{"as_of":"2026-08-10T15:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5a6ef5c80b392fc7e73491caa1cb56c6070a062875124ff7fb0e6e0ba72e2394","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T19:57:50.547396Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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":"2026-08-07T04:46:43.210852Z","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":"2026-05-12T06:16:25.829629Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.00193","snapshot_observed_at":"2026-08-07T04:46:43.210852Z","title":"Byzantine-resilient zero-order opti- mization for communication-efficient heterogeneous federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.09870","last_updated":"2025-06-11T15:42:18Z","snapshot_observed_at":"2026-08-10T07:50:37.296357Z","submitted_at":"2025-06-11T15:42:18Z","title":"Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:46:43.210852Z"},"links":{"cited_paper":"/paper/2502.00193","citing_paper":"/paper/2506.09870"},"observation_digest":"sha256:c2fceb0b16531d375e8771dea0382e46b1cf3481cac1aa7c8eb71ffe255c8a69","observation_id":"25deb499-83c5-4e8a-9b84-e49aeefc1086","resolution":{"observed_at":"2026-08-07T04:46:43.210852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"cited_work":{"arxiv_id":"2502.00193","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.00193","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2502.00193 , year=","venue":null,"work_id":"08073b1a-e27b-425d-bee7-7f39d699fdf0","year":null},"citing_paper":{"arxiv_id":"2605.09337","last_updated":"2026-05-10T05:24:02Z","snapshot_observed_at":"2026-08-02T15:50:32.604234Z","submitted_at":"2026-05-10T05:24:02Z","title":"Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates","version":1},"reference_index":187,"source":"arxiv_source","source_observed_at":"2026-05-12T04:27:35.605021Z"},"links":{"cited_paper":"/paper/2502.00193","citing_paper":"/paper/2605.09337"},"observation_digest":"sha256:5fccfe5bd5e6af4ee0666d7c611491a3acc5b45af16a86ea81470e396f44de97","observation_id":"1ec96496-c241-4917-b3f5-9660305374c3","resolution":{"observed_at":"2026-05-12T06:16:25.832694Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.00193/citation-record","integrity":"/paper/2502.00193/integrity","json":"/paper/2502.00193/citation-record.json","paper":"/paper/2502.00193"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.549639Z","title":"Byzantine-resilient non-convex stochastic gradient descent","venue":null,"work_id":"5816d1dc-2bb4-42f0-bce7-3b202701a4c4","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.255349Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:2a248339f760ec6feb2ed955f6d5f07f76e281f5989bfd9e3a94dd3d28cc720c","observation_id":"b305cf53-31ad-417b-b94d-b15d7d33804d","resolution":{"observed_at":"2026-08-09T19:57:51.555553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.531583Z","title":"Fixing by mixing: A recipe for optimal byzantine ml under heterogeneity","venue":null,"work_id":"3ef81ad1-ef78-483e-8325-d959db7b4a54","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.261196Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:6ff9890a3f4c611febcb9f39d1f670c4bd7b933eb2de95e2accab93e5dcbb616","observation_id":"6bd13f47-7d9a-4d2e-ab4b-83e4310af883","resolution":{"observed_at":"2026-08-09T19:57:51.537508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.509791Z","title":"Differential privacy has disparate impact on model accuracy","venue":null,"work_id":"2338e4e0-0bb1-4c2d-8f71-bfe76469c573","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.266688Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d07fe9e90cf9b97fbc14dae880a367e14affa29cede6880ac8a33bff897a2b83","observation_id":"1a5212e1-4c44-4eed-9333-df94fe83430c","resolution":{"observed_at":"2026-08-09T19:57:51.515828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.492184Z","title":"A little is enough: Circumventing defenses for distributed learning","venue":null,"work_id":"b7a1a86b-3725-4a73-a273-2a3b09f389e2","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.272523Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:46055b0682b610483545e601a9932eca2d1daed2e13625cadf0e7e2d9d8bc867","observation_id":"24ab1b60-02f4-42ef-a292-05b87f347416","resolution":{"observed_at":"2026-08-09T19:57:51.498200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.472256Z","title":"M., Guerraoui, R., and Stainer, J","venue":null,"work_id":"fef53a9a-89de-43d5-902f-01ba2722fa30","year":2017},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.277828Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:5875d54d6844e086a19ecc7ed9b583a413fdf0e5059292978db49050f5ab69ba","observation_id":"2ecdeef4-b2b8-451a-81ac-ac48b1de53a0","resolution":{"observed_at":"2026-08-09T19:57:51.478126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.454412Z","title":"R., Angeli, G., Potts, C., and Manning, C","venue":null,"work_id":"6094344b-0a04-47e7-a4fe-4e2b1d69c9a3","year":2015},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.283624Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:ee570d445b4b33eb2e68e96a113cf6d4d6133b230306b46a70bfc4cbf947bf15","observation_id":"a9ad964c-4d08-401c-90d8-644aea2580d1","resolution":{"observed_at":"2026-08-09T19:57:51.459919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.435054Z","title":"Learning from untrusted data","venue":null,"work_id":"b0accb46-0c3c-40f6-94b6-d93c4dc20eaf","year":2017},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.289889Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:a21543b1b2306e254542b808a93a36ebcad67e911431e5df16bf57904ded07ee","observation_id":"517deeaf-dd34-494b-bc59-5a5a89420d57","resolution":{"observed_at":"2026-08-09T19:57:51.441050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.415531Z","title":"Fine-grained theoretical analysis of federated zeroth-order optimization","venue":null,"work_id":"2a044b36-2d12-4092-89ac-af125ef84ae3","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.294778Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:2f58dc5cb66e49b3eb3109c907fb87d51b600a974ad152769669f4aa60c6501e","observation_id":"fea329d8-b181-444a-a990-28139db3ac47","resolution":{"observed_at":"2026-08-09T19:57:51.421575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.395682Z","title":"C., Jordan, M","venue":null,"work_id":"d64bbcc3-9037-49d7-8bde-05c2b66769d7","year":2015},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.299825Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:adf235e1da4f41c2bb2764a1bc86d476e6eb658d849360a9dd3ec93da96352b6","observation_id":"18928b5c-d931-41ca-8f84-f9d309fe6151","resolution":{"observed_at":"2026-08-09T19:57:51.403444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.374048Z","title":"Private aggregation in wireless federated learning with heterogeneous clusters","venue":null,"work_id":"a1cd3690-a763-465c-a20a-11edcbd4bb41","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.304866Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:b7c65ab6e3352ed806d8e2fd0b3fac8aeaa2ddc283ee4e6f07b2d5c8ae82ecd8","observation_id":"46d6f759-6389-4821-ba36-81766a9066ee","resolution":{"observed_at":"2026-08-09T19:57:51.380829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.354907Z","title":"M., Farhadkhani, S., Guerraoui, R., Guirguis, A., Hoang, L.-N., and Rouault, S","venue":null,"work_id":"05a6f787-a2ba-40e7-966e-9193b5c22345","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.309753Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:9dada609699a74ba62905ee503960392daea6f6fe1284ace2945a5e5eee415bf","observation_id":"cffcbd17-df37-410f-99ef-2e230c764d07","resolution":{"observed_at":"2026-08-09T19:57:51.361312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.331324Z","title":"Local model poisoning attacks to byzantine-robust federated learning","venue":null,"work_id":"b93c454f-8305-4aed-b5d7-a02e71f85151","year":2020},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.314772Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:aeae92dff9bef901e90cbe1cd98181ecbedef2acd947a5ddd16b5a7acf185bfe","observation_id":"615b83cc-2d6d-400b-a323-2c28a4d432ec","resolution":{"observed_at":"2026-08-09T19:57:51.337727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.319581Z","title":"N., and Zhou, Y","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.319581Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:e433b29229fabe73064f60c81a80629584e944a4f45a7fb4f78fa24d52f36998","observation_id":"63f645f1-a962-4336-a1ee-7201fbf686da","resolution":{"observed_at":"2026-08-09T19:57:50.319581Z","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":"2026-08-09T19:57:51.296805Z","title":"D., Kalai, A","venue":null,"work_id":"20a3d18d-34d6-413f-9e1d-e382403f34f2","year":2005},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.324459Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:de72be2ba31d5abd5f6d12971707f867784c376d2f2fb77cc753ce06257d65df","observation_id":"e765a6bc-10ca-4c12-8ad8-48e3b4388e0c","resolution":{"observed_at":"2026-08-09T19:57:51.301945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.280060Z","title":"On the information-adaptive variants of the admm: an iteration complexity perspective","venue":null,"work_id":"23b2bb9b-970f-4890-ad2c-88a62aefb50f","year":2018},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.329046Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:b2fdeae270f8dc490a5a2079b1cb2d8058aad7f4acfc1181e8c5edcdfdc94dfc","observation_id":"46978c12-30a8-41f3-93ad-633da82fdcb5","resolution":{"observed_at":"2026-08-09T19:57:51.285357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.264047Z","title":"and Lan, G","venue":null,"work_id":"29f1ad7b-1d0c-44ea-b97c-8ecad0dc8306","year":2013},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.334064Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:1e5a86b80ab5af372a93414684000157531f000b123065f4a73a95a194bbe242","observation_id":"1a1f3ccc-7ab5-44bc-8fde-de4a033e6677","resolution":{"observed_at":"2026-08-09T19:57:51.268720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.248242Z","title":"Black-box adversarial attacks with limited queries and information","venue":null,"work_id":"189a9087-9357-4f76-8900-8a757a39f1f9","year":2018},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.338991Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:5c277d0317b7ed091fd7887fe77e728820c72fe6aed59a3f1ab1689fc05ab7d4","observation_id":"ca4e4366-8711-4337-9ae5-0fa328df38a6","resolution":{"observed_at":"2026-08-09T19:57:51.253423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.231802Z","title":"A., Li, S., and Caire, G","venue":null,"work_id":"9ca9123c-e2c4-4f61-8302-4210c219a4fb","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.343864Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d402a0fd21001a7e9d18c50c88f4062987842ff80dab4fa26d10473b3a24916d","observation_id":"85a0a4eb-1035-4194-9dd0-c16aa5c55aed","resolution":{"observed_at":"2026-08-09T19:57:51.236702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.212170Z","title":"and Lindenstrauss, J","venue":null,"work_id":"db686e62-1a75-4311-af8b-56fee37244a0","year":1984},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.348797Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:37b180d8cdc60c29d8f0da2a6327d10fce49adf50a4247e0366bde00bc10ad8c","observation_id":"25ce674f-0c0f-44ae-9609-996f913310ad","resolution":{"observed_at":"2026-08-09T19:57:51.220467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.194133Z","title":"P., Rebjock, Q., Stich, S., and Jaggi, M","venue":null,"work_id":"2e40ebae-0752-4a2f-814c-c1dec237dadb","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.353948Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:1d1b5a5bfe767172f7ff161937f301179d2f2b1f726cdf221fa89000fffccbcf","observation_id":"bf6b3740-49c3-46a5-974a-d79123e12c6b","resolution":{"observed_at":"2026-08-09T19:57:51.199591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.176643Z","title":"P., He, L., and Jaggi, M","venue":null,"work_id":"2121597a-43b5-4501-a495-adbe12994d2b","year":2022},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.359080Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d58a5bb902723f25b5eb303e1501840da83f7d1c6cfd311a1a6aca3aa85e5eeb","observation_id":"dce0f977-44de-49c1-99e7-2c602ffcdb02","resolution":{"observed_at":"2026-08-09T19:57:51.182780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.157995Z","title":"and Wolfowitz, J","venue":null,"work_id":"e161796c-d3c5-4f97-82d6-5df3d1eac71c","year":1952},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.364150Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d7fea88d4668755c2227b994c8ac3a242c7dff28019cd7a4c6ddd6d771b55584","observation_id":"562c118e-256c-41da-855d-6f0629c6aaaa","resolution":{"observed_at":"2026-08-09T19:57:51.163574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.00211","last_updated":"2020-02-01T14:09:48Z","snapshot_observed_at":"2026-08-07T00:07:33.465634Z","submitted_at":"2020-02-01T14:09:48Z","title":"Learning to Detect Malicious Clients for Robust Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.00211","snapshot_observed_at":"2026-08-09T19:57:50.369406Z","title":"Learning to detect malicious clients for robust federated learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.369406Z"},"links":{"cited_paper":"/paper/2002.00211","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:682fd3ac23d42a307b0b06eeb94c705d7bf8a9a624f53cad5b91854d3d2d0917","observation_id":"8e938a50-8864-4d08-abe0-d21e15c32c74","resolution":{"observed_at":"2026-08-09T19:57:50.369406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10232","last_updated":"2024-07-19T12:49:42Z","snapshot_observed_at":"2026-08-03T23:11:40.388566Z","submitted_at":"2024-02-10T15:37:46Z","title":"Simple, unified analysis of Johnson-Lindenstrauss with applications","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10232","snapshot_observed_at":"2026-08-09T19:57:50.375356Z","title":"Simple, unified analysis of johnson-lindenstrauss with applications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.375356Z"},"links":{"cited_paper":"/paper/2402.10232","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:8cea13365d24c9bb9470a2724b33718596842992b4416a4c95aaadbe002c226e","observation_id":"08af1bba-c669-460e-8d28-fc9b8c08420a","resolution":{"observed_at":"2026-08-09T19:57:50.375356Z","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":"2026-08-09T19:57:51.139692Z","title":"O., and Varshney, P","venue":null,"work_id":"5cdd6492-dd30-4b65-8e3c-5d15032bfcdc","year":2020},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.381261Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:4b13b62c1c718b46f512aafe2ab66533328f33a5c9b29364cd23b0075388c4e9","observation_id":"fd1ca28a-623c-4b82-91f4-8d21311e0232","resolution":{"observed_at":"2026-08-09T19:57:51.144925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.123285Z","title":null,"venue":null,"work_id":"e5bb9489-7ed3-4e5b-9f1f-e34ac22df45e","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.386695Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:5e56733729e4734102b4f92bbe3fa167894be1bfc3142910dfed8387da764b03","observation_id":"41d805e4-fc7b-4231-99ce-27a60900fb24","resolution":{"observed_at":"2026-08-09T19:57:51.128325Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-09T19:57:50.392319Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.392319Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:bc33eb273cb86eb0298d9e2a8d4c4ef19e3c1daebef1d1ad5638063b982f1f90","observation_id":"6c38131f-358c-4bfc-b80b-8182290016d3","resolution":{"observed_at":"2026-08-09T19:57:50.392319Z","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":"2026-08-09T19:57:51.105428Z","title":"An efficient statistical-based gradient compression technique for distributed training systems","venue":null,"work_id":"bc0fce37-4ef9-4675-8332-d7c62dee1f6b","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.399485Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d35986f2c9b03f26213c9714c4b402fa55cde45ac943109c72e3cf8172763714","observation_id":"f530da2e-1e16-4235-92a1-08852cebc720","resolution":{"observed_at":"2026-08-09T19:57:51.111333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.087340Z","title":"V., Bondaschi, M., Vogels, T., Jaggi, M., Kim, H., and Gastpar, M","venue":null,"work_id":"35f9f763-3766-4ea3-9e63-eed187293e67","year":2024},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.404742Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:c6bb618a1d37ecfaa0b351a3339cf69a2359b261d253e40189e623d3ffb59632","observation_id":"37ef1d83-4567-4477-bb47-e9eb4e80da9b","resolution":{"observed_at":"2026-08-09T19:57:51.092708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.410072Z","title":"D., Chen, D., and Arora, S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.410072Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:9734ef42874ec33e681e6bdad21f3406ece47cacd6727474448cdf6022834d13","observation_id":"d16d1a99-74bc-481d-85de-7b3a32113596","resolution":{"observed_at":"2026-08-09T19:57:50.410072Z","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":"2026-08-09T19:57:50.416405Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.416405Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:e863c549087733502c1d3c73c22421e562ddc2997c474c2c4219327bc82d9963","observation_id":"eec7e311-8110-48be-9bd3-074a724ec31a","resolution":{"observed_at":"2026-08-09T19:57:50.416405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14362","last_updated":"2024-06-20T14:36:12Z","snapshot_observed_at":"2026-07-06T18:34:15.291938Z","submitted_at":"2024-06-20T14:36:12Z","title":"Communication-Efficient Byzantine-Resilient Federated Zero-Order Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14362","snapshot_observed_at":"2026-08-09T19:57:50.421569Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.421569Z"},"links":{"cited_paper":"/paper/2406.14362","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:612970a39c24ea744e803d194834be750be56ca8900ba066d1582d48d74a9eb9","observation_id":"42790764-0a9d-4497-a93b-ca7e957b91a1","resolution":{"observed_at":"2026-08-09T19:57:50.421569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06353","last_updated":"2024-05-27T08:31:47Z","snapshot_observed_at":"2026-08-04T21:00:04.840805Z","submitted_at":"2023-12-11T13:03:21Z","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.06353","snapshot_observed_at":"2026-08-09T19:57:50.427096Z","title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.427096Z"},"links":{"cited_paper":"/paper/2312.06353","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:222bfa5cdf84b08e7f0b2847882042200155791592c159d5353eb3de33c3584c","observation_id":"c22040e8-806e-404f-989e-461d05cb824a","resolution":{"observed_at":"2026-08-09T19:57:50.427096Z","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":"2026-08-09T19:57:51.049559Z","title":"Zeroth-order methods for nondifferentiable, nonconvex, and hierarchical federated optimization","venue":null,"work_id":"74b195cf-2849-4160-83ab-42fe58692fc7","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.432480Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:5f93c411f0ac62f429abf5f2cda02c7ad361577a1d7e845fb985ef26b6d990a4","observation_id":"8600d7f2-6e26-4958-9927-0c69fae99e09","resolution":{"observed_at":"2026-08-09T19:57:51.054736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:51.034073Z","title":"V., Herrera, F., and Mart \\' nez-C \\'a mara, E","venue":null,"work_id":"04322345-c9a0-4a12-862d-d181e148b1fa","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.437366Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:0ec00890a8e20eb7917c87acd20b0aed3c8d278ad5275042306a7ae93b87e0e9","observation_id":"3addd7f9-fa9d-4949-aabe-0a48065ea182","resolution":{"observed_at":"2026-08-09T19:57:51.039023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03864","last_updated":"2017-09-07T23:28:48Z","snapshot_observed_at":"2026-07-06T05:33:17.404544Z","submitted_at":"2017-03-10T23:02:19Z","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03864","snapshot_observed_at":"2026-08-09T19:57:50.442632Z","title":"Evolution strategies as a scalable alternative to reinforcement learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.442632Z"},"links":{"cited_paper":"/paper/1703.03864","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:8bc0e1e4cd1e7429cbf122eaf5c755b508d801b755f78c3c8273e42eab030bbe","observation_id":"4c70315d-dd59-400e-97e2-383771cc4c26","resolution":{"observed_at":"2026-08-09T19:57:50.442632Z","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":"2026-08-09T19:57:51.018110Z","title":"K., Moraes, M","venue":null,"work_id":"d48280cc-1cf2-4c9f-aa50-8f1519585559","year":2011},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.447878Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d276e8534e3ce223224afa578809b6d0e1c229add33bc9640831f67bd6b53dec","observation_id":"fff918d9-8f03-4e81-99f8-09881233bb4f","resolution":{"observed_at":"2026-08-09T19:57:51.023415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.999883Z","title":null,"venue":null,"work_id":"7e5c2738-f78c-40ac-926e-295ac7191b32","year":2023},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.452786Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:85d1ebe37941c1d94e7aabb2ed053651ecdae4c751c74ec99e535a3c23ccf9ef","observation_id":"bc06642b-d9a3-4312-94cc-ed541a53bbbb","resolution":{"observed_at":"2026-08-09T19:57:51.006858Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.983493Z","title":"Auror: Defending against poisoning attacks in collaborative deep learning systems","venue":null,"work_id":"d3314e40-d87a-4291-aae8-4dad57759936","year":2016},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.457797Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:b86fb949f5ec664c8c6b23ca85f8978b4a11c55d558c2a5477b259863b01dbef","observation_id":"aa342947-e0c6-4c8d-9998-91ae97f63497","resolution":{"observed_at":"2026-08-09T19:57:50.988925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.967353Z","title":"D., Ng, A","venue":null,"work_id":"f02aaa8e-907e-4192-8f1b-01c7b1bc5d2a","year":2013},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.462742Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:ff7a2de2725992b1f2cb45953c55bcd511e3714f1fe9e0ccadef37a47600b81f","observation_id":"38efc425-39ca-468d-8f68-d3c6069caef4","resolution":{"observed_at":"2026-08-09T19:57:50.972306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.951552Z","title":"Multivariate stochastic approximation using a simultaneous perturbation gradient approximation","venue":null,"work_id":"4fe4566c-8649-449a-89db-f40ebc030d79","year":1992},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.467801Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:51f725e4264ce9a5d10520dbc38da6246eecf08579180c6ade11bee74fa72eaf","observation_id":"e7b9e787-482a-44b7-8bf5-79ae617e6b5d","resolution":{"observed_at":"2026-08-09T19:57:50.956660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.935481Z","title":"Private fine-tuning of large language models with zeroth-order optimization","venue":null,"work_id":"96789566-26ee-4aef-8c5c-64ea172b59f1","year":2024},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.472848Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:a0b3beb5aa461e4970b2eeb2192eaf2dce5049216b38ce3b82b1af4cf37d0474","observation_id":"1269dd92-224f-4187-8e13-aae7852b0cc4","resolution":{"observed_at":"2026-08-09T19:57:50.941127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.918720Z","title":"Distributed zero-order algorithms for nonconvex multiagent optimization","venue":null,"work_id":"287d3c84-5d84-4d4c-a13f-4764eb3dc565","year":2020},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.478476Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:b01916f08940d3fd766dc370233421c61536678faf71abb2c12dafe744db978e","observation_id":"91a155f1-dcb6-469f-b68e-0c4505454e2a","resolution":{"observed_at":"2026-08-09T19:57:50.924435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.901156Z","title":"z -SignFedAvg : A unified stochastic sign-based compression for federated learning","venue":null,"work_id":"65264f79-5542-46dc-a912-2dd14466d9c4","year":2024},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.484867Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:a538368dc6c44e73547f53ded23e14bfc24345387e86469505bf5f214c7a4399","observation_id":"1474a045-24a8-4f7f-93f1-1342410e4132","resolution":{"observed_at":"2026-08-09T19:57:50.906530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.884037Z","title":"A hybrid approach to privacy-preserving federated learning","venue":null,"work_id":"cca32aaf-5b12-4c05-a5ab-1c91e256c516","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.490159Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:011033169d3698eab2ddfba6cdd10adc4f59cd77d047c9d78efeeaf7a18875cb","observation_id":"80b66190-9ada-4336-8a1f-03af6b321f7b","resolution":{"observed_at":"2026-08-09T19:57:50.889408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.867187Z","title":"P., and Jaggi, M","venue":null,"work_id":"060e1b31-12e8-4725-b3c4-5e220374f473","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.496041Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:14c9fe8b24dff9aa3502122884abfcdd3cecb4ff064b906c6f2ca81391597f6f","observation_id":"8675d9fd-d8aa-44ae-911f-c6b2c58cc95a","resolution":{"observed_at":"2026-08-09T19:57:50.872313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.848813Z","title":null,"venue":null,"work_id":"42560bc1-e6e2-48df-a005-dd736f7ed03e","year":2000},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.501318Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:3782681e894c1f58fab11f255c2c1ea8a9481833b4202e043b2dcb11b4b1cbb3","observation_id":"1248d24e-2519-45e6-801f-a4ceddfd241b","resolution":{"observed_at":"2026-08-09T19:57:50.854025Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.831525Z","title":null,"venue":null,"work_id":"874a98e6-bd6a-48ed-8016-652f69f46b20","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.506233Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:3e77a00818aa59f561ce0203a89e9e1c772a6d2d0cb7be9e938bf29eba8f3b58","observation_id":"2de5b987-af72-4b9e-bf42-3fa72d363a5b","resolution":{"observed_at":"2026-08-09T19:57:50.836935Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.814178Z","title":"A