{"as_of":"2026-08-19T18:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d850884c6a6b4b089143a1cdfeafb217324530a2310bb4ec666cdac101d3b714","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:44:55.343341Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T08:16:52.079166Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-03T13:18:12.926797Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"cited_work":{"arxiv_id":"2504.17471","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.17471","snapshot_observed_at":"2026-07-03T13:18:12.926797Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","venue":"cs.LG","work_id":"33f71478-ace9-49df-982e-2d2b2b95bf66","year":2025},"citing_paper":{"arxiv_id":"2606.12246","last_updated":"2026-06-10T15:48:31Z","snapshot_observed_at":"2026-08-12T23:27:33.467854Z","submitted_at":"2026-06-10T15:48:31Z","title":"Efficient and Robust Online Learning to Rank in Decentralized Systems","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T08:16:52.079166Z"},"links":{"cited_paper":"/paper/2504.17471","citing_paper":"/paper/2606.12246"},"observation_digest":"sha256:6ddbf4e997f2ddb585114ed1f38f555028b5bda28995a610b16cd9dcbb52b4ca","observation_id":"d99b7e7f-91dc-4300-a157-121222776365","resolution":{"observed_at":"2026-07-03T13:18:12.928408Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.17471/citation-record","integrity":"/paper/2504.17471/integrity","json":"/paper/2504.17471/citation-record.json","paper":"/paper/2504.17471"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:56.101500Z","title":"Gossip learning as a decentral- ized alternative to federated learning,","venue":null,"work_id":"3317eedc-0dcc-45fc-939a-2e982cf28ecd","year":2019},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.124518Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:3d6b719738dc67b0973087c89a05139371c0d2a09dfb61db28aab4908dfbe23b","observation_id":"beddda73-1e47-4f69-8d2a-dc1765589386","resolution":{"observed_at":"2026-08-16T10:44:56.105450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.128981Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.128981Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:390b1b4525eceb73c25fa8cc168a45d201793f15a0106924b058bd3a7bdf7046","observation_id":"2e180433-575e-4f4d-a29f-14337696e1ba","resolution":{"observed_at":"2026-08-16T10:44:55.128981Z","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":"2026-08-16T10:44:55.132829Z","title":"Decentralized learning works: An empirical comparison of gossip learning and federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.132829Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:6146ba3a577195b940a4004f10e7569265cf490b81c1682bc65c3304679fc0bc","observation_id":"e8665a74-40c7-47d0-b81d-badbff286911","resolution":{"observed_at":"2026-08-16T10:44:55.132829Z","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":"2026-08-16T10:44:56.075268Z","title":"Muffliato: Peer-to- peer privacy amplification for decentralized optimization and averag- ing,","venue":null,"work_id":"2a88216e-26cc-42e8-bf97-5c48ab867232","year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.137077Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:9a9a9dbc81b1ae22b6b1f5b284e08f23d2bd677608b3e737cf08171e2e17d7f2","observation_id":"ab56e79c-6158-4165-a605-fd7fa0860638","resolution":{"observed_at":"2026-08-16T10:44:56.079069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:56.063012Z","title":"Cyclon: Inexpensive membership management for unstructured p2p overlays,","venue":null,"work_id":"bbf439f3-3cbb-46d1-b246-270f12f34c2c","year":2005},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.140892Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:99799b730fc2008d405db3f91a80307b30b2dcd9864fbcf576b09e97b6f781d0","observation_id":"5505dd0a-9e0b-4645-81c8-0c3b830a486d","resolution":{"observed_at":"2026-08-16T10:44:56.067177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:56.050909Z","title":"Communication-efficient topologies for decentralized learning with o(1) consensus rate,","venue":null,"work_id":"4e0f26b7-5940-4496-8df2-718922cbac01","year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.144845Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:a1112b2f1b972e9b5ef31be441c320b7590c5889de832ea0c919568ee45ead23","observation_id":"af848dc8-2cd2-4e1f-992d-4ea8a5c0d1b4","resolution":{"observed_at":"2026-08-16T10:44:56.055108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:56.038325Z","title":"Exponential