{"as_of":"2026-08-21T20:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17d26a90784a6b53cd072db82282245f8ba838e1c27eb84d6beae221ba91c667","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:51:57.379453Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2506.15181/citation-record","integrity":"/paper/2506.15181/integrity","json":"/paper/2506.15181/citation-record.json","paper":"/paper/2506.15181"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:51:58.351820Z","title":"Resilient distributed vector consensus using centerpoint","venue":null,"work_id":"058c38da-d0bd-49e6-8638-8a384df45aaa","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.053329Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:4b538cf541a48d8aad347c9255860f50b619e8d092b70e8e92d909b065e0ccc4","observation_id":"c6ff8555-3179-4b33-837b-7b521a4e9238","resolution":{"observed_at":"2026-08-15T19:51:58.356773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.335160Z","title":"A little is enough: Circumventing defenses for distributed learnin g","venue":null,"work_id":"2960e0bb-5752-4704-80f6-2cf72c792f75","year":2019},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.059348Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:858697113f1bc4c1f023aa7688e68fd3d66c7c77450421dc87622819e32bdd7d","observation_id":"cfc28767-e6e6-47ed-a90e-54659f9b29d0","resolution":{"observed_at":"2026-08-15T19:51:58.340996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.318686Z","title":"Priva te empirical risk minimization: Efficient algorithms and tight error bounds","venue":null,"work_id":"525e94a7-b208-478d-a429-4212d9c51169","year":2014},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.064510Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:6563b3aa20e8d34736b14ab30ccdf0a0c18e11bf36364deee50f0b40ae7bceee","observation_id":"93244567-32b8-4f0c-8647-8a9c0bee824f","resolution":{"observed_at":"2026-08-15T19:51:58.323737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.302463Z","title":"Bounds on the sample complexity for private learning and private data release","venue":null,"work_id":"5a810553-c283-4d81-8b61-7fa2114c68b1","year":2014},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.071013Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:59be019ec431fd8602e506c237a4388a7419f254007f366d7ce67318f0bbc6ef","observation_id":"742b2c88-5020-4e59-8363-672f6c1f08af","resolution":{"observed_at":"2026-08-15T19:51:58.307664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.286841Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent","venue":null,"work_id":"7fb7a99a-e805-4e9a-b5ba-93c5411d8d15","year":2017},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.076549Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:6d58eff9404b04f37fa0ea126d49dd28770d97526ebb4ba988ab1dd741169160","observation_id":"78d9047a-3cc6-4b08-85c5-f9c2405e2cb8","resolution":{"observed_at":"2026-08-15T19:51:58.291843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.269452Z","title":"Optimization methods for large-scale machine learning","venue":null,"work_id":"f24cd346-4f46-4ec9-b132-5b2292b4a171","year":2018},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.082629Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:486162200f0c459fe4ba636c8da7fd5987df94164553adb69179a6032ecd1cb3","observation_id":"93a07f54-ca3b-4aaa-ac62-8b2ba12b141b","resolution":{"observed_at":"2026-08-15T19:51:58.275770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.253639Z","title":"An optimal randomized algorithm for maximum tukey depth","venue":null,"work_id":"dc23796a-d16a-4fca-959b-fcce0c0558cd","year":2004},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.088591Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:04ac3f078bc28e95ce9362de41d5af4ea185c7044cf2aeede5f85b666380efcc","observation_id":"3b2cafe7-fe5d-4b08-9238-2c934aab87c1","resolution":{"observed_at":"2026-08-15T19:51:58.258564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.237819Z","title":"Distributed statistical machine learning in adversarial settings: Byz antine gradient descent","venue":null,"work_id":"6f92fa7d-a44d-4f99-b5c6-3a76297c8b45","year":2017},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.093722Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:3afceeef65f3cbff5f41cfdabc36d34d0b790b76d521665ced9786b4886b03c8","observation_id":"6800431d-61dc-47de-8ba8-44ef2f5dd237","resolution":{"observed_at":"2026-08-15T19:51:58.243039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.222304Z","title":"Privacy amplificati on by decentralization","venue":null,"work_id":"92d1c692-f82a-48bc-a02b-b9c3e679c32c","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.098436Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:da0aef46c75a03f47da25649e6214abda219215950b502773b6a1c9a64db228d","observation_id":"bc285af2-0282-43b7-a8c7-aadbfba49287","resolution":{"observed_at":"2026-08-15T19:51:58.227145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.206826Z","title":"Differentially