new theoretical perspective on data heterogeneity in federated optimization","venue":null,"work_id":"527d5f92-9513-4077-807e-66f6a005bbca","year":2025},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.511319Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:ecdf925c222650a5a70587d7a3c24ad9b03fb4ac9bb40b8428d59b88be22923a","observation_id":"0bd8cf2c-b16e-46b5-a738-e6b5dcc690e0","resolution":{"observed_at":"2026-08-09T19:57:50.820066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.794949Z","title":"H., Farokhi, F., Jin, S., Quek, T","venue":null,"work_id":"dc3d7f1c-3d46-4d82-a824-728a1d621973","year":2020},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.516281Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:87b8d4ff5de5306e1e25d970dac5282695d01b3190f6fe6b7127318c9aa7f509","observation_id":"be5a7768-495d-47d3-93d8-57fb05647339","resolution":{"observed_at":"2026-08-09T19:57:50.801044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.777429Z","title":"TernGrad : Ternary gradients to reduce communication in distributed deep learning","venue":null,"work_id":"c461e4c8-8bad-40b4-817d-8824df3f1962","year":2017},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.521289Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:f7a787ba7f246297b871403341aad7d7ca560894f1e931961b7f0f68de601417","observation_id":"46e86a7e-a4a4-4582-bce3-c9b5de0139bb","resolution":{"observed_at":"2026-08-09T19:57:50.782705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.759754Z","title":"Fall of empires: Breaking byzantine-tolerant sgd by inner product manipulation","venue":null,"work_id":"8c637564-20a4-4bbd-875f-3cfa55797c60","year":2020},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.526705Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:890bd0de059d6299333012d630b6f859db64fece067e73fecb9109fe7a311eaf","observation_id":"0314852a-f3e9-4024-a5c7-a84152fcb488","resolution":{"observed_at":"2026-08-09T19:57:50.764914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.742516Z","title":"Byzantine-robust distributed learning: Towards optimal statistical rates","venue":null,"work_id":"294a3fa8-536b-4a82-8fc4-b6ad5768073c","year":2018},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.531911Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:d5c7190b45f15c68d7955e86d417729f2fd11fc20b27502a8e98afbfadf839af","observation_id":"9f61ed1f-e279-4747-abce-306f127053f0","resolution":{"observed_at":"2026-08-09T19:57:50.748035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-09T19:57:50.536963Z","title":"Federated learning with non-iid data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.536963Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:3e250bbbd6260b588be8957dd7b74a77cdd808ad39245bfb9d11f7ed29f9b0aa","observation_id":"853e43a4-f2ba-4b79-9181-e1926ec60a0e","resolution":{"observed_at":"2026-08-09T19:57:50.536963Z","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":"2026-08-09T19:57:50.723850Z","title":"Federated learning on non-iid data: A survey","venue":null,"work_id":"b34a916f-c1ae-4e5c-abb1-5e4bf4415e69","year":2021},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.542150Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:4feab79e63885651fc072acc8d751762d8e4fd4dea8c9de44435ac38d61cc776","observation_id":"feaec60c-5607-4051-a2e4-3ba0882470a1","resolution":{"observed_at":"2026-08-09T19:57:50.730040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:50.705011Z","title":"and Philip, S","venue":null,"work_id":"08178a36-ad85-4098-9559-17033fd12a53","year":2019},"citing_paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-09T19:57:50.547396Z"},"links":{"citing_paper":"/paper/2502.00193"},"observation_digest":"sha256:c6e67d67a4d4ca3b7d95b03463c7fbc91b70b17e359c9853df1d64487243f455","observation_id":"39f2d880-e7b1-4743-9156-48ee0660b461","resolution":{"observed_at":"2026-08-09T19:57:50.711881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.00193","last_updated":"2025-01-31T22:22:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T19:48:51.354919Z","submitted_at":"2025-01-31T22:22:11Z","title":"Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":42},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 2 inbound Pith citation observations for arXiv:2502.00193."}