graph is provably efficient for decentralized deep training,","venue":null,"work_id":"e3fdaffa-e8d8-49cf-b25d-f6cdde8025de","year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.148890Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:1fba07a2a49502fee49e6331595ebe8a721a96068c23b0c667a44daed0ad8efc","observation_id":"80ed295e-7aac-49be-9c62-b416a89cb4b4","resolution":{"observed_at":"2026-08-16T10:44:56.043328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:56.026915Z","title":"In- ferring communities of interest in collaborative learning-based recom- mender systems,","venue":null,"work_id":"a04a7292-86da-4709-a58c-02fef2d7dffd","year":2025},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.152919Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:27925ba311cfd4bca96004d77cdf818780d3e762ad1ec2f075f1487356fe6204","observation_id":"4f49c679-592b-4704-a705-008eddb1f555","resolution":{"observed_at":"2026-08-16T10:44:56.030806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.156375Z","title":"Scrutinizing the vulnerability of decentralized learning to membership inference attacks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.156375Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:e802bbb400afb14350b1cd0bf90e869aa14fab014bc57aff190d35a069423dff","observation_id":"219d1c79-9c1e-4aec-8fe4-8bf4dfe96b6a","resolution":{"observed_at":"2026-08-16T10:44:55.156375Z","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":"2026-08-16T10:44:55.160029Z","title":"Fall of empires: Breaking byzantine- tolerant sgd by inner product manipulation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.160029Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:46d16af93ee7f12f07630112e2379c0fec29e95fab5f2378dfe91d574d7af863","observation_id":"8b4da5cf-1aba-4636-a990-8a7c39ecc298","resolution":{"observed_at":"2026-08-16T10:44:55.160029Z","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":"2026-08-16T10:44:55.163895Z","title":"A little is enough: Circumvent- ing defenses for distributed learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.163895Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:8eb0b44cb26bb20b401b9a49d8a49038b5085dcd83e8b4d5533bcc9ff4e886d4","observation_id":"ccc2324b-8029-45f7-89e7-b6cf943dc8f2","resolution":{"observed_at":"2026-08-16T10:44:55.163895Z","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":"2026-08-16T10:44:56.001364Z","title":"Automatic adversarial adaption for stealthy poisoning attacks in federated learning,","venue":null,"work_id":"60e776d8-2cbb-4220-8da6-b032582ec604","year":2024},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.167540Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:055338ad023803dc9ee505e6e1872c374af69bc31153c4de5a3df8ef55d8124c","observation_id":"324d2a5c-dd4d-4522-ae71-e5c376d75de4","resolution":{"observed_at":"2026-08-16T10:44:56.005449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.989060Z","title":"Crowdguard: Federated backdoor detection in federated learning,","venue":null,"work_id":"f4355b4d-bec5-49c3-80a7-6529c3ba03fd","year":2024},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.171513Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:930c5e99621b27351a43b3f206f8856a3fc2d07bb0e9b45b653c4664dcfa13b8","observation_id":"a024da93-1c8a-4e40-bda4-48431a8820ed","resolution":{"observed_at":"2026-08-16T10:44:55.993131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.976669Z","title":"Fundamentals of robust machine learning,","venue":null,"work_id":"1c18689a-ccb3-4fe1-b706-4e51d33f016c","year":2024},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.175095Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:f8b0612301ecb24c827ab530f09a8ec24059facb1add715ae8885eff3b7a2c14","observation_id":"77ec6c6d-9780-48d4-9a22-4f5946e6eecc","resolution":{"observed_at":"2026-08-16T10:44:55.980431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.965102Z","title":"Interpretable deep learning under fire,","venue":null,"work_id":"596d1b7c-293e-408d-b712-1da74f499bd5","year":2020},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.178659Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:13c410101d2d7bb177f551a7612e8043598abdd8a2c98c144d0a4ad1fd95c16a","observation_id":"cf871714-b88d-45ee-bfbd-55e26d995f85","resolution":{"observed_at":"2026-08-16T10:44:55.968880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.953203Z","title":"Fixing