{"as_of":"2026-08-08T02:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:80ef38de804b90577aa774747d6ef8ad6ee9f9d5e8cc5b8d9ddb387a6e65be38","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:43:25.494823Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.14024/citation-record","integrity":"/paper/2505.14024/integrity","json":"/paper/2505.14024/citation-record.json","paper":"/paper/2505.14024"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:43:38.494749Z","title":"Baffle: Backdoor detection via feedback-based federated learning","venue":null,"work_id":"1e034a3c-fab6-4d44-8654-e4eab5080daa","year":2021},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:18.482999Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:865ca7f034a1d019069653d7dfef0d2d17c327aa54654cab22146bb4bbd08db1","observation_id":"63509926-7e2d-4989-9ac7-86895e216e20","resolution":{"observed_at":"2026-08-07T15:43:38.634861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.00459","last_updated":"2019-08-06T04:36:45Z","snapshot_observed_at":"2026-08-07T03:33:38.635570Z","submitted_at":"2018-07-02T04:37:43Z","title":"How To Backdoor Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.00459","snapshot_observed_at":"2026-08-07T15:43:18.557553Z","title":"How to backdoor federated learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:18.557553Z"},"links":{"cited_paper":"/paper/1807.00459","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:252472e4a66bf5e7c0b93ad54ffe48f5e3e1eb694acc5ea4b99f3273c1e14ac8","observation_id":"126fd1c1-5425-4abe-b5a9-4ea768723bc9","resolution":{"observed_at":"2026-08-07T15:43:18.557553Z","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":"2026-08-07T15:43:38.243368Z","title":"A little is enough: Circumventing defenses for distributed learning","venue":null,"work_id":"985d58a4-d2f7-434d-bca5-a94ea4aee788","year":2019},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:18.661187Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:5b0de17e7d88ab3f4869717a927dd55d391b7f61e5963c30b4394135e9a01bd4","observation_id":"661640f1-172f-4f1b-9914-fa7ee3858f32","resolution":{"observed_at":"2026-08-07T15:43:38.324752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:37.954571Z","title":"Analyzing feder- ated learning through an adversarial lens","venue":null,"work_id":"3172de0b-553b-4c30-844f-1f1d5e6147d6","year":2019},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:18.796107Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:ff942d951894471d2fef65bb59d72a277d163658302f0d8d0d9a603fac13e0bd","observation_id":"be79534b-1f77-4de9-aaa9-7ece9a2e453e","resolution":{"observed_at":"2026-08-07T15:43:38.106423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:37.656898Z","title":"Machine learn- ing with adversaries: Byzantine tolerant gradient descent","venue":null,"work_id":"1651a02f-8a99-4b2d-9cec-187c59a7ad37","year":2017},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:18.934333Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a681fa3a9a90f6a1915bb13549ab86318da7d5e237cc421aa1d00dcfd3583b2b","observation_id":"e03d196d-1ce1-4878-9210-6936a965f745","resolution":{"observed_at":"2026-08-07T15:43:37.832976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:37.311101Z","title":"Understanding distributed poisoning attack in federated learning","venue":null,"work_id":"4135bd85-d0fb-41b7-9fde-61f7d9c809a6","year":2019},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.043899Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a3a1e345559ff7be98be3d4aa48e5cc15fcac8001d7e03a506757980c3ccc06a","observation_id":"52b4edcd-201b-4298-b18e-6d5e88e14792","resolution":{"observed_at":"2026-08-07T15:43:37.436737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13995","last_updated":"2022-04-12T01:56:47Z","snapshot_observed_at":"2026-07-06T10:28:06.533127Z","submitted_at":"2020-12-27T18:43:39Z","title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13995","snapshot_observed_at":"2026-08-07T15:43:19.169271Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.169271Z"},"links":{"cited_paper":"/paper/2012.13995","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:63c64c3b8c9bfea2251bbc5b19cfad437a3fba37f028976d7ae2b73c876b4b34","observation_id":"18a2b53e-abff-4f02-a7d8-442ea81372d0","resolution":{"observed_at":"2026-08-07T15:43:19.169271Z","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":"2026-08-07T15:43:37.021505Z","title":"Mpaf: Model poisoning attacks to federated learning based on fake clients","venue":null,"work_id":"a0403a23-4b03-40d4-82c4-fe3f79ff7152","year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.453623Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a77ab0b994731adcf1550fb4504a30248dc2edbaf0b4f1703db45e01d50e2401","observation_id":"9738aa72-ea0f-4aa4-a083-e94c8e4bdb36","resolution":{"observed_at":"2026-08-07T15:43:37.142437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:36.790893Z","title":"Towards multi-party targeted model poisoning attacks against federated learning systems","venue":null,"work_id":"1944c78d-3774-45cc-893c-e1e1e1a2530a","year":2021},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.577375Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:4a9bb25d5e3fdbc83742b67cb1113b969714b4c83f79e038e30f46c3e880a1c8","observation_id":"a51a2da2-a76b-47c9-8f09-85333185c066","resolution":{"observed_at":"2026-08-07T15:43:36.903248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:36.561722Z","title":"Local model poisoning attacks to {Byzantine-Robust} federated learning","venue":null,"work_id":"2181338f-b3b0-491a-82ad-6e33c62fff05","year":2020},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.755867Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:90c37db907c0bfd1bab472d00b12acc12dce36fd5a08c7ca734ff98ca3587819","observation_id":"f6904867-0918-4a2b-9a7f-7784c8b0ebb8","resolution":{"observed_at":"2026-08-07T15:43:36.645900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17381","last_updated":"2025-01-29T02:28:03Z","snapshot_observed_at":"2026-08-04T22:56:55.182475Z","submitted_at":"2025-01-29T02:28:03Z","title":"Do We Really Need to Design New Byzantine-robust Aggregation Rules?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17381","snapshot_observed_at":"2026-08-07T15:43:19.864924Z","title":"Do we really need to design new byzantine-robust aggregation rules? arXiv preprint arXiv:2501.17381, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.864924Z"},"links":{"cited_paper":"/paper/2501.17381","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:c15cecd4cff0cfee9ad9e5e76f895abe2be47607f6c2163e4864adcc74e2569c","observation_id":"f2fade37-6539-4816-987c-4b93406357b7","resolution":{"observed_at":"2026-08-07T15:43:19.864924Z","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":"2026-08-07T15:43:36.297229Z","title":"Badnets: Evaluating backdooring attacks on deep neural networks","venue":null,"work_id":"f1bb3b5f-fe68-400a-8a61-45da41d9a1b6","year":2019},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:19.965750Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:ce641fb8fb755e41882ca665b26762e84595f1036deeff94fb97995eb194c52f","observation_id":"aa4e3c00-2386-479d-b6d4-22921f127d27","resolution":{"observed_at":"2026-08-07T15:43:36.417058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:20.104688Z","title":"The hidden vulnerability of distributed learning in byzantium","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.104688Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:00a7bdbd3c8d5aae4818ed0b4897e5dd58b2732aec0eaf5f12009344bc872bc0","observation_id":"919a327f-9c77-4c8c-b9bb-d1e61f54196d","resolution":{"observed_at":"2026-08-07T15:43:20.104688Z","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":"2026-08-07T15:43:36.124234Z","title":"Flmjr: Improving robustness of federated learning via model stability","venue":null,"work_id":"8245ef05-05a4-453b-9b5f-c559a209343b","year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.224166Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:c3bb8a740edb2b2ddd54d88817029d7c2e9d4324fd1e86048bee83327653eff8","observation_id":"7a229f86-7a93-4760-80a5-43f8c6306c65","resolution":{"observed_at":"2026-08-07T15:43:36.229202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:20.389062Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.389062Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:00ff0dcaa2a380efa3fa92c9beda328c8fe987332b1f11399c7e649e0e8caaef","observation_id":"bff77564-cb56-45d6-be6e-a87b816ed28b","resolution":{"observed_at":"2026-08-07T15:43:20.389062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.09365","last_updated":"2023-11-22T09:08:15Z","snapshot_observed_at":"2026-08-07T05:21:15.626151Z","submitted_at":"2020-06-16T17:58:53Z","title":"Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.09365","snapshot_observed_at":"2026-08-07T15:43:20.514911Z","title":"Byzantine-robust learning on heteroge- neous datasets via bucketing","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.514911Z"},"links":{"cited_paper":"/paper/2006.09365","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:b877e2949cba503cdbb2501a933de9b8821e67b20b8d087597e01c830e887498","observation_id":"f878b71a-8ab8-4927-9d0e-88c6e3e38174","resolution":{"observed_at":"2026-08-07T15:43:20.514911Z","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":"2026-08-07T15:43:20.635751Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.635751Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:f51dc9a4ef77f5dab966d2790e98cb6026557f5af4b36d98a2d9711504f2819f","observation_id":"97b1ad61-a869-421d-9b17-b38df67b330d","resolution":{"observed_at":"2026-08-07T15:43:20.635751Z","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":"2026-08-07T15:43:20.701172Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.701172Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:b23b5c25102f0966b9d47ee6a62fbb56a746ec6b0a0388e451bdc0c98bc1ff91","observation_id":"8f709f6b-f9ec-45d1-96dc-d5240c566eaa","resolution":{"observed_at":"2026-08-07T15:43:20.701172Z","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":"2026-08-07T15:43:20.804827Z","title":"A review of applications in federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.804827Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:ffb9b95024108bd656308718e50ad4eefce6f3e785da84977daffccbae11847c","observation_id":"4b527716-3fa6-4530-9518-bbfa07206b11","resolution":{"observed_at":"2026-08-07T15:43:20.804827Z","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":"2026-08-07T15:43:20.934371Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:20.934371Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:96b25d2f2aa311ca5cf4f31e7f0fa3050f4441e9feb2653d9673e6f4e077c24a","observation_id":"f6d6a22a-f847-4953-ae00-ceab638f3f7c","resolution":{"observed_at":"2026-08-07T15:43:20.934371Z","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":"2026-08-07T15:43:35.804804Z","title":"On the convergence of fedavg on non-iid data, 2020","venue":null,"work_id":"382aa2c5-8daa-46b0-9461-ce6bf2fa7819","year":2020},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.029034Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:3216592f0d88445cf999677efc8ac534948a2491e94dfff7053d90f8512452d1","observation_id":"c928820a-abfc-4d59-9373-3eec66f891cf","resolution":{"observed_at":"2026-08-07T15:43:35.871835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:21.175704Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.175704Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:91f0369d80776410ebac128f43934f2d5914ee44bbfdf7b755d60f307365d5b0","observation_id":"01f4b404-8cd6-4ae1-8a47-c3c4acb8cabd","resolution":{"observed_at":"2026-08-07T15:43:21.175704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03561","last_updated":"2022-05-27T12:03:31Z","snapshot_observed_at":"2026-07-06T09:53:43.248602Z","submitted_at":"2020-09-08T07:37:23Z","title":"Local and Central Differential Privacy for Robustness and Privacy in Federated Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03561","snapshot_observed_at":"2026-08-07T15:43:21.295807Z","title":"Local and central differential privacy for robustness and privacy in federated learning","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.295807Z"},"links":{"cited_paper":"/paper/2009.03561","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:44a754aeb3acd8131b7251ed59d6d21c8f94b065be3f1c7d30d479e157cda8c8","observation_id":"07e7bc06-2564-4ffa-be51-0066316c1f48","resolution":{"observed_at":"2026-08-07T15:43:21.295807Z","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":"2026-08-07T15:43:35.483821Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"26a0aaa4-bd6b-40c5-ac9a-5a15c2bde2d9","year":2011},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.404244Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:4e5212f3a6a2a3c23bffeaa9847ad9bb9e89e7cdee9c6d6aa3d2b1c3c7ae601d","observation_id":"f7882a72-db62-4f87-9e2c-f45f05e944d4","resolution":{"observed_at":"2026-08-07T15:43:35.626943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:35.354277Z","title":"{FLAME}: Taming backdoors in federated learning","venue":null,"work_id":"8f6cf2f4-9f05-4737-8e38-76f88d4045d5","year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.567299Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:3c2a957d7ea16966c8f6e5f4c1a2a549a5400b7b215c577d510d6565eb2fedda","observation_id":"30562c3e-addc-4fbf-bc0a-82acb46285fe","resolution":{"observed_at":"2026-08-07T15:43:35.420155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:35.186597Z","title":"Defending against backdoors in federated learning with robust learning rate","venue":null,"work_id":"056f5d6f-d864-4367-a5f4-c6cd82c753df","year":2021},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.627498Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:dc73e7c4b37536aa1fa0c922ae9b7fff206eefc89dc7084a610688ae26068462","observation_id":"569ebf6f-44ba-4539-9042-30754827f1d1","resolution":{"observed_at":"2026-08-07T15:43:35.234335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:21.711437Z","title":"Robust aggregation for federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.711437Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:df1cfb41936c8067ad845f186fd1f58b4bb4399403ededf03dbf2aa69561ae97","observation_id":"bacc66cc-dfed-42fc-b2bd-a1d153061c93","resolution":{"observed_at":"2026-08-07T15:43:21.711437Z","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":"2026-08-07T15:43:35.008579Z","title":"Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning","venue":null,"work_id":"35416803-324d-4af7-aac9-ed728767db96","year":2021},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.833038Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:ee9fe7d2392ef56d6605ede2fb6292152f9fafe279e8dca7e13a8bdbb4086ebd","observation_id":"e95f9f46-c67e-4628-83e0-440c90503c63","resolution":{"observed_at":"2026-08-07T15:43:35.093168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:34.889872Z","title":"Back to the drawing board: A critical evaluation of poisoning attacks on production federated learning","venue":null,"work_id":"0ee16f98-4826-4436-8380-43c6c2d1a7c2","year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:21.947434Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:414b786902cf5fd5f571c1841e5108758cdd044583797f42001a03f3293a2a88","observation_id":"77cda690-b1bc-409f-a5f1-f547b8a4fa2e","resolution":{"observed_at":"2026-08-07T15:43:34.931824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07963","last_updated":"2019-12-02T19:00:11Z","snapshot_observed_at":"2026-08-06T20:09:23.048652Z","submitted_at":"2019-11-18T21:25:03Z","title":"Can You Really Backdoor Federated Learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07963","snapshot_observed_at":"2026-08-07T15:43:22.015946Z","title":"Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.015946Z"},"links":{"cited_paper":"/paper/1911.07963","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:c03c78a07771b3a4c0158397949e9c6e433fe73ff8cca7eab59d247e2d01d2f0","observation_id":"1bc21286-cd58-4436-96f6-9e0c93b91e43","resolution":{"observed_at":"2026-08-07T15:43:22.015946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.10242","last_updated":"2022-08-15T22:04:26Z","snapshot_observed_at":"2026-07-06T09:22:05.728894Z","submitted_at":"2020-05-20T17:59:57Z","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","version":10},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.10242","snapshot_observed_at":"2026-08-07T15:43:22.127451Z","title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.127451Z"},"links":{"cited_paper":"/paper/2005.10242","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:be34115c2d774840f8e77d4ecce880a6e9062196c7bd68f796de645b26bad696","observation_id":"b121c8c2-8415-43be-8b89-da4054cc194c","resolution":{"observed_at":"2026-08-07T15:43:22.127451Z","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":"2026-08-07T15:43:34.618160Z","title":"Crfl: Certifiably robust federated learning against backdoor attacks","venue":null,"work_id":"ee22318b-c8b7-42ba-a423-68e90d8cc22b","year":2021},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.215286Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:8321745f0555b8648c540d2b18379541beea9f3eae867c58c141d376307f5262","observation_id":"2a69bde9-4ad2-47f9-b9ea-881c19eb9024","resolution":{"observed_at":"2026-08-07T15:43:34.736644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:34.371634Z","title":"Dba: Distributed backdoor attacks against federated learning","venue":null,"work_id":"f117e60d-6fd7-41d0-8ddf-aa30a1f57a41","year":2019},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.324868Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:f92f061bae8136b302866db8b0c2da95d9a40a9d99e202fc05867f74e53f024c","observation_id":"fa5920d5-3a3c-459f-a1ab-3ffa776ef676","resolution":{"observed_at":"2026-08-07T15:43:34.485338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15611","last_updated":"2025-08-13T10:00:16Z","snapshot_observed_at":"2026-07-06T18:04:46.468725Z","submitted_at":"2024-04-24T03:02:21Z","title":"Model