private decentralized learning with random walks","venue":null,"work_id":"96178d21-aacc-4116-b434-22f1310c4d8d","year":2024},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.103111Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:9d65fe3aec00d0c11f693f7fe7f00baf2e0ca96347156633e29f2edc59cf0505","observation_id":"e3856e14-ed6c-40b6-819e-c8a48affe7ee","resolution":{"observed_at":"2026-08-15T19:51:58.211692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.190336Z","title":"Muffliato: Peer-to-peer privacy amplification for decentralized optimization and averaging","venue":null,"work_id":"0a6026a2-9870-4699-b530-719d6db7a2b5","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.108018Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:73ba2f1a0999000e938f977b04975d1e9d969777ef8acf241ab9e24f3d7097d7","observation_id":"da0b0bab-4092-4a45-9e2d-ab6186892d92","resolution":{"observed_at":"2026-08-15T19:51:58.195731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.174110Z","title":"Hell y’s theorem and its relatives","venue":null,"work_id":"b3a25c01-9cc3-4452-982a-8aceff1f1a4b","year":1963},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.112824Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:abe011898bc0978db3c0536bc394dd05c79cf5166453c717923d22a0c12dfad9","observation_id":"308bdad7-412f-4436-a01e-1339eab926a8","resolution":{"observed_at":"2026-08-15T19:51:58.179481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.157646Z","title":"Large scale distributed deep networks","venue":null,"work_id":"cb317337-dc29-40d6-8ba1-595dba3b40b1","year":2012},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.117775Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:d54b1c6509da57281f719a4bf6055a5b99e4b498608cce4b9b7ca70542d6c09a","observation_id":"54aa5da8-88d6-4e95-90a2-9810e0d61aaa","resolution":{"observed_at":"2026-08-15T19:51:58.162759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.141312Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"4c8e0e1a-95ea-4079-ae68-488af2a63e3f","year":2014},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.122651Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:512da254c8e6c47fbe4f4dce0542e0b32c74bea8fefe08060ebd7279fb66ba23","observation_id":"b50d58d6-a6b0-49fe-87de-0c176bf36cca","resolution":{"observed_at":"2026-08-15T19:51:58.146588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.125585Z","title":"Bridge: Byzantine-resilient decentralized gradient descent","venue":null,"work_id":"c9fe57dd-162b-4f78-a9ec-e175aeffbdbc","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.128445Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:b5cb6d204d150692736f0e018ab963cdc9df7cb25fbda630ef22665de768be6d","observation_id":"e8073d6e-109f-4bc0-9f91-5aa23fe898c2","resolution":{"observed_at":"2026-08-15T19:51:58.130540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.109056Z","title":"Local model poisoning attacks to byzantine-robust federat ed learning","venue":null,"work_id":"77518723-d8e7-406c-8f2a-431acb0bc2dc","year":2020},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.133344Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:e279a8f2940f90ca5f507b7e6abb2d24282cf7db1d2a2093727f294d99f87a7b","observation_id":"9352230d-4d9c-43c4-8cd5-893e0d11ae49","resolution":{"observed_at":"2026-08-15T19:51:58.113812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.093467Z","title":"Byzantine- robust decentralized federated learning","venue":null,"work_id":"0f7dcdf2-9b73-48a9-9a43-c8f2b6377cc3","year":2024},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.138199Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:fdcd244a7132fa5abca50f794b864ebaf9b9478a6b345cd804f0e47b490147ac","observation_id":"6074d299-3bf6-4938-8f95-2709d43df90a","resolution":{"observed_at":"2026-08-15T19:51:58.098360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.077445Z","title":"Model inversion attacks that exploit confidence informatio n and basic countermeasures","venue":null,"work_id":"10b41c30-3b12-46ae-8836-6188a662a524","year":2015},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.143648Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:9914c05a0f3d14adcd64598cafc5127fefdb00d85df539ef85dfb2f98bd79392","observation_id":"5789c9e5-ee74-4bf3-aabb-87445a64fbcf","resolution":{"observed_at":"2026-08-15T19:51:58.083149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17970","last_updated":"2024-04-27T18:17:36Z","snapshot_observed_at":"2026-08-21T02:23:54.183936Z","submitted_at":"2024-04-27T18:17:36Z","title":"Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.17970","snapshot_observed_at":"2026-08-15T19:51:57.151663Z","title":"Privacy-preserving aggregation for decentralized learning with byzantine-robustness","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.151663Z"},"links":{"cited_paper":"/paper/2404.17970","citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:66d27fd883b046e479800fa4cb36f1e97b7c816a4d13808ad71c8747dfee232e","observation_id":"530377a9-fd13-4797-bc16-7aba760e8e1f","resolution":{"observed_at":"2026-08-15T19:51:57.151663Z","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":"2026-08-15T19:51:58.062144Z","title":"The hidde n vulnerability of distributed learning in byzantium","venue":null,"work_id":"f9eccabb-3998-4556-a173-03c274d4fdb1","year":null},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.157784Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:1501ac0eb827d832fa1fc5c883c1f25af19ca5687e560fc8da5c6f2af531e1b6","observation_id":"98cb30f7-bfc4-4cf8-9912-f91ccee8f174","resolution":{"observed_at":"2026-08-15T19:51:58.067205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.044654Z","title":"Gradvit: Gradient inversion of vision transformers","venue":null,"work_id":"c9835aef-2bf5-4709-8c62-a6da1e448fe4","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.163575Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:503d866eef02897a6a270df7c67468bdb8435e18cdfb9e6d5a80ba06fbbf509b","observation_id":"afd5ce63-df85-4d4e-a048-2d20d7fb0863","resolution":{"observed_at":"2026-08-15T19:51:58.050821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01545","last_updated":"2023-04-20T15:22:15Z","snapshot_observed_at":"2026-08-16T17:23:53.342388Z","submitted_at":"2022-02-03T12:04:36Z","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01545","snapshot_observed_at":"2026-08-15T19:51:57.168929Z","title":"Byzantine-robust decentralized learning via clippedgoss ip","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.168929Z"},"links":{"cited_paper":"/paper/2202.01545","citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:be6511c5b0de30b72652c3822996ea90d196ea1b224761c93f376e6728ef4862","observation_id":"c03d6168-e9c1-4306-83b3-4d5490052fe7","resolution":{"observed_at":"2026-08-15T19:51:57.168929Z","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":"2026-08-15T19:51:58.028025Z","title":"What can we learn privately? SIAM Journal on Computing , 40(3):793–826, 2011","venue":null,"work_id":"f468181b-eb4e-44d7-866f-f29954580e20","year":2011},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.174729Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:191587785f2d54a7f258694f925a1d18a835f1a47f1ef89fcb13d41a82d96abf","observation_id":"6e950416-faca-4719-8630-5780521fc902","resolution":{"observed_at":"2026-08-15T19:51:58.032928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:58.012348Z","title":"Revisiting gradient clipping: Stochastic bias and t ight convergence guarantees","venue":null,"work_id":"765d426e-a269-474d-b9b9-39eeace60adb","year":2023},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.180624Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:1399424e435bb3848c7d718b31285eba3aa3331887afefb1c0be01cafe5f27a7","observation_id":"a4ed7df5-c987-405f-a6d4-4885aa217261","resolution":{"observed_at":"2026-08-15T19:51:58.017486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.996990Z","title":"A unified theory of decentralize d sgd with changing topology and local updates","venue":null,"work_id":"0fac4e53-7ec2-4f69-b2fb-b1b799845460","year":null},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.187107Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:f386b0871d5a76d38afcf885b53236713dae7081e884751f7e222d3b8d9346b5","observation_id":"68e1c3ab-7cf1-45af-8644-87d3e9fa6b79","resolution":{"observed_at":"2026-08-15T19:51:58.002125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.981361Z","title":"Resilient asymptotic consensus in robust networks","venue":null,"work_id":"a3c29195-33c6-4894-8be1-634b881a2b23","year":2013},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.192603Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:9076e12dabec70c6ba4af36c29e81c5e0598246bf31cdef0070608c3b57a11fc","observation_id":"c8dc2363-398c-4722-8839-a10bb797b20d","resolution":{"observed_at":"2026-08-15T19:51:57.986269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.965162Z","title":"Byzantine resilient distributed learning in multirobot systems","venue":null,"work_id":"53a862af-de51-4076-8654-09dfde55eef9","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.197591Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:4f5fda30be68f7d6a399a7eb80bc51a7e714bcabfc75731e555a6aab5ef02e90","observation_id":"fab0351e-5743-4824-901f-e9f967deef30","resolution":{"observed_at":"2026-08-15T19:51:57.970195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.947822Z","title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized par allel stochastic gradient descent","venue":null,"work_id":"1860f0be-293e-4f49-aecc-a2a612aecb66","year":2017},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.203314Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:3438795420bfe652e660720277c7658e92db90bfd53160d2714eb108a752a9c7","observation_id":"5ddd4791-327b-40eb-a763-f1eac2875681","resolution":{"observed_at":"2026-08-15T19:51:57.953854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.932525Z","title":"Concentrated geo-privacy","venue":null,"work_id":"64302fd3-bdfd-4b7b-beae-bd8b03ad90ff","year":2023},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.208321Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:e66ed2bc3f1db8588c98a9472259f49a961be83661626f97e5208284ba6dec66","observation_id":"c501138b-160d-4166-967f-2c45f76435a6","resolution":{"observed_at":"2026-08-15T19:51:57.937290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.917487Z","title":"Privacy- preserving decentralized federated learning over time-va rying communication graph","venue":null,"work_id":"32fa7dee-95a2-471e-bac4-e4eb484ea81d","year":2023},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.213296Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:e5e778fc33375d7a46cc4011c5e7d5e1c78df56fac0b6262d19e76b6694916d3","observation_id":"2fb834fc-64dd-48b3-bca5-d62ce4de76e8","resolution":{"observed_at":"2026-08-15T19:51:57.922223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.902156Z","title":"Multidimension al approximate agreement in byzantine asynchronous systems","venue":null,"work_id":"1aaf34d9-f735-44a2-b0d4-e92255b93021","year":2013},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.218478Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:1e0aa32a0534ac2a6d7b4b14855a4e71aefb6f8f8b2d85064b85ed1486e00c78","observation_id":"21e5e0fe-112a-4942-a2fe-52397a4cdce5","resolution":{"observed_at":"2026-08-15T19:51:57.907232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.886393Z","title":"R´ enyi differential privacy","venue":null,"work_id":"fe59a164-1b78-4754-b72c-14666734a31c","year":2017},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.224050Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:a1a4d509930a448033ea1b85fdd37481d8b66377ae4f60cceed0d5f18a233964","observation_id":"e1f1b29a-6414-4464-81ce-fd66786f7f02","resolution":{"observed_at":"2026-08-15T19:51:57.891454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.869545Z","title":"Fault-tolerant rendezvous of multirobot systems","venue":null,"work_id":"34c53202-8476-42ea-989f-95385e49715a","year":2017},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.229399Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:2111459046a4f54d1cbbc3d3bc5d0dfbe50705d5ede2ab07dd4f22c9ae89960b","observation_id":"f9a2d164-8579-49ff-9b53-09dc6a65f56d","resolution":{"observed_at":"2026-08-15T19:51:57.874552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.854589Z","title":"On measures of entropy and information","venue":null,"work_id":"4308b0ee-45d6-4d66-bfb2-8585f52e0feb","year":1961},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.234990Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:3dd57f231c9bd8b7a4987d8a8cd3d7cf6c262588dac7c683e3604da930deade7","observation_id":"3311a323-647c-4298-8627-e6b73826076c","resolution":{"observed_at":"2026-08-15T19:51:57.859254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.837404Z","title":"A scala ble approach for privacy-preserving collaborative machine learning","venue":null,"work_id":"e0441731-1d23-49cf-83e5-441532fb9366","year":2020},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.240886Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:b90c51ab1df2132326f7044bdf5ccb97df8283aa571a1e3349d0c0786510b524","observation_id":"6b911d88-e81c-4093-9355-9b7b3adf70cd","resolution":{"observed_at":"2026-08-15T19:51:57.842660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.822607Z","title":"Training very deep networks","venue":null,"work_id":"dd791628-ced1-4296-8576-842c57ce40b5","year":2015},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.248699Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:e6a38d91b5f312af94db8c660d4fadfb8d2c3dd106246616cb75c047b86d5f64","observation_id":"44d0f507-e8b2-46ad-a75b-6ec88935f6b0","resolution":{"observed_at":"2026-08-15T19:51:57.827201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.806373Z","title":"Decentralized federated averaging","venue":null,"work_id":"0f7d9419-7f6c-4e78-b223-d025579f0e25","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.256149Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:313d9b284055775150ec9d13a45881f18381200e17e3396a47f6ac30743d0191","observation_id":"0ef1200b-4f6d-4acc-a2e9-a08119b45f9a","resolution":{"observed_at":"2026-08-15T19:51:57.811173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.790824Z","title":"Iterative byzantine vector consensus in incomplete graphs","venue":null,"work_id":"a48c90f3-f6f1-4fa6-aa2f-99ebcc414647","year":2014},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.263469Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:a20a3c09e8f76781c5a53c235e942e7d5984cf026118a975c9d9933d9429405b","observation_id":"2cc2009a-d398-4a29-b204-080f37777c6e","resolution":{"observed_at":"2026-08-15T19:51:57.796109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.10271","last_updated":"2018-07-10T06:24:07Z","snapshot_observed_at":"2026-08-14T18:58:46.754744Z","submitted_at":"2018-06-27T02:19:01Z","title":"A Resilient Convex Combination for consensus-based distributed algorithms","version":2},"cited_work":{"arxiv_id":"1806.10271","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.10271","snapshot_observed_at":"2026-08-15T19:51:57.458824Z","title":"A Resilient Convex Combination for consensus-based distributed algorithms","venue":"math.OC","work_id":"3e094c07-ef12-4834-8cb1-07ba41c12452","year":2018},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.269555Z"},"links":{"cited_paper":"/paper/1806.10271","citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:df8706f0c8faf9e5ae333262a810b55507d5039ee4417dea997b13587c00b567","observation_id":"6ec4db86-3b34-4ea6-8a6d-ad85f67cbea6","resolution":{"observed_at":"2026-08-15T19:51:57.468717Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.775564Z","title":"Tailoring gradient methods for differentially private distributed optimizati on","venue":null,"work_id":"c95f293e-dd3f-460a-a17f-588ab64c7f2a","year":2023},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.276948Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:d8d861828f73c17f1aa4df0e65b6aab7d8533c8ef316464eb19177d00c1a606c","observation_id":"14295073-ec68-4d8a-afb8-c808bbd80f69","resolution":{"observed_at":"2026-08-15T19:51:57.780560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.759800Z","title":"Byzantine- resilient decentralized stochastic optimization with rob ust aggregation rules","venue":null,"work_id":"aa8c9b93-2f22-4087-a8ff-a98da54260fc","year":2023},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.284272Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:5021615c80eb6216c2882a809a04c1cca9abb1b68548acb8e83f8603c396bb3c","observation_id":"6b644ad8-d863-442f-b0cf-44948d9885e1","resolution":{"observed_at":"2026-08-15T19:51:57.765352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.745219Z","title":"Faba: an algorithm for fast aggregation against byzantine attacks in distributed neural networks","venue":null,"work_id":"ea928d4a-94fd-4f36-bbab-16769d50f3e0","year":2019},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.291516Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:a94c419482046603a5903d2127cd7c7d2cd9270d182f47ccff8a5def0206cc64","observation_id":"107c87f3-afa3-4892-ac43-8476ff866a1b","resolution":{"observed_at":"2026-08-15T19:51:57.749986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.727434Z","title":"A(DP) 2SGD: Asynchronous decentralized parallel stochastic gradient descent with differential privacy","venue":null,"work_id":"e9b8007c-5d13-474a-bc7c-ad1e4c616398","year":2021},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.305661Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:78fefcf9e3a0ef4f0975ab823f2a14f090a04e48df319ca5b725ed539d42d91e","observation_id":"ca904949-c828-413e-b835-c11b6bf8f144","resolution":{"observed_at":"2026-08-15T19:51:57.735159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.710984Z","title":"Resilient multi-dimensional consensus in adversaria l environment","venue":null,"work_id":"aeade02d-6eab-4e92-8e23-96493caf2017","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.312016Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:874756f6d914607c79076c5e6b732278327dd34a546fc02b402c309463e2e385","observation_id":"e89d1fc5-ec03-432b-a26c-de8c014f8aee","resolution":{"observed_at":"2026-08-15T19:51:57.716252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.695204Z","title":"Byzantine-robust decentralized learning via remove-then-clip aggregation","venue":null,"work_id":"1213464e-b9db-449d-bb2c-6f98c445b685","year":2024},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.317956Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:858d37f66ef5645ca3aa9c1f1ba4b1ea3566e41969af4d10a780a6312cf9e91f","observation_id":"8075a8e3-7bbd-4ae6-b2f1-3890d2e74ae4","resolution":{"observed_at":"2026-08-15T19:51:57.700124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.678808Z","title":"Byrdie: Byzantine- resilient distributed coordinate descent for decentraliz ed learning","venue":null,"work_id":"b8e832c2-6e00-4de0-8f63-2581b9d23192","year":2019},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.323334Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:edb7f6d2ab8e9aee5587140a65240aa6876fe73dc3836b1d99025da4dadba6a2","observation_id":"2b13b457-8bbf-4711-811c-579cc583f61a","resolution":{"observed_at":"2026-08-15T19:51:57.684069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.660264Z","title":"On the tradeoff between privacy preservation