by mixing: A recipe for optimal byzantine ml under heterogeneity,","venue":null,"work_id":"77ed2e29-47d3-4c37-9a11-867dd036a834","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.181973Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:012aa5f6a4eec0804bbc1f5f39b4c3a77f04f7181709027db80bb1c2fc9b31d4","observation_id":"2b2c1b18-169a-4eae-ad29-71e5bc45a330","resolution":{"observed_at":"2026-08-16T10:44:55.957443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.941639Z","title":"Byzantine machine learning: A primer,","venue":null,"work_id":"004f7143-3d5c-48c6-a7d3-1f99cb4cb335","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.185708Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:87611c98d22fb9384fb5b964b7f5b8f396c3f47439f308c2c0fd3d62ce064c16","observation_id":"0402691f-7a51-492b-bba7-ab64d036e009","resolution":{"observed_at":"2026-08-16T10:44:55.945458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.929956Z","title":"Robust distributed learning: Tight error bounds and breakdown point under data heterogeneity,","venue":null,"work_id":"7cbe332a-b7b3-46ea-ad64-6e305afdb1ef","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.189479Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:6e98e23e7d3f0ebb11803955ad5f128a8390e356a9a8da2bfa2e90ddb94988b4","observation_id":"3a322e5d-5f42-4eb2-a81c-7aecfab07af1","resolution":{"observed_at":"2026-08-16T10:44:55.934035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.193011Z","title":"Manipulating the byzantine: Opti- mizing model poisoning attacks and defenses for federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.193011Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:7989d5642377b2ae270c19cd5909152f91b9f5ba1474f03cb71225ea379d5a15","observation_id":"231321fc-9320-44a8-837f-a8414afe3360","resolution":{"observed_at":"2026-08-16T10:44:55.193011Z","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":"2026-08-16T10:44:55.910921Z","title":"Learning from history for byzantine robust optimization,","venue":null,"work_id":"e5ed52b6-f67e-4501-8f1a-09be284ba2ff","year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.196371Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:fad386030f4f3e250c0ebbbfb6f0a880171bb37a6199f94d1b072fc3e3d4fffa","observation_id":"21b0e91d-b071-447b-8d8c-a6d48c35574a","resolution":{"observed_at":"2026-08-16T10:44:55.914565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.898796Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping,","venue":null,"work_id":"80e61e1a-0050-4120-b5a2-a76dee691f61","year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.199901Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:01f074ad40a1fa043d97ca73fa7847da7fa5d6f6bca0d8b3ba99a4ca6a4776e6","observation_id":"8a1fec5c-5dac-4fa4-a047-b7221e4312f9","resolution":{"observed_at":"2026-08-16T10:44:55.902845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.886650Z","title":"Byzantine-resilient stochastic gradient descent for distributed learning: A lipschitz-inspired coordinate- wise median approach,","venue":null,"work_id":"ecbd5a69-75aa-49b8-89e0-b0655bd0e859","year":2019},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.204365Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:35b7ac98aa1c4884aaac0daeb09f124a74ed729b2d053bad74be8987d414e6af","observation_id":"e5034c41-abc8-444a-a473-63f6cbf1cc8c","resolution":{"observed_at":"2026-08-16T10:44:55.890820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.874981Z","title":"Byzantine-resilient decentralized stochas- tic optimization with robust aggregation rules,","venue":null,"work_id":"2fa8e5df-2e6d-4f26-a868-99e35c89ad8e","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.211518Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:ce31160a225a127bd1f0415c6ed931d29ee56e7de54079db79cfbbc0ab1d0bc8","observation_id":"6e809dd6-fecd-4d60-9ef9-b5909e550952","resolution":{"observed_at":"2026-08-16T10:44:55.878978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"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":"2026-08-16T10:44:55.215440Z","title":"Byzantine-robust decentralized learning via clippedgossip,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.215440Z"},"links":{"cited_paper":"/paper/2202.01545","citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:7e18951e52f3cf797d00065f85a63b69c00b889fb5cf41affd8d80296cf9b68b","observation_id":"803f32b2-2273-4dcc-801f-e9bbbdc07cd4","resolution":{"observed_at":"2026-08-16T10:44:55.215440Z","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":"2026-08-16T10:44:55.863026Z","title":"Byzantine-resilient distributed hypothesis testing with time-varying network topology,","venue":null,"work_id":"eacb0336-144d-4ffe-8d45-d55788e8dcdc","year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.219150Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:013bc949a7decc961b4e3bb774dd34346c27d512b75766bb33c20c1434ae45cd","observation_id":"5bb5f93e-ae17-42d4-a2a4-78ff1afc167d","resolution":{"observed_at":"2026-08-16T10:44:55.867047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.222466Z","title":"Byzantine-robust decentralized stochastic optimization over static and time-varying networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.222466Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:db9103185ff10baf7c7f561c4a4d3c6531808412bd1d891ae92df47aa693c120","observation_id":"e322478a-d838-42c3-89c7-cb84ac4381c5","resolution":{"observed_at":"2026-08-16T10:44:55.222466Z","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":"2026-08-16T10:44:55.844649Z","title":"Secure peer sampling,","venue":null,"work_id":"500bb259-88f6-4643-9493-f8c38a4c0dba","year":2010},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.225974Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:ba6d0670079e857b8cf74cb5b349ac139bea4b4f6bdf8ba3b59ace19c324190e","observation_id":"670315c4-bb08-464e-b851-f361d78b4c12","resolution":{"observed_at":"2026-08-16T10:44:55.848222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.832655Z","title":"Eclipse attacks on bitcoin’s peer-to-peer network,","venue":null,"work_id":"7b1ac2c5-78c4-4a5c-b8c4-08562b075d9e","year":2015},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.229486Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:3022f97ce6b6671a0a89dce6140a0f206d21a30c9f6bec083cc4abc9a27d862a","observation_id":"5257b10b-e417-44a2-b722-40b57f458cb5","resolution":{"observed_at":"2026-08-16T10:44:55.836939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.821149Z","title":"Eclipse attacks on overlay networks: Threats and defenses,","venue":null,"work_id":"b13e16fb-ff57-4fd5-8639-c32c495a1949","year":2006},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.232992Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:22d579ac77e090d742e28462b13444a500923c2770dc56cbce6761b678b131df","observation_id":"c537f61a-51f9-4eaa-8168-509a34bb7424","resolution":{"observed_at":"2026-08-16T10:44:55.824932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.809970Z","title":"Basalt: A rock-solid byzantine-tolerant peer sampling for very large decentral- ized networks,","venue":null,"work_id":"a98c03f2-cbff-4e6e-b24f-cbdd5fdce24f","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.236827Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:4f674822f357696bb14002fb23878bb5fc07cd3744bdee3cbf70844681aca5fd","observation_id":"a2867b62-d28b-4ea1-9ccb-f1cae8beb895","resolution":{"observed_at":"2026-08-16T10:44:55.813794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.798162Z","title":"Brahms: Byzantine resilient random membership sampling,","venue":null,"work_id":"4e1ef60f-4fa7-4e47-b98d-fa5ad6c895ea","year":2008},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.240365Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:85c05d35f5fa65959d4180e97ace371c32c4356fc0b38770c818d9e0ee9095d6","observation_id":"71be1217-108a-4331-a11e-9c1763518e31","resolution":{"observed_at":"2026-08-16T10:44:55.801978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.787407Z","title":"A measure of asymptotic efficiency for tests of a hypoth- esis based on the sum of observations,","venue":null,"work_id":"a9a60710-dac5-4e08-be47-f2b43a28f257","year":1952},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.243907Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:f08726c9e39e3c6d8fcf2337c0c0c128b4e5fc7893e2df45d8ec7aa24a4e1f77","observation_id":"4cbcc771-e379-4d12-876d-195f15312eb8","resolution":{"observed_at":"2026-08-16T10:44:55.791162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.775528Z","title":"Pepper: Empowering user-centric recommender systems over gossip learning,","venue":null,"work_id":"526644c1-e35a-4b53-94ca-1964a365a829","year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.247869Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:6ee7f614173140077605c173814ece90690e1e64c675b978583895e747aaced8","observation_id":"b89a3ee0-a6c1-4125-a5a9-26b28ee78eaf","resolution":{"observed_at":"2026-08-16T10:44:55.780114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.252182Z","title":"Robust aggregation for federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.252182Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:069367aa9999612180848ade39551c2b0fd20b8e792d4e8d0e7b8246fc1c5e43","observation_id":"72e34d36-5428-4e38-8ff0-b95d9d1c9316","resolution":{"observed_at":"2026-08-16T10:44:55.252182Z","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":"2026-08-16T10:44:55.256381Z","title":"Byzantine-robust dis- tributed learning: Towards optimal statistical rates,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.256381Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:490b85d433c8f9771811f4d837014e8de2dba4363461322980eb626ed95ab5d5","observation_id":"47534fea-59d0-470b-8475-4f9c767dd61d","resolution":{"observed_at":"2026-08-16T10:44:55.256381Z","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":"2026-08-16T10:44:55.260044Z","title":"Bridge: Byzantine-resilient decen- tralized gradient descent,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.260044Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:b4d868603b1b37d0bb47616ef53addc0884920a8f9104552ae604b0c0626ee50","observation_id":"1cbfd23e-e606-441c-b326-777c27ef84c8","resolution":{"observed_at":"2026-08-16T10:44:55.260044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.02757","last_updated":"2017-03-08T09:26:36Z","snapshot_observed_at":"2026-08-16T21:10:44.237485Z","submitted_at":"2017-03-08T09:26:36Z","title":"Byzantine-Tolerant Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.02757","snapshot_observed_at":"2026-08-16T10:44:55.264121Z","title":"Byzantine-tolerant machine learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.264121Z"},"links":{"cited_paper":"/paper/1703.02757","citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:2b1ecc927aca6f68db69bf44a2d31ebcfb31c1cfd5ab0f7305649941e2a1556b","observation_id":"3fd31dd2-6b86-43e2-814e-037e96597564","resolution":{"observed_at":"2026-08-16T10:44:55.264121Z","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":"2026-08-16T10:44:55.268118Z","title":"Byrdie: Byzantine-resilient distributed coordinate descent for decentralized learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.268118Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:02bb25b3570b0c434ad6be924eeb55a8561b8d093b3eceefe7de97d1c4230acd","observation_id":"f54ed084-2422-466d-9136-e79bcaee50c6","resolution":{"observed_at":"2026-08-16T10:44:55.268118Z","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":"2026-08-16T10:44:55.736072Z","title":"Byzantine-robust decentralized federated learning,","venue":null,"work_id":"a0362972-de69-41b7-ba29-de29f6da8a8c","year":2024},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.271995Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:8e5d1d7673e8c2513ea49239b106c28d4ea531de7a804bec900c89167bbff2a3","observation_id":"8f4ec05b-ffa2-43f8-95c1-66218e82705e","resolution":{"observed_at":"2026-08-16T10:44:55.739752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.275468Z","title":"Zenops: A distributed learning system integrating communication efficiency and security,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.275468Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:defd06453700820a2868e61b168b15117d50000a8edca3855232bc2f4ed6b0c1","observation_id":"90165ba7-0269-446d-bada-e92ae8038525","resolution":{"observed_at":"2026-08-16T10:44:55.275468Z","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":"2026-08-16T10:44:55.717751Z","title":"Unraveling the connections between privacy and certified robustness in federated learning against poisoning attacks,","venue":null,"work_id":"bc7ebff7-ceb9-49a5-a373-003ae6d1149e","year":2023},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.278929Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:70007785662e4f0bed0942b4cd2acd0485ab35e0970645416f390211a7e918b0","observation_id":"de1c831d-b686-47f0-b785-94e18f66c80d","resolution":{"observed_at":"2026-08-16T10:44:55.721445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.706477Z","title":"Min- wise independent permutations,","venue":null,"work_id":"ad638c12-f8c2-415c-8fea-c06a9a42f715","year":1998},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.282562Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:12f315bfb346dd112c0bea5f768677c4766afa2fdf14c0643bdc3cbf118f6dec","observation_id":"ce299da3-d484-4926-afff-cdbaa4b6ae9f","resolution":{"observed_at":"2026-08-16T10:44:55.710376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1109.1396","last_updated":"2012-06-06T09:26:30Z","snapshot_observed_at":"2026-08-15T04:36:11.721590Z","submitted_at":"2011-09-07T09:16:37Z","title":"Gossip Learning with Linear Models on Fully Distributed Data","version":3},"cited_work":{"arxiv_id":"1109.1396","doi":null,"metadata_source":"pith","pith_arxiv_id":"1109.1396","snapshot_observed_at":"2026-08-16T10:44:55.374359Z","title":"Gossip Learning with Linear Models on Fully Distributed Data","venue":"cs.LG","work_id":"485b03e8-f590-401c-9a57-298043af26ed","year":2011},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.287657Z"},"links":{"cited_paper":"/paper/1109.1396","citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:d0d8f80546a11228879dc268b4cad8ae13032a4de15e0adefd4f95d369ce9977","observation_id":"5d420862-02de-41d8-b693-4e1670d99baf","resolution":{"observed_at":"2026-08-16T10:44:55.380130Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.694247Z","title":"Fast linear iterations for distributed averaging,","venue":null,"work_id":"2e675504-687a-4356-9cb0-f38eee9ac6bc","year":2004},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.291613Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:56afc92bc2b44cb4100a5d1a314b7c07de8ad82447f9ae180045ba62fc9235b0","observation_id":"3cf477f4-1b8d-4d51-a046-e8650938b41d","resolution":{"observed_at":"2026-08-16T10:44:55.698482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.682718Z","title":"On the uniformity of peer sampling based on view shuffling,","venue":null,"work_id":"01995c09-94a1-433a-a13e-fd93d59e5a99","year":2011},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.295270Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:ded0acd0844d804ce0c3818716283f6ad4df23af34eb6a2af3f1cccd63640fa2","observation_id":"8246867c-1ad0-41a3-bd7d-1b0085d9303a","resolution":{"observed_at":"2026-08-16T10:44:55.686399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.671312Z","title":"The peer sampling service: Experimental evaluation of unstructured gossip- based implementations,","venue":null,"work_id":"01aeb71e-4ef0-4cbc-8b5e-523fc114cf97","year":2004},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.299030Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:e286affe856f86ba471d21c3546847d90e369322cffc85a94785f9dd5c6faa5f","observation_id":"27a12788-43a7-448a-802b-ea64d5a0f574","resolution":{"observed_at":"2026-08-16T10:44:55.675224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.648570Z","title":"Correctness of a gossip based membership protocol,","venue":null,"work_id":"a22ccb52-1983-48e8-b94f-03f7e714b16b","year":2005},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.306547Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:f3153b15863a003a350de7df0f92bc22ffa2a6ddf5b7403beecfe267b5ce45f1","observation_id":"15710ca6-19b1-420c-b8d7-53b4392db669","resolution":{"observed_at":"2026-08-16T10:44:55.652415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.637025Z","title":"Approximate byzantine fault- tolerance in distributed optimization,","venue":null,"work_id":"78d0ea51-6270-41de-b91a-5b21b04fdaaa","year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.310077Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:2613ed3b12c85b2fdf1582a1cf4e40f2ce0a0ec94ee54742443d2075a65c9362","observation_id":"5286022f-00ca-43c6-be75-b742fb9c3cb6","resolution":{"observed_at":"2026-08-16T10:44:55.641037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10418","last_updated":"2025-06-10T18:04:41Z","snapshot_observed_at":"2026-08-18T00:31:53.561678Z","submitted_at":"2024-10-14T12:10:52Z","title":"Unified Breakdown Analysis for Byzantine Robust Gossip","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10418","snapshot_observed_at":"2026-08-16T10:44:55.313456Z","title":"Unified breakdown analysis for byzantine robust gossip,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.313456Z"},"links":{"cited_paper":"/paper/2410.10418","citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:952f62db8f1814b65924304bef550b16817481b3a9118d88188383ac28c9dafb","observation_id":"acda48b4-5a43-4559-8ef6-724f07ade0a8","resolution":{"observed_at":"2026-08-16T10:44:55.313456Z","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":"2026-08-16T10:44:55.317015Z","title":"Mitzenmacher and E","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.317015Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:0178f5246a30624693a54957361cebb31e066b60d70646679e28011ce00fbdb3","observation_id":"acacef07-b51d-4597-b464-1fe4846db488","resolution":{"observed_at":"2026-08-16T10:44:55.317015Z","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":"2026-08-16T10:44:55.321579Z","title":"Pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.321579Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:0623523cd3eb02d5ad52b7b1e5586d1232bdcc9ecf17761923d2f14b7bc7ec20","observation_id":"520bd842-8814-4ae1-be22-d63d6086300d","resolution":{"observed_at":"2026-08-16T10:44:55.321579Z","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":"2026-08-16T10:44:55.325206Z","title":"The mnist database of handwritten digits,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.325206Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:52729f80fcf909850d63dee799fafef3dbebea5a71b97133b1b1c0a4628279b7","observation_id":"66361a31-7004-4b67-99cf-353952163c48","resolution":{"observed_at":"2026-08-16T10:44:55.325206Z","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":"2026-08-16T10:44:55.328554Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.328554Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:4677e9505e564a3b6516355baddfa8811f0ac4a36ecf8b34bbec7e91f41685dc","observation_id":"40e10647-a45f-45eb-8930-18b8571ecfc6","resolution":{"observed_at":"2026-08-16T10:44:55.328554Z","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":"2026-08-16T10:44:55.333008Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.333008Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:c38a3cfd7eeb979749f34468a9d1e0568cac57bef7695f3b539fb58dec54d36d","observation_id":"d96486a0-7aba-4a5d-bc02-6600fdc7d206","resolution":{"observed_at":"2026-08-16T10:44:55.333008Z","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":"2026-08-16T10:44:55.336484Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.336484Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:c7280996b8dd51f85b61b96ea7330dd7b3e4f984bec093a1d26dc6b54c6a9f32","observation_id":"f7adef4e-5841-491a-890a-19052d07e6ce","resolution":{"observed_at":"2026-08-16T10:44:55.336484Z","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":"2026-08-16T10:44:55.339781Z","title":"A unified theory of decentralized sgd with changing topology and local updates,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.339781Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:ef83b5f4323f511bcbd4ff3056e2516aff21dde0f07085879744b04faee19075","observation_id":"bda3f802-a8dc-4c00-98dc-06c3c6a35108","resolution":{"observed_at":"2026-08-16T10:44:55.339781Z","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":"2026-08-16T10:44:55.577234Z","title":"Gossip-based peer sampling,","venue":null,"work_id":"037de516-c26b-4243-af0f-4950d31fe8ed","year":2007},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.343341Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:b1243e0a24ad2e37e9175d93ba3b0c94167ff114656963e5bb3b96f094790d4d","observation_id":"b8ec228f-77bd-4cb8-ac2b-24901ad1fbe0","resolution":{"observed_at":"2026-08-16T10:44:55.581030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:44:55.660082Z","title":"Springer, 2004, pp","venue":null,"work_id":"24cd6e86-7055-43d6-88df-c2ade2f5afa4","year":2004},"citing_paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","version":2},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:55.302815Z"},"links":{"citing_paper":"/paper/2504.17471"},"observation_digest":"sha256:12ea921506eb3ed4dc01e03e749ab4c52f5507f4f777b12f07440b99e7450ef4","observation_id":"8821b9d2-8e8d-40a1-8902-eb391050cf79","resolution":{"observed_at":"2026-08-16T10:44:55.663805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.17471","last_updated":"2026-06-01T14:09:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T05:37:01.897703Z","submitted_at":"2025-04-24T12:03:15Z","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":1,"verified_fuzzy":35},"total_outbound_references":58},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2504.17471."}