Poisoning Attacks to Federated Learning via Multi-Round Consistency","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15611","snapshot_observed_at":"2026-08-07T15:43:22.436920Z","title":"Model poisoning attacks to federated learning via multi-round consistency","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.436920Z"},"links":{"cited_paper":"/paper/2404.15611","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:5764f2a61edd988ab638b893c59ed01b0a847348494a6ebe106d4ac1914fc28c","observation_id":"0dfe9d95-d911-4352-9c4b-b63b4e46883e","resolution":{"observed_at":"2026-08-07T15:43:22.436920Z","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":"2026-08-07T15:43:34.165568Z","title":"Fedrola: Robust federated learning against model poisoning via layer-based aggregation","venue":null,"work_id":"52aef9f2-b11b-40f6-9f39-fde68b08d45f","year":2024},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.537229Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:fa4571835a70ec3904fe1ea0512fddd1c97bc09aecb5a5933b7d8925e294a1c1","observation_id":"14b4d9a5-cbde-4b40-8a8f-6de6434b7f5d","resolution":{"observed_at":"2026-08-07T15:43:34.268415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:34.032818Z","title":"Byzantine-robust distributed learning: Towards optimal statistical rates","venue":null,"work_id":"5697d8e9-8a82-498f-b953-8f66ec39075f","year":2018},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.627107Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:0191ba85b944c25ae9aeb7c8513dd2bfedb835c4a8d4c23ff7bfd3cfa657b5a0","observation_id":"7b334183-3bfc-4bdb-8527-736e5099bb99","resolution":{"observed_at":"2026-08-07T15:43:34.076305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:33.841968Z","title":"Fedredefense: Defending against model poisoning attacks for federated learning using model update reconstruction error","venue":null,"work_id":"85298065-5440-420a-9fb9-44943c5dd381","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.701336Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a124d9cd82975513c80451ad875d329f97470b2abf02efbb2a58994678517408","observation_id":"85da89d9-b013-4815-8055-fd9846b99042","resolution":{"observed_at":"2026-08-07T15:43:33.910001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:33.697296Z","title":"Fldetector: Defending federated learning against model poisoning attacks via detecting malicious clients","venue":null,"work_id":"f7427c2d-55eb-414b-8c2d-2ff14b9a173f","year":2022},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.816322Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:e04f51b5411c74faf87550c551cfd806dcb6daa15d9a8a5c5189190ff0a43e8c","observation_id":"43ec8b2e-5622-41f9-9ae9-cb2edd940ac3","resolution":{"observed_at":"2026-08-07T15:43:33.762241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.04466","last_updated":"2024-04-15T15:52:41Z","snapshot_observed_at":"2026-07-06T16:04:02.943124Z","submitted_at":"2023-08-08T05:46:47Z","title":"Backdoor Federated Learning by Poisoning Backdoor-Critical Layers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.04466","snapshot_observed_at":"2026-08-07T15:43:22.934842Z","title":"baseline model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:22.934842Z"},"links":{"cited_paper":"/paper/2308.04466","citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a5e3bbdcc88103632713c44cbb79961bcc3febef4c3600befadce7bd72754226","observation_id":"b87a9dde-ff07-4175-88d2-66836ce42fcf","resolution":{"observed_at":"2026-08-07T15:43:22.934842Z","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":"2026-08-07T15:43:33.497204Z","title":"FedGraM has shown similar performances with C = 20% and C = 30%","venue":null,"work_id":"6a9c1020-f0e3-44b5-a0d1-bd61ad997bcb","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.001223Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:1aa44ce9e7ab2ee6fd35fdc98a5564fecdea19301c39d1347a7657d543b3aa16","observation_id":"980ffa7c-92b1-4409-a119-e304b902f27a","resolution":{"observed_at":"2026-08-07T15:43:33.596137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:33.294566Z","title":"Under all kinds of untargeted attacks, it can successfully defend the attacks and maintain the test accuracy of the global model at a high level","venue":null,"work_id":"81be5bee-c1b6-452a-87fc-51c40fcd985e","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.117276Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:aa1bc63b095120418b9bc68ef985b49d475ce8d983a9fda2e0769a67cb742045","observation_id":"db9ae580-9d6b-440d-8b04-a1734a078c7c","resolution":{"observed_at":"2026-08-07T15:43:33.383514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:33.055436Z","title":"SVHN