{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FUNVUPXOCRQKPCXWNYN2L2LSYW","short_pith_number":"pith:FUNVUPXO","schema_version":"1.0","canonical_sha256":"2d1b5a3eee1460a78af66e1ba5e972c59f068eefce25678fb38ccccf5fb0722c","source":{"kind":"arxiv","id":"2410.10418","version":3},"attestation_state":"computed","paper":{"title":"Unified Breakdown Analysis for Byzantine Robust Gossip","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Aymeric Dieuleveut, Hadrien Hendrikx, Renaud Gaucher","submitted_at":"2024-10-14T12:10:52Z","abstract_excerpt":"In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of *breakdown point*, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule, coined CS+, such that CS+-RG has a near-o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.10418","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-10-14T12:10:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ee85b38a4d2af1b525823779d623a334ef481bf494beaca083ce4e009c15ea9","abstract_canon_sha256":"a7c772f42982a6e3b6c20d3cb4fd5c00513c3aa63a64edbde92d17b5638f1d7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:21.650021Z","signature_b64":"GXmJnFi5+7ZW9MIgkenZ2anYkyhjwGOqmuc/rG2DUHIPvjU+bpCQ4YiFWkmroJYhgxw9RzN1EdI2kdi58zZ5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d1b5a3eee1460a78af66e1ba5e972c59f068eefce25678fb38ccccf5fb0722c","last_reissued_at":"2026-07-05T11:19:21.649493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:21.649493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Breakdown Analysis for Byzantine Robust Gossip","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Aymeric Dieuleveut, Hadrien Hendrikx, Renaud Gaucher","submitted_at":"2024-10-14T12:10:52Z","abstract_excerpt":"In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of *breakdown point*, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule, coined CS+, such that CS+-RG has a near-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10418","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.10418/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.10418","created_at":"2026-07-05T11:19:21.649553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10418v3","created_at":"2026-07-05T11:19:21.649553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10418","created_at":"2026-07-05T11:19:21.649553+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUNVUPXOCRQK","created_at":"2026-07-05T11:19:21.649553+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUNVUPXOCRQKPCXW","created_at":"2026-07-05T11:19:21.649553+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUNVUPXO","created_at":"2026-07-05T11:19:21.649553+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12246","citing_title":"Efficient and Robust Online Learning to Rank in Decentralized Systems","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW","json":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW.json","graph_json":"https://pith.science/api/pith-number/FUNVUPXOCRQKPCXWNYN2L2LSYW/graph.json","events_json":"https://pith.science/api/pith-number/FUNVUPXOCRQKPCXWNYN2L2LSYW/events.json","paper":"https://pith.science/paper/FUNVUPXO"},"agent_actions":{"view_html":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW","download_json":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW.json","view_paper":"https://pith.science/paper/FUNVUPXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10418&json=true","fetch_graph":"https://pith.science/api/pith-number/FUNVUPXOCRQKPCXWNYN2L2LSYW/graph.json","fetch_events":"https://pith.science/api/pith-number/FUNVUPXOCRQKPCXWNYN2L2LSYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW/action/storage_attestation","attest_author":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW/action/author_attestation","sign_citation":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW/action/citation_signature","submit_replication":"https://pith.science/pith/FUNVUPXOCRQKPCXWNYN2L2LSYW/action/replication_record"}},"created_at":"2026-07-05T11:19:21.649553+00:00","updated_at":"2026-07-05T11:19:21.649553+00:00"}