{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GIATE423RH56FEBK7YEVYXBFZK","short_pith_number":"pith:GIATE423","schema_version":"1.0","canonical_sha256":"320132735b89fbe2902afe095c5c25caa56a4c55b1250e8228588eb92b1d0541","source":{"kind":"arxiv","id":"2402.12780","version":2},"attestation_state":"computed","paper":{"title":"Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geovani Rizk, Nirupam Gupta, Rachid Guerraoui, Rafael Pinot, Sadegh Farhadkhani, Sasha Voitovych, Youssef Allouah","submitted_at":"2024-02-20T07:40:11Z","abstract_excerpt":"The possibility of adversarial (a.k.a., {\\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at the server in the standard $\\mathsf{FedAvg}$ algorithm by a \\emph{robust averaging rule}. While a significant amount of work has been devoted to studying the convergence of federated {\\em robust averaging} (which we denote by $\\mathsf{FedRo}$), prior work has largely ignored the impact of {\\em client subsampling} and {\\em local steps}, two fundamental FL ch"},"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":"2402.12780","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T07:40:11Z","cross_cats_sorted":[],"title_canon_sha256":"925d393740b0e294fdcd91fa28bd8b075f1947be49b4701b9d1739fa4961e61e","abstract_canon_sha256":"4a9e9803feacdd649c93822f2c322749dd65b360747b487a9a07dd72e8178481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.605994Z","signature_b64":"rNCqhjDhj9SwwAAtiVdB8FwwEhpcSNfHxAP/j+ufQttTn6jAldobGlDsYRFgVT9yduKiJLlH8RpvRdvz1favDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320132735b89fbe2902afe095c5c25caa56a4c55b1250e8228588eb92b1d0541","last_reissued_at":"2026-07-05T08:29:22.605566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.605566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Geovani Rizk, Nirupam Gupta, Rachid Guerraoui, Rafael Pinot, Sadegh Farhadkhani, Sasha Voitovych, Youssef Allouah","submitted_at":"2024-02-20T07:40:11Z","abstract_excerpt":"The possibility of adversarial (a.k.a., {\\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at the server in the standard $\\mathsf{FedAvg}$ algorithm by a \\emph{robust averaging rule}. While a significant amount of work has been devoted to studying the convergence of federated {\\em robust averaging} (which we denote by $\\mathsf{FedRo}$), prior work has largely ignored the impact of {\\em client subsampling} