{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MWEMOWQ6KHHYRMBKJLCLWXHUYO","short_pith_number":"pith:MWEMOWQ6","schema_version":"1.0","canonical_sha256":"6588c75a1e51cf88b02a4ac4bb5cf4c3a369e5d30d105fae1fb8fec231a42d7d","source":{"kind":"arxiv","id":"2407.08632","version":1},"attestation_state":"computed","paper":{"title":"Generalization Error Matters in Decentralized Learning Under Byzantine Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoxiang Ye, Qing Ling","submitted_at":"2024-07-11T16:12:53Z","abstract_excerpt":"Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central server. When some of the agents are malicious (also termed as Byzantine), resilient decentralized learning algorithms are able to limit the impact of these Byzantine agents without knowing their number and identities, and have guaranteed optimization errors. However, analysis of the generalization errors, which are critical to implementations of the trained"},"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":"2407.08632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T16:12:53Z","cross_cats_sorted":[],"title_canon_sha256":"7080e5c2455d05d4031957038cff85fb0465fcfae4411645c21648a3c66c8e17","abstract_canon_sha256":"491510a51a0b997b18f8071ac51299102213f615fbe0f85b33a1a40636b098d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:50.818870Z","signature_b64":"LuaN+IL+V96KSqSf0Lzci7sX22jZWHhv1KDrmb8niKphy94pugnE/WlUHxP7ml2q+IQea/bis2prbcRKvDowDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6588c75a1e51cf88b02a4ac4bb5cf4c3a369e5d30d105fae1fb8fec231a42d7d","last_reissued_at":"2026-07-05T08:42:50.818516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:50.818516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Error Matters in Decentralized Learning Under Byzantine Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoxiang Ye, Qing Ling","submitted_at":"2024-07-11T16:12:53Z","abstract_excerpt":"Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central server. When some of the agents are malicious (also termed as Byzantine), resilient decentralized learning algorithms are able to limit the impact of these Byzantine agents without knowing their number and identities, and have guaranteed optimization errors. However, analysis of the generalization errors, which are critical to implementations of the trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08632","kind":"arxiv","version":1},"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/2407.08632/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":"2407.08632","created_at":"2026-07-05T08:42:50.818574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08632v1","created_at":"2026-07-05T08:42:50.818574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08632","created_at":"2026-07-05T08:42:50.818574+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWEMOWQ6KHHY","created_at":"2026-07-05T08:42:50.818574+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWEMOWQ6KHHYRMBK","created_at":"2026-07-05T08:42:50.818574+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWEMOWQ6","created_at":"2026-07-05T08:42:50.818574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17740","citing_title":"Sensitivity Curve Maximization: Attacking Robust Aggregators in Distributed Learning","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO","json":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO.json","graph_json":"https://pith.science/api/pith-number/MWEMOWQ6KHHYRMBKJLCLWXHUYO/graph.json","events_json":"https://pith.science/api/pith-number/MWEMOWQ6KHHYRMBKJLCLWXHUYO/events.json","paper":"https://pith.science/paper/MWEMOWQ6"},"agent_actions":{"view_html":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO","download_json":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO.json","view_paper":"https://pith.science/paper/MWEMOWQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08632&json=true","fetch_graph":"https://pith.science/api/pith-number/MWEMOWQ6KHHYRMBKJLCLWXHUYO/graph.json","fetch_events":"https://pith.science/api/pith-number/MWEMOWQ6KHHYRMBKJLCLWXHUYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO/action/storage_attestation","attest_author":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO/action/author_attestation","sign_citation":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO/action/citation_signature","submit_replication":"https://pith.science/pith/MWEMOWQ6KHHYRMBKJLCLWXHUYO/action/replication_record"}},"created_at":"2026-07-05T08:42:50.818574+00:00","updated_at":"2026-07-05T08:42:50.818574+00:00"}