last_updated":"2023-09-08T07:19:22Z","snapshot_observed_at":"2026-08-16T15:14:47.628228Z","submitted_at":"2023-07-20T06:32:14Z","title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","version":2},"cited_work":{"arxiv_id":"2307.10616","doi":"10.48550/arxiv.2307.10616","metadata_source":"pith","pith_arxiv_id":"2307.10616","snapshot_observed_at":"2026-08-16T12:16:17.039197Z","title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","venue":"cs.LG","work_id":"67e2a3a0-6609-499d-8b2a-d1096dfffac8","year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.289489Z"},"links":{"cited_paper":"/paper/2307.10616","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:9fae719cf72420e6bca829cb56e4a4032db76a1a41baadf7f4fb88a2e045958f","observation_id":"396a8771-5031-4023-b257-a3cce67e0ca7","resolution":{"observed_at":"2026-08-15T22:39:29.898406Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.293303Z","title":"Fedbiad: Communication-efficient and accuracy-guaranteed federated learning with bayesian inference-based adaptive dropout,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.293303Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:37d091142d6faee68208ca8437f195722fc56a44b5b8d70d85054d69f0bdffea","observation_id":"8ba40a47-6211-4fe8-9172-0ace40452c4c","resolution":{"observed_at":"2026-08-15T22:39:29.293303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.05849","last_updated":"2024-03-05T13:57:22Z","snapshot_observed_at":"2026-08-16T16:02:28.495572Z","submitted_at":"2023-01-14T08:08:29Z","title":"Knowledge Distillation in Federated Edge Learning: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.05849","snapshot_observed_at":"2026-08-15T22:39:29.296687Z","title":"Survey of knowledge distillation in federated edge learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.296687Z"},"links":{"cited_paper":"/paper/2301.05849","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:caca74d11fa10535cdd6d8c4f08ab5ff8edc9ef6157231586ef93df513d61c85","observation_id":"936f42ac-835e-4862-8a6c-b7d0b8bfb36a","resolution":{"observed_at":"2026-08-15T22:39:29.296687Z","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":"2026-08-15T22:39:29.301372Z","title":"Understanding and mitigating dimensional collapse in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.301372Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:cd731752a904f4e923478819006929df630fbe4d2d217b368456dbd4575d0e39","observation_id":"a8c5f121-14ed-4ba3-8662-df350a2b0481","resolution":{"observed_at":"2026-08-15T22:39:29.301372Z","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":"2026-08-15T22:39:29.304600Z","title":"CLC: A consensus-based label correction approach in federated learning,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.304600Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:d9bd40945d3e80feae23233cc874c6b6cf7b135480303e48d388f90c9bcd84b3","observation_id":"9473529f-8a99-4328-9914-688261cd9de9","resolution":{"observed_at":"2026-08-15T22:39:29.304600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.11359","last_updated":"2020-01-29T09:31:01Z","snapshot_observed_at":"2026-07-06T08:53:45.264296Z","submitted_at":"2020-01-29T09:31:01Z","title":"FOCUS: Dealing with Label Quality Disparity in Federated Learning","version":1},"cited_work":{"arxiv_id":"2001.11359","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.11359","snapshot_observed_at":"2026-08-15T22:39:31.501085Z","title":"FOCUS: Dealing with Label Quality Disparity in Federated Learning","venue":"cs.LG","work_id":"e4bb71dd-f8c2-4359-abe3-21afbc852af3","year":2020},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.311696Z"},"links":{"cited_paper":"/paper/2001.11359","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:859c72601882be9d0ace5a3bf92c40c32daaab6ec4b9b659c3bae98666080847","observation_id":"2d3e9062-85d9-4a25-9625-f5f72589cbab","resolution":{"observed_at":"2026-08-15T22:39:31.506822Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.314995Z","title":"Robust federated learning with noisy labels,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.314995Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1f489869f49e7e135564904619fd7827be569b306af02a4ad5feed7b334d90b6","observation_id":"d84b8636-8a2b-4ed2-ac64-4ac6b1d8bf7a","resolution":{"observed_at":"2026-08-15T22:39:29.314995Z","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":"2026-08-15T22:39:29.321685Z","title":"Fedrn: Exploiting k-reliable neighbors towards robust federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.321685Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:fa8e6e251cbfdd56204226cce4daecc609bc27d6397ca26447ed1a3727c8acf0","observation_id":"c3eb82dc-0ac9-4447-aaba-5e280369e50e","resolution":{"observed_at":"2026-08-15T22:39:29.321685Z","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":"2026-08-15T22:39:29.325478Z","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.325478Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:6990754e5fd46b1e8966701bf5ed57bdbb930c6e92f28cb6b73948150d69cd94","observation_id":"7db3dc54-3eb9-418c-8654-d0c0e9778641","resolution":{"observed_at":"2026-08-15T22:39:29.325478Z","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":"2026-08-15T22:39:29.328873Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.328873Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:f84b3f33377a06166f6672e8092c7c63011591c6eb98182ea99f3349a50297f1","observation_id":"bd403451-8e76-4bef-9936-cee8838cecd7","resolution":{"observed_at":"2026-08-15T22:39:29.328873Z","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":"2026-08-15T22:39:29.332058Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.332058Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:325fa31e776153d1ba3f6a377f559f5fab3fe6f8d4981a9832b409d4fc749eba","observation_id":"ed94dad0-ca7c-438d-a19b-eb5d6158d83e","resolution":{"observed_at":"2026-08-15T22:39:29.332058Z","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":"2026-08-15T22:39:29.335387Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.335387Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:2ea8110feb61b74cc2a00cc441e9ad43252893fee5b10bd8bcd4a7aeb005c90b","observation_id":"d1c753cb-8340-4f13-984f-884988351665","resolution":{"observed_at":"2026-08-15T22:39:29.335387Z","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":"2024.34662","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:39:31.318925Z","title":"Fedcrac: Improving federated classification performance on long-tailed data via classifier representation adjustment and calibration,","venue":null,"work_id":"fd9935ff-ca6d-4aa2-9192-8ab8ed499989","year":2025},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.339634Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1f7f06fceee7de61e04a9c5d9617cc181468bc5ddb223b10663a49c308919853","observation_id":"1ac77d1b-5330-45bc-b072-a9ceea16182e","resolution":{"observed_at":"2026-08-15T22:39:31.323999Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.342656Z","title":"Federated learning on non-iid data: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.342656Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:ba8058f2b01c62bfe5098dc1105c316cc6d8bb82941007d861bc181d8f63ac01","observation_id":"b7c57f4c-818b-4c76-90c2-bd811fff6aac","resolution":{"observed_at":"2026-08-15T22:39:29.342656Z","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":"2026-08-15T22:39:29.349269Z","title":"Agglomerative federated learning: Empowering larger model training via end-edge-cloud collaboration,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.349269Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1054dd2e3beeacde0faa07cbb8ecf7aa5e80be63635a8cf7ebf6877312386429","observation_id":"d3333987-4b03-4e34-bd4e-20553ff1eeac","resolution":{"observed_at":"2026-08-15T22:39:29.349269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08202","last_updated":"2023-11-14T14:37:33Z","snapshot_observed_at":"2026-08-16T14:43:25.105885Z","submitted_at":"2023-11-14T14:37:33Z","title":"Federated Skewed Label Learning with Logits Fusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08202","snapshot_observed_at":"2026-08-15T22:39:29.353241Z","title":"Federated skewed label learning with logits fusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.353241Z"},"links":{"cited_paper":"/paper/2311.08202","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7dfc4025dbe915b7969eb6ac318feb39519980024adcfd24e6fa61315c6d701a","observation_id":"6312ce50-5370-4d48-80ce-3f1b8067fb35","resolution":{"observed_at":"2026-08-15T22:39:29.353241Z","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":"2026-08-15T22:39:29.357643Z","title":"Fedlf: Adaptive logit adjustment and feature optimization in federated long-tailed learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.357643Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:3ed1c0eabd75289c445b330fd734f4b7311404de824014ba08f14e1ac541151a","observation_id":"d65df53a-6bf7-4145-9312-73d7d4ed3ec8","resolution":{"observed_at":"2026-08-15T22:39:29.357643Z","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":"2026-08-15T22:39:29.360890Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.360890Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:02ea6bb8a48ea75afb8546a2819e64b99853649afa77362185594d956c9012e9","observation_id":"2fa918c6-58dd-499e-86da-abd60084c969","resolution":{"observed_at":"2026-08-15T22:39:29.360890Z","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":"2026-08-15T22:39:29.363932Z","title":"Fedexp: Speeding up federated averaging via extrapolation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.363932Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:e70b3bf17e08082b452cbe7c8cdf026f3c3e6af193dbee876e12d2a909b8dcef","observation_id":"a74cf3e1-1674-4a9f-887e-378dfd7fa6ac","resolution":{"observed_at":"2026-08-15T22:39:29.363932Z","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":"2026-08-15T22:39:29.366959Z","title":"Mopro: Webly supervised learning with momentum prototypes,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.366959Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:f8acaa44f5fa41bfac419ce8d20b3da895dff14d1ab180fe8d9dcb1b30575a5c","observation_id":"daa338bd-ef8f-474b-a13d-ffeadb4ad4a1","resolution":{"observed_at":"2026-08-15T22:39:29.366959Z","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":"2026-08-15T22:39:29.369983Z","title":"Learning from massive noisy labeled data for image classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.369983Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:180f2673e585195e8996e4c1a74dfcc5ad4cdbc8cc1d83342e56a931f54cb986","observation_id":"fc077004-fcdf-4d39-8941-725fff546551","resolution":{"observed_at":"2026-08-15T22:39:29.369983Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T22:39:29.372963Z","title":"The open images dataset V4,","venue":null,"work_id":null,"year":1956},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.372963Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7f0b6b10fbefea04f023908f833cf330dcf52921b5e21191ebadf79f4a15e975","observation_id":"7eb0d646-ded2-479d-8e73-0ac3839eae18","resolution":{"observed_at":"2026-08-15T22:39:29.372963Z","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":"2026-08-15T22:39:29.376458Z","title":"Image- based recommendations on styles and substitutes,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.376458Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1ec1152cdbbd0b39c395bd0ef471086c753af151a29bf43ac224716580aaf21f","observation_id":"a7b9aae5-c073-4574-81c2-187991c38964","resolution":{"observed_at":"2026-08-15T22:39:29.376458Z","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":"2026-08-15T22:39:29.379845Z","title":"Pervasive