and byzantine-robustness in decentralized learning","venue":null,"work_id":"adffa854-5ac6-41d0-88cd-2e459026a237","year":2024},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.328502Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:f2f2c1b66351912cf4b2f06b2958d83104253b6449de880ac3459215e3cf1f88","observation_id":"44883e39-f00b-42e9-8eb0-13a5258e9a2d","resolution":{"observed_at":"2026-08-15T19:51:57.666204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.643165Z","title":"Interior point algorithms: theory and analysis","venue":null,"work_id":"8bba6673-e5d5-4678-8d0e-4b78488e3741","year":2011},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.333498Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:badb95f87085b411ecc2cac192345a77a637d51d63bb090951df59218b5cd85e","observation_id":"2e2882cd-e4ae-48f4-b0dc-f811834b2d73","resolution":{"observed_at":"2026-08-15T19:51:57.648486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.625001Z","title":"Byzantine-robust distributed learning: Toward s optimal statistical rates","venue":null,"work_id":"ac1480bc-5d96-439e-bb42-faec2797d1d8","year":2018},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.338497Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:7ae1b1f59a8bbd6f9ef9ca32eb434773949fafce85c5ecaa2b27b30a554688dc","observation_id":"237b227d-d6f8-4e43-9a5d-a128e67c58c8","resolution":{"observed_at":"2026-08-15T19:51:57.631088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.607393Z","title":"Subsampled r´ enyi differential privacy and analytical moments accountant","venue":null,"work_id":"0f1b832d-fdfb-47f7-93bf-1776d8f17978","year":2019},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.345690Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:c62ab5e94cc8446254115d46f644a012575a14fbf4a8580582eb6fcd09c1d251","observation_id":"17bafdfb-6296-4aba-8c17-1176860ed5b0","resolution":{"observed_at":"2026-08-15T19:51:57.612371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.589585Z","title":"Admm based privacy-preserving decentralized optimizatio n","venue":null,"work_id":"23a82f92-47bc-43fd-918d-77840e24e8cd","year":2018},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.350952Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:5a02f9b62237714adced84a109cc70fb0c13222a5fd272978e0838473380f3f8","observation_id":"9fce5f06-6d24-48f9-8098-1e57cbaf1aec","resolution":{"observed_at":"2026-08-15T19:51:57.595182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.571664Z","title":"The secret revealer: Generative model-inversion attacks against deep neural networks","venue":null,"work_id":"db7d7671-4ab8-41b3-b0e7-848ecfabeded","year":2020},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.357297Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:f332c2032705e2859efda5279e16aab8951a5349cea289cf6de07478f97d211c","observation_id":"6ffedcdb-a64b-4ffc-bcd7-bc8578035661","resolution":{"observed_at":"2026-08-15T19:51:57.577696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-20T00:01:01.707115Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-15T19:51:57.363769Z","title":"idlg: Improved deep leakage from gradients","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.363769Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:d6016c9f77e1b4e4a19c190254a3ffd1b7841c8b61d368d82f81674d7a21a2dd","observation_id":"9a2ba5da-c2ec-4b9e-b4e6-12faee81ae17","resolution":{"observed_at":"2026-08-15T19:51:57.363769Z","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":"2026-08-15T19:51:57.547474Z","title":"Pvd-fl: A privacy-preserving and verifiable decentralized federated learning framework","venue":null,"work_id":"00f11a5a-9911-46a4-9733-5b00bbc40b1b","year":2022},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.371305Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:0f78b5fd930a9d10cc534846b1f871249870d3348496a86db959b9205df2ef63","observation_id":"8a96716a-237d-4d50-8a77-9952f7bb5a09","resolution":{"observed_at":"2026-08-15T19:51:57.553941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T19:51:57.529761Z","title":"Deep leakage from gradients","venue":null,"work_id":"80dd1409-5e2d-4762-a571-bd25edb792f3","year":2019},"citing_paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T19:51:57.379453Z"},"links":{"citing_paper":"/paper/2506.15181"},"observation_digest":"sha256:e05d55ca2c44295afd7615c30003931bf28d579b44c9a02ca64dc647ca7b9506","observation_id":"da2f047b-7bd6-4aa8-96c9-9bf768b71a90","resolution":{"observed_at":"2026-08-15T19:51:57.535309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.15181","last_updated":"2025-06-18T06:53:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T08:58:50.613750Z","submitted_at":"2025-06-18T06:53:52Z","title":"ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":1,"verified_fuzzy":51},"total_outbound_references":55},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2506.15181."}