is an easier classification task compared with CIFAR10 which further facilitate the robustness of FedGraM","venue":null,"work_id":"5c761399-376d-425b-afbe-de987e68ad5c","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.197559Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:83566ba9c025e5b53ddd7d5ccc27a3efd021e3d49ba4930055dd80c5a46fd490","observation_id":"44c6f57e-805a-42c4-9cc7-f221833a2b1b","resolution":{"observed_at":"2026-08-07T15:43:33.165971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:32.785420Z","title":"[Yes] \" is generally preferable to","venue":null,"work_id":"6fb35ff2-e29d-4019-923a-ae9ac031ba68","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.315774Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:8c64cbf8eceb393fddf94615f44d42f41d617cd4f78db93c6e6a54b8df672741","observation_id":"ce82ad4a-72e7-4cd1-87a1-1420adddac70","resolution":{"observed_at":"2026-08-07T15:43:32.937462Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:32.559054Z","title":"Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper","venue":null,"work_id":"a728482a-29db-4248-97e2-8709bf8971b0","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.454751Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:f31c25e5bcc2648afaacfc950b1a3998dd7fb7d5a7a9e79f40911d0319e0dbaf","observation_id":"a02cdb79-49d1-4564-935c-6b5f987a230b","resolution":{"observed_at":"2026-08-07T15:43:32.672637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:32.356147Z","title":"Limitations","venue":null,"work_id":"a7e5dc4f-540e-4161-a0d5-8ebec6c5bedc","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.527292Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:4d07dca72a4eba334515723cd75372eebc293fba74ff35024fb10111f95a9226","observation_id":"dbb15add-1ef3-4511-85af-cdcfb32c8bbf","resolution":{"observed_at":"2026-08-07T15:43:32.438093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:32.119299Z","title":"Guidelines: • The answer NA means that the paper does not include theoretical results","venue":null,"work_id":"83c72908-dc93-4420-b8cf-9ffccaa5782b","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.662762Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a1e09ab0e1f5c9a6b78f9e01911826b800c77c0000d9161eb18da6028fe9f31e","observation_id":"ad9cdaf7-ba04-4d82-804a-9f688300daec","resolution":{"observed_at":"2026-08-07T15:43:32.240694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:31.905510Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"2b65c7ab-4500-4c2d-b525-ab478bef617d","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.734303Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:42469b51cb3b5abcab7e9dc3468caff108bdec78c15a154478fda8f541c04782","observation_id":"91dc93d2-d817-4658-812e-fc3e03e95875","resolution":{"observed_at":"2026-08-07T15:43:31.972044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:31.750774Z","title":"Guidelines: • The answer NA means that paper does not include experiments requiring code","venue":null,"work_id":"c3f24b06-8950-42f5-b6b1-a983eac3ed42","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:23.834818Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:34b9411db4c466dd9b5858ef582bcbb4f98eb0f7c1717c5f8e1ac5bacb821c69","observation_id":"2dd82a55-f2f3-4f64-966f-03b540625b47","resolution":{"observed_at":"2026-08-07T15:43:31.829684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:31.586663Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"570a9482-76f1-4077-977c-8049f1a19460","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.003546Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:6908c5febd434561eb19e5b61f153cba35cf9d5c73fe4e6187eb2d96836989d4","observation_id":"d39ebdcc-7410-4256-afa0-6c37651444be","resolution":{"observed_at":"2026-08-07T15:43:31.643699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:31.381080Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"141fc46d-4e3e-4109-9866-5928d84d9f72","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.183164Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:1ad84c7d59f44e18637c20b0f69d6f54ac1b361fff5ea9d3a37826b6bedda04e","observation_id":"0357809f-44b0-4d28-9192-2ec68369b8f4","resolution":{"observed_at":"2026-08-07T15:43:31.481143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:31.146860Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"bd5860e4-9363-4d4d-b973-1475560386c4","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.364843Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a57977e688d48e01d0a025e3667c6e3ad745508ec91e48468eda6e34ac81e6aa","observation_id":"e6df1490-1ccb-434d-957e-36e5ed0205be","resolution":{"observed_at":"2026-08-07T15:43:31.252275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:30.882292Z","title":"Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics","venue":null,"work_id":"a266abce-c0c8-4b63-8fc4-4413577d8780","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.564811Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:f4780fea8f0debe73b123c27493016b414e8785ef4de1fb0b9300623906911c2","observation_id":"980e1f65-e211-43bf-9672-05d339551ab5","resolution":{"observed_at":"2026-08-07T15:43:30.995909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:30.723048Z","title":"Guidelines: • The answer NA means that there is no societal impact of the work performed","venue":null,"work_id":"5a828eac-c8ba-445c-9381-846eed825117","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.651089Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:70214bb8350198312e11a8d8e9f1f0805dd80d7f98ea820c65c57782ce24399a","observation_id":"3d843db6-c018-4f54-869a-9f91bf09db1b","resolution":{"observed_at":"2026-08-07T15:43:30.780603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:30.525717Z","title":null,"venue":null,"work_id":"9ae2710f-3ee9-4513-b245-4776cd244a1f","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.717292Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:227a98e060d80ec5b662cb507bf1df7f9a4136ec85c4236119c73ef783b6768c","observation_id":"05fb2787-cdf5-47c0-b16d-064d4e4e4afe","resolution":{"observed_at":"2026-08-07T15:43:30.615861Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:30.330891Z","title":"Guidelines: • The answer NA means that the paper does not use existing assets","venue":null,"work_id":"3cf176ee-a7af-498b-bb92-3da0d9c3f993","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.815747Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:d8442d2cd059e64fb757ca39deaca4ef45c800c587597581ef3ec03131099a43","observation_id":"f4c93266-ac6a-4e40-b0f0-dfcaed0319ab","resolution":{"observed_at":"2026-08-07T15:43:30.408458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:24.960573Z","title":"Guidelines: • The answer NA means that the paper does not release new assets","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:24.960573Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:a790895ea20f56b9c8968e3ea2a4fea128a40bd8717021ea229beb8485e9f645","observation_id":"0801d23e-9580-4721-81c0-8e6c55a3eed0","resolution":{"observed_at":"2026-08-07T15:43:24.960573Z","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":"2026-08-07T15:43:26.204325Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"3f85cb3c-5999-4f20-8758-9b85726139ca","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:25.193727Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:43e42f65262b7ea8a21771851ce300fae266d4b78a67a522488a37e8dcf38574","observation_id":"01a0581b-9f9c-4ac3-9c62-166b24de0332","resolution":{"observed_at":"2026-08-07T15:43:30.124947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:25.786610Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"947ba397-91dc-4c22-84c4-4be7300285f2","year":null},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:25.329456Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:e6c51bd5a7764ec50a3435c742474da899c2492910c232903b7156f5ecd724fd","observation_id":"08f09d19-d22c-4e20-b441-6d848b94ce51","resolution":{"observed_at":"2026-08-07T15:43:25.908406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T15:43:25.494823Z","title":"Answer: [NA] Justification: The core method development in this research does not involve LLMs as any important, original, or non-standard components","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T15:43:25.494823Z"},"links":{"citing_paper":"/paper/2505.14024"},"observation_digest":"sha256:abcde47092a56399341504bc52329d82804062e6bac7c5ddc49f0af87662321c","observation_id":"72c2e98b-2de2-4034-8504-7d3216cd373f","resolution":{"observed_at":"2026-08-07T15:43:25.494823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.14024","last_updated":"2025-05-20T07:26:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:40:03.712919Z","submitted_at":"2025-05-20T07:26:54Z","title":"FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":59},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2505.14024."}