label errors in test sets destabilize machine learning benchmarks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.379845Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:08c8e2809e1c9e7cdf246647a5bae06abe73abdac44d926d6b1cb58c458c63d0","observation_id":"03efb105-530e-4e06-8f76-08672ad2a8d5","resolution":{"observed_at":"2026-08-15T22:39:29.379845Z","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":"2026-08-15T22:39:29.382712Z","title":"Robustfed: A truth inference approach for robust federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.382712Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:43865ed0bad46f2db8c5965c4d3939eb14081a6735c21014d613b90d6a22230c","observation_id":"415b51d3-241a-4883-806a-d916d4bbabaf","resolution":{"observed_at":"2026-08-15T22:39:29.382712Z","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":"2026-08-15T22:39:29.385793Z","title":"Incentive mechanism for horizontal federated learning based on reputation and reverse auction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.385793Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:9d0e08d270269aa2eefd48ddb208ac582dbaa5774b97e95b10bf62b7cfe481c0","observation_id":"12ef87a6-0717-4df4-bdfa-51ef1fd3227b","resolution":{"observed_at":"2026-08-15T22:39:29.385793Z","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":"2026-08-15T22:39:29.388659Z","title":"Regulation (EU) 2016/679 of the European Parliament and of the Council","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.388659Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:252be6340918533d3336089a21fb47a9a2a84a40a502c509234f7ecdc659c708","observation_id":"13d9ccba-7eb4-4b91-bbe5-87c832ed2ee5","resolution":{"observed_at":"2026-08-15T22:39:29.388659Z","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":"2026-08-15T22:39:29.391561Z","title":"Federated learning with unreliable clients: Performance analysis and mechanism design,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.391561Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:b828c761a091190698299b3532e62796c3353b0f5e57758200622af5ef08f4a0","observation_id":"a8fcb2f5-20fe-4d95-b378-253179c61b57","resolution":{"observed_at":"2026-08-15T22:39:29.391561Z","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":"2026-08-15T22:39:29.398231Z","title":"A closer look at memorization in deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.398231Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:890823d0d4d68f4e8f0c145a79d8ad13cbfa4110205ad97159a4a162f7dc645a","observation_id":"5d767ffc-1207-4ad7-8c1e-5c8f522d22ec","resolution":{"observed_at":"2026-08-15T22:39:29.398231Z","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":"2026-08-15T22:39:29.402836Z","title":"Learning from noisy labels with deep neural networks: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.402836Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:144efe1165243d7dd12d6a746e8c8c6f38f3676e644e546011dfac5bb4c63d5d","observation_id":"8cf94a51-c1a3-4c52-a5d5-cbe4be724da6","resolution":{"observed_at":"2026-08-15T22:39:29.402836Z","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":"2026-08-15T22:39:29.405955Z","title":"How does disagreement help generalization against label corruption?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.405955Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:b7e1f38522501866e79e06edd491d58b730977329c64505b1e06948f2289cb59","observation_id":"c6893ac6-cf1a-401c-92ae-4634e7875fb5","resolution":{"observed_at":"2026-08-15T22:39:29.405955Z","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":"2026-08-15T22:39:29.409857Z","title":"Joint optimization framework for learning with noisy labels,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.409857Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:e3bda1035d180d07b506a4800ee125642be20bc625f4567e5f03063999d1d49b","observation_id":"7e953e0a-24ef-4ebc-a36d-ca1edbdcdcea","resolution":{"observed_at":"2026-08-15T22:39:29.409857Z","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":"2026-08-15T22:39:29.414000Z","title":"SELFIE: refurbishing unclean samples for robust deep learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.414000Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:be4cd57a69f22b1f378249938f52fcaf1eca43a927274268f7025839f6089b7d","observation_id":"058a6e8a-ae58-4b4f-a3f7-a351750810ae","resolution":{"observed_at":"2026-08-15T22:39:29.414000Z","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":"2026-08-15T22:39:29.417725Z","title":"Symmetric cross entropy for robust learning with noisy labels,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.417725Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:aa3f119620836b8ac20ebdb48eac6f8e65a81c695cce58bd9ff4ea9a5661533d","observation_id":"25c459a1-6459-4f3c-850c-69412e239714","resolution":{"observed_at":"2026-08-15T22:39:29.417725Z","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":"2026-08-15T22:39:29.425184Z","title":"Robust loss functions under label noise for deep neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.425184Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:fe257af9b46fb5ba1a1c6c9cd315f3bff94f44075bf82b0493e0f91d2c4d726b","observation_id":"5f6d199c-fa0c-4524-8298-2fe7603ae18d","resolution":{"observed_at":"2026-08-15T22:39:29.425184Z","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":"2026-08-15T22:39:29.429477Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.429477Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:513643690b797902cdf558200e18105ed6eb25b0e2d7e2ea179f444a8e17cadc","observation_id":"bb738884-11e0-44f5-99ad-09c0b6922e12","resolution":{"observed_at":"2026-08-15T22:39:29.429477Z","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":"2026-08-15T22:39:29.433789Z","title":"Dividemix: Learning with noisy labels as semi-supervised learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.433789Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:a50b005d8fe56d4281d85ba054c311779bca1dec55a4c73c2190392295b449b4","observation_id":"4b39323b-d1ff-4ec0-b0d3-46b7d282280e","resolution":{"observed_at":"2026-08-15T22:39:29.433789Z","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":"2026-08-15T22:39:29.437937Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.437937Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:4096b6d9c5257ad80e27ba70cef2f2baffeae8773594f30348ba4e82b30eddde","observation_id":"59b100dd-7283-4034-b3ae-9cbd1a788da3","resolution":{"observed_at":"2026-08-15T22:39:29.437937Z","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":"2026-08-15T22:39:29.445525Z","title":"Mixmatch: A holistic approach to semi-supervised learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.445525Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:36c1541be94aa8398b41037bc861d5624e23390312579ba4f080dc922e35c54b","observation_id":"b12135d8-7ede-479f-bd6a-721fb8582027","resolution":{"observed_at":"2026-08-15T22:39:29.445525Z","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":"2026-08-15T22:39:29.450429Z","title":"Early-learning regularization prevents memorization of noisy labels,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.450429Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:db70f1001b36de504d4564d62dd8202b532aba0a65ec7c7c2c2312c7984788aa","observation_id":"95ef0ec5-0cc7-40a2-9408-143220c38f3f","resolution":{"observed_at":"2026-08-15T22:39:29.450429Z","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":"2026-08-15T22:39:29.454502Z","title":"Learning with noisy labels,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.454502Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:c67c503def0c4a2b4dfe547f23d6423a999c50e99d19b2f7bffa7a49ac24ae6e","observation_id":"d1b19521-bfc1-4b32-9e81-0f2af1e6d017","resolution":{"observed_at":"2026-08-15T22:39:29.454502Z","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":"2026-08-15T22:39:29.463216Z","title":"Fedcorr: Multi-stage federated learning for label noise correction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.463216Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:e6ff82ca4a79c0d7d1bc48f4ed30aef81d8117611899a43a69f7a8906a10c780","observation_id":"6fbc9e60-1d20-4158-a9e7-b93f10f6c697","resolution":{"observed_at":"2026-08-15T22:39:29.463216Z","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":"2026-08-15T22:39:29.466182Z","title":"Learning cautiously in federated learning with noisy and heterogeneous clients,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.466182Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:69a43430e98066ee8cfce754e38d825914722bceeca5121bff0c558c5734a015","observation_id":"33c61ab6-22b5-4517-8c76-80420de3017a","resolution":{"observed_at":"2026-08-15T22:39:29.466182Z","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":"2026-08-15T22:39:29.470193Z","title":"On the number of components in a gaussian mixture model,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.470193Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:e4ed5eb95475596e813e7112e75c53b68e1d3d7697d08cf3cc9cfa8416b8d969","observation_id":"1fd977d7-fbb2-4e56-a246-4f3e87176591","resolution":{"observed_at":"2026-08-15T22:39:29.470193Z","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":"2026-08-15T22:39:29.474197Z","title":"Federated learning with extremely noisy clients via negative distillation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.474197Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:43ec470617e586748c31cbfbfbb147748503031403c29bb13c024c34ab7c1960","observation_id":"6186c5bb-aa63-4bfe-a08d-2991984c662f","resolution":{"observed_at":"2026-08-15T22:39:29.474197Z","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":"2026-08-15T22:39:29.478406Z","title":"Fedelr: When federated learning meets learning with noisy labels,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.478406Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:588612c03a64ac9b302f958ecc4de0e7eb4b3a230d7aad7ddd0263e2f0c1c533","observation_id":"ae1e639f-9fe4-4393-a661-b3dbe032de65","resolution":{"observed_at":"2026-08-15T22:39:29.478406Z","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":"2026-08-15T22:39:29.483155Z","title":"Agrevader: Poisoning membership inference against byzantine-robust federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.483155Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7e286c69f3a245e26d87b51467278350078cdfd8ee3a973e58492c58335aa01b","observation_id":"a99ca825-530c-4e47-9791-ffaef7d30d82","resolution":{"observed_at":"2026-08-15T22:39:29.483155Z","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":"2026-08-15T22:39:29.490750Z","title":"Robust aggregation for federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.490750Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:d8849173592f8949348032c1f84187a277336819e8c54ce8b7f6fe40c7b2e706","observation_id":"2bdbc603-a5c9-402d-a31b-74a2e850c9d8","resolution":{"observed_at":"2026-08-15T22:39:29.490750Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T22:39:29.494673Z","title":"Ditto: Fair and robust federated learning through personalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.494673Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:3353383d3776a8469a013ff52dafec56c876145ed067e5cee2dd2d2d51dec23b","observation_id":"7feac19e-76b7-4fd2-911e-1f23e7684da1","resolution":{"observed_at":"2026-08-15T22:39:29.494673Z","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":"2026-08-15T22:39:29.498689Z","title":"Byzantine-robust distributed learning: Towards optimal statistical rates,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.498689Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:dabcdac041838b8e4941effe1649f04b29ec710142ec843f8d112a5c61d966e5","observation_id":"e6c9beb0-9c5a-4106-b1ac-d9df9f2fade1","resolution":{"observed_at":"2026-08-15T22:39:29.498689Z","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":"2026-08-15T22:39:29.502818Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.502818Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:eeb691622485c4787dbe83438cfa4d23f8e20c7ad2e867d4861723d3e58c1e3a","observation_id":"259c3b7b-20b1-48fb-bb4c-037128f96602","resolution":{"observed_at":"2026-08-15T22:39:29.502818Z","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":"2026-08-15T22:39:29.505800Z","title":"FedScale: Benchmarking model and system performance of federated learning at scale,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.505800Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:8476f0c0a7697b90f412215e4d2087423255d948c85529b38fc2ca7451825e35","observation_id":"6fb92e43-3081-4c52-92ad-b307fae988b1","resolution":{"observed_at":"2026-08-15T22:39:29.505800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.13518","last_updated":"2020-11-08T19:34:25Z","snapshot_observed_at":"2026-08-15T04:01:16.573126Z","submitted_at":"2020-07-27T13:02:08Z","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.13518","snapshot_observed_at":"2026-08-15T22:39:29.509737Z","title":"Fedml: A research library and benchmark for federated machine learning,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.509737Z"},"links":{"cited_paper":"/paper/2007.13518","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:dd98f248398727880e9458538b3a96fe879021f14cd86210a38256b3cb2611ba","observation_id":"f0a5f8e1-2eca-4f00-a92e-73c91a82145d","resolution":{"observed_at":"2026-08-15T22:39:29.509737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-16T19:49:29.879809Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-15T22:39:29.513923Z","title":"LEAF: A benchmark for federated settings,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.513923Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:cd607c5f5dbdce26a670424365aa40046b282f78b9b530bfb9607d761d08d166","observation_id":"bcf0abc6-ade0-4854-80c4-c7fca4f86e4b","resolution":{"observed_at":"2026-08-15T22:39:29.513923Z","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":"2026-08-15T22:39:29.518507Z","title":"How asynchronous can federated learning be?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.518507Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:eeb9d97e6fceab06236514808444f71b7be4e89e73c74a1b0d647ae2bb89ae43","observation_id":"fad917eb-4ae1-4050-87bc-897cc0513750","resolution":{"observed_at":"2026-08-15T22:39:29.518507Z","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":"2026-08-15T22:39:29.522677Z","title":"Fedlab: A flexible federated learning framework,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.522677Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:71daca34cd3117b69922d77139cdf42c7051c83f9adcf410e96cb98a22e7a19e","observation_id":"04508d4e-a63c-4c64-bc19-c3bf7e6e6007","resolution":{"observed_at":"2026-08-15T22:39:29.522677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11650","last_updated":"2025-02-22T06:52:04Z","snapshot_observed_at":"2026-08-16T15:22:29.829002Z","submitted_at":"2023-06-20T16:18:14Z","title":"FedNoisy: Federated Noisy Label Learning Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11650","snapshot_observed_at":"2026-08-15T22:39:29.526138Z","title":"Fednoisy: Federated noisy label learning benchmark,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.526138Z"},"links":{"cited_paper":"/paper/2306.11650","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:8a669bda93e52c6a865ea841fa55cdddefb64b4a9a4a91d04397b5124be5274a","observation_id":"a4b3eddd-5d40-41ab-83e8-5ab525901644","resolution":{"observed_at":"2026-08-15T22:39:29.526138Z","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":"2026-08-15T22:39:29.531248Z","title":"Communication efficient distributed machine learning with the parameter server,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.531248Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:b55a604aae31dd71c969b9d3c3def0645453a15aaaaada5f232e0f2284abf734","observation_id":"4ccb9f7d-173d-4b61-ba48-f04e4412eaea","resolution":{"observed_at":"2026-08-15T22:39:29.531248Z","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":"2026-08-15T22:39:29.535337Z","title":"Character-level convolutional networks for text classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.535337Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:216dfcf55e65620c0e40c8d8412077c3dca3573b53ea52f66eb54edb41d7f4fc","observation_id":"4a3768b9-b2a1-4122-b456-af43accb4a8c","resolution":{"observed_at":"2026-08-15T22:39:29.535337Z","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":"2026-08-15T22:39:29.539439Z","title":"Learning with noisy labels revisited: A study using real-world human annotations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.539439Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:f22d090e2bb4948abb83c00e9e0abee105a132dc17f53c3ac18727618bad61c1","observation_id":"1a8942a8-ce7b-4bc2-b97d-70fe4057f379","resolution":{"observed_at":"2026-08-15T22:39:29.539439Z","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":"2026-08-15T22:39:29.543413Z","title":"Labeling chaos to learning harmony: Federated learning with noisy labels,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.543413Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:ec4a3a33397ae324e9c7d2ae95e3aa36b1707b296abe8ff34b1639b3e213e37f","observation_id":"01343b49-46c8-48d8-9e4b-087fa6e60de3","resolution":{"observed_at":"2026-08-15T22:39:29.543413Z","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":"2026-08-15T22:39:29.550853Z","title":"Learning with symmetric label noise: The importance of being unhinged,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.550853Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:ed94268db6e32b74380b638d8e4c9185af403dc27980547baee0ce53545a7490","observation_id":"c93c9ef7-6752-4403-9893-e2edeeaf6dab","resolution":{"observed_at":"2026-08-15T22:39:29.550853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.16519","last_updated":"2022-10-29T07:20:02Z","snapshot_observed_at":"2026-08-16T16:20:09.808997Z","submitted_at":"2022-10-29T07:20:02Z","title":"Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.16519","snapshot_observed_at":"2026-08-15T22:39:29.554758Z","title":"Security-preserving federated learning via byzantine-sensitive triplet distance,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.554758Z"},"links":{"cited_paper":"/paper/2210.16519","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:01cca0aa5142fdc106f19469a133ecf3fb95c793e311974321e864db655a448a","observation_id":"3ab78f08-06e8-4657-9407-d0ecb2c2c328","resolution":{"observed_at":"2026-08-15T22:39:29.554758Z","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":"2026-08-15T22:39:29.563320Z","title":"Understanding deep learning requires rethinking generalization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.563320Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:f8b87009dc7a64db2c152b64981ae44326d85533b6660c10b5993e0487790285","observation_id":"3ec53a2a-e053-4e04-b7cd-a7bff6924619","resolution":{"observed_at":"2026-08-15T22:39:29.563320Z","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":"2026-08-15T22:39:32.322360Z","title":"Understanding dimensional collapse in contrastive self-supervised learning,","venue":null,"work_id":"3adc0d80-47d8-44f7-b49a-92a7da69b45f","year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.567080Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:3a8384e9ab5d2e6525a5b81421c99369291c71e2781b8109900f03927e1ec007","observation_id":"cf69bdbc-1ae6-41b4-84e1-a137c34bfb0f","resolution":{"observed_at":"2026-08-15T22:39:32.326116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1410.2024","last_updated":"2014-10-14T14:44:42Z","snapshot_observed_at":"2026-08-14T23:16:32.816396Z","submitted_at":"2014-10-08T08:45:37Z","title":"Bilayer-induced asymmetric quantum Hall effect in epitaxial graphene","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.2024","snapshot_observed_at":"2026-08-15T22:39:29.571370Z","title":"SA-SVD: mitigating bias in face recognition by fair representation learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.571370Z"},"links":{"cited_paper":"/paper/1410.2024","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:e184a186658c0bf257826a234fd18396cdf4bd44fca8095cd2c59d962183e0bf","observation_id":"e37f78cd-d9aa-46c4-9187-a27edb24febb","resolution":{"observed_at":"2026-08-15T22:39:29.571370Z","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":"2026-08-15T22:39:32.311083Z","title":"Model-contrastive federated learning,","venue":null,"work_id":"1f4a7e52-5246-462a-982f-f62461815e89","year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.575250Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:fc2493c3f62b5d8aeb11a7a254cb474d19ed7f70621ff420d25093d455fcaf1d","observation_id":"530f6055-cf0b-49b0-8625-0cc820191fc0","resolution":{"observed_at":"2026-08-15T22:39:32.314374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.300559Z","title":"Correlated-pca: Principal components’ analysis when data and noise are correlated,","venue":null,"work_id":"e9db67cb-22d5-42c9-b3f2-d53d5fd1fca8","year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.578764Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:51236838513a67c0e0d7879e5539dc9fd8091f7ab54c14c9c9ae7c7b64489247","observation_id":"517426ef-5a97-4151-aaee-7059e486bd97","resolution":{"observed_at":"2026-08-15T22:39:32.304191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1508.28157","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:39:30.557144Z","title":"An O(n3) algorithm for the frobenius normal form,","venue":null,"work_id":"05040dc6-5773-4b83-baf9-d2cc3e2de944","year":1998},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.586613Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:60251fa901df69dcc8fcb88a3eda66f2f7da274eb777ea68e6b8ae792ca3b824","observation_id":"b9b99e1f-e7eb-4151-b7ed-1c64667a518c","resolution":{"observed_at":"2026-08-15T22:39:30.562373Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.547005Z","title":"Available: https://doi.org/10.1145/3626242","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.547005Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:5cf2586480f3145aab8d24600f07128714837e89c798fd98df44b4ce2418dfc6","observation_id":"7d18b13d-c7b1-4c84-87fc-f3b7e0e7937d","resolution":{"observed_at":"2026-08-15T22:39:29.547005Z","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":"2026-08-15T22:39:29.594172Z","title":"Unsupervised ensemble learning with noisy label correction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.594172Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:6eb89354afc2f9486455f21a4c9d5e33c359e6924780f1971a1015810183129c","observation_id":"8b64b1f7-22d4-453f-b63b-5588eb4f3a35","resolution":{"observed_at":"2026-08-15T22:39:29.594172Z","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":"2026-08-15T22:39:32.268043Z","title":"Understanding and utilizing deep neural networks trained with noisy labels,","venue":null,"work_id":"e1cff8f0-94ca-49c7-b9fd-1f949fc398cf","year":2019},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.597772Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:691241ef62752cbbb8cb6235820ad09a35485633218bef9b1ab2f884679fdeba","observation_id":"ac6d1de4-5a9e-4036-97ec-7d82c6f67420","resolution":{"observed_at":"2026-08-15T22:39:32.271595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.16519","last_updated":"2022-10-29T07:20:02Z","snapshot_observed_at":"2026-08-16T16:20:09.808997Z","submitted_at":"2022-10-29T07:20:02Z","title":"Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance","version":1},"cited_work":{"arxiv_id":"2210.16519","doi":"10.48550/arxiv.2210.16519","metadata_source":"pith","pith_arxiv_id":"2210.16519","snapshot_observed_at":"2026-08-16T12:16:17.039197Z","title":"Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance","venue":"cs.LG","work_id":"ef59161c-8371-43ab-bb09-ce0e825c238a","year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.558640Z"},"links":{"cited_paper":"/paper/2210.16519","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:b421b6247592accace628258e84adf92a0707a0054b94674e94213c8bec52158","observation_id":"0ac8f89b-beaa-4115-bd5b-65f394f6c40f","resolution":{"observed_at":"2026-08-15T22:39:29.805119Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.607455Z","title":"Bag of tricks for efficient text classification,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.607455Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:1d13e550d0ae8eeed9d7ce459f8651a74a21cd917a2a829a46d0e8f77322103b","observation_id":"1b1d3fcc-47ae-4ac0-8e63-32ef3440a62a","resolution":{"observed_at":"2026-08-15T22:39:29.607455Z","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":"2026-08-15T22:39:29.610823Z","title":"Overcoming noisy labels in federated learning through local self-guiding,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.610823Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:81d75fbe4d30a78a196cef7165aaf449d34934f72c9b94b22bc5b0b0b0eb4d3e","observation_id":"4525e104-664a-4ffa-9510-72674398c8fb","resolution":{"observed_at":"2026-08-15T22:39:29.610823Z","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":"2026-08-15T22:39:29.614322Z","title":"Self-filtering: A noise-aware sample selection for label noise with confidence penalization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.614322Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:abe308537e3eaf2e9e14ea531fc0f0317100a01afda7221728be69c8ba5fb4f4","observation_id":"87259fae-3943-4e36-90cc-a655fa1787c2","resolution":{"observed_at":"2026-08-15T22:39:29.614322Z","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":"was/2018031","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:39:30.400822Z","title":null,"venue":null,"work_id":"e33c6a02-08c2-45d8-996b-d8b8feec5cfa","year":2009},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.618023Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:6a365ea55cd4e6e569ba8e052d9283a0c812b70aa1938d68a5ebceb26fc9a974","observation_id":"af87f71a-44ea-4617-b489-7e5e4a5c8147","resolution":{"observed_at":"2026-08-15T22:39:30.405552Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.234323Z","title":null,"venue":null,"work_id":"21cf6de5-bf1e-4146-a028-d14ad82a8c55","year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.622119Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:b0096318ac87108d6404c7d35a4de8afc82101902659d4b72f440d43c8b4508b","observation_id":"a14c98c1-ebad-4047-b2cd-e07d0515a5eb","resolution":{"observed_at":"2026-08-15T22:39:32.238391Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.223321Z","title":"Robust heterogeneous federated learning under data corruption,","venue":null,"work_id":"ad92529f-d482-4fc9-b753-44311b36dc34","year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.625179Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:c08a03909749e2eabea6dc2f72e158120ea1d6ed0d676f736805e3169d09ef64","observation_id":"7351f47d-9125-4bab-a167-42350f064935","resolution":{"observed_at":"2026-08-15T22:39:32.226598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.213137Z","title":"Quantifying and mitigating the impact of label errors on model disparity metrics,","venue":null,"work_id":"3f15f937-c18c-455c-a83c-2d70e63e9d80","year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.633367Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:092f77fac71a29531997edd17b0820fda795e8454d6e55297b3f354a62198fff","observation_id":"15ec7e3c-72f0-47a1-9142-5d082a41c5a8","resolution":{"observed_at":"2026-08-15T22:39:32.216461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.278914Z","title":"Paszke, S","venue":null,"work_id":"be7b9714-13e7-4d74-8309-5147e21aa06f","year":2017},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.590288Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:afbafe725f967a3e7674761455d2cefdd511c937d4ea28b23077c3daf6a6fa07","observation_id":"000d1dce-c527-4e9b-ab38-5f53c1e3d46c","resolution":{"observed_at":"2026-08-15T22:39:32.282696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18905","last_updated":"2024-11-28T04:37:04Z","snapshot_observed_at":"2026-08-14T10:05:32.141796Z","submitted_at":"2024-11-28T04:37:04Z","title":"FedRGL: Robust Federated Graph Learning for Label Noise","version":1},"cited_work":{"arxiv_id":"2411.18905","doi":"10.48550/arxiv.2411.18905","metadata_source":"pith","pith_arxiv_id":"2411.18905","snapshot_observed_at":"2026-08-16T12:16:17.039197Z","title":"FedRGL: Robust Federated Graph Learning for Label Noise","venue":"cs.LG","work_id":"f68d6eb8-5ce6-418f-9720-8ce92e1d5eef","year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.641941Z"},"links":{"cited_paper":"/paper/2411.18905","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:a42f594fc8723f183bb3c91a896889047adccfbcd88696f2f3ed59d6dcce5d45","observation_id":"ffce05e6-b696-4a92-a9f3-55a7fd12dbb4","resolution":{"observed_at":"2026-08-15T22:39:29.776846Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.645416Z","title":"Feda3i: Annotation quality- aware aggregation for federated medical image segmentation against heterogeneous annotation noise,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.645416Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:995f964ffff7e919ad43645ee336cb6c3da8de76defde9d9ae553c0367e9146a","observation_id":"11c1fa22-fc8d-4c65-bee7-6ce9cbc854a2","resolution":{"observed_at":"2026-08-15T22:39:29.645416Z","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":"2026-08-15T22:39:32.256848Z","title":"Mixed precision training,","venue":null,"work_id":"a2b61181-f219-47cd-9791-a90a968a4022","year":2018},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.600668Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7eb513fd8373e2113d299fff7337415a45edd6d1c7b655a4d7944bbdf5816174","observation_id":"bc47a904-a549-4400-87ee-7be0a3e287ab","resolution":{"observed_at":"2026-08-15T22:39:32.260376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.246108Z","title":"Available: https://openreview.net/forum?id=r1gs9JgRZ","venue":null,"work_id":"4a5500bf-03d2-4437-892f-5c648544f839","year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.603949Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7405303dd22831097c7fcf78e0f2f994971ecb7079b61318af2938a032033ebd","observation_id":"04ef8977-7e1d-45f1-8181-81dcce4c9a7b","resolution":{"observed_at":"2026-08-15T22:39:32.249907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:32.195758Z","title":"Augmentation strategies for learning with noisy labels,","venue":null,"work_id":"2e299db4-e955-471a-99a7-afdb27b18d1b","year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.657736Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:4560c642edbe73130228acb755ea04d6de8eb855d2f668c3b8a2a3942786943f","observation_id":"3d8a3d14-67fd-4bdb-ac83-2e77646b4bf4","resolution":{"observed_at":"2026-08-15T22:39:32.199704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:39:29.661465Z","title":"Sample-level data selection for federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.661465Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:d730281763d2ea63818d6d05bcde6cdcbefbb248ef365b8579f05b874ed4a4e7","observation_id":"235dbf75-94b0-4929-b6b6-baad77127ca2","resolution":{"observed_at":"2026-08-15T22:39:29.661465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10110","last_updated":"2022-05-20T12:06:39Z","snapshot_observed_at":"2026-08-16T16:58:55.344813Z","submitted_at":"2022-05-20T12:06:39Z","title":"FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10110","snapshot_observed_at":"2026-08-15T22:39:29.665646Z","title":"Fednoil: A simple two-level sampling method for federated learning with noisy labels,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.665646Z"},"links":{"cited_paper":"/paper/2205.10110","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:f92ff0f218c5ac3b7bac192b3639f6a2edb2d42bbafbabf5201caaab4f527e5e","observation_id":"6bb88e30-86a0-48a3-8193-b552535ebeeb","resolution":{"observed_at":"2026-08-15T22:39:29.665646Z","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":"2026-08-15T22:39:32.185264Z","title":"Smote-variants: A python implementation of 85 minority oversampling techniques,","venue":null,"work_id":"39f27ba3-4188-4881-8b35-083047368d4a","year":null},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.670131Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:53180587004ffe7faa4925af44aabb4ea807912c74bab84496a7314831a38de1","observation_id":"38c39451-55f7-46a9-bc14-c26ba1bc671f","resolution":{"observed_at":"2026-08-15T22:39:32.188833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05025","last_updated":"2023-07-11T05:58:20Z","snapshot_observed_at":"2026-08-16T15:17:15.010703Z","submitted_at":"2023-07-11T05:58:20Z","title":"Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05025","snapshot_observed_at":"2026-08-15T22:39:29.678169Z","title":"Unleashing the potential of regularization strategies in learning with noisy labels,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.678169Z"},"links":{"cited_paper":"/paper/2307.05025","citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:99e47c3f32f4d80b06a20e9ac9383e1b7e7f33e2bd7b0a3db9f1b49674f363a3","observation_id":"4c3f64cf-4936-4388-92c7-5680432da2cf","resolution":{"observed_at":"2026-08-15T22:39:29.678169Z","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":"2026-08-15T22:39:29.682066Z","title":"Communication-efficient robust federated learning with noisy labels,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.682066Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:7f6ffd03f2d9297fa900f2b92817183b022cadcbb988174f3dc924945e19a702","observation_id":"149eb866-2f44-4f59-be37-314fd2b8dc5b","resolution":{"observed_at":"2026-08-15T22:39:29.682066Z","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":"2026-08-15T22:39:29.628762Z","title":"4997–5007","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","version":1},"reference_index":105,"source":"pdf_text","source_observed_at":"2026-08-15T22:39:29.628762Z"},"links":{"citing_paper":"/paper/2505.06684"},"observation_digest":"sha256:96d790cb0b74eab782c3043bad5e7b3471c0307bca936e57db8f88cc104ed8de","observation_id":"409a5ff9-af21-4948-b452-ba02e73e258f","resolution":{"observed_at":"2026-08-15T22:39:29.628762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.06684","last_updated":"2025-05-10T16:14:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T19:50:13.727637Z","submitted_at":"2025-05-10T16:14:52Z","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":3,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":80,"verified_exact":4,"verified_fuzzy":11},"total_outbound_references":119},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 100 of 119 outbound references and 2 inbound Pith citation observations for arXiv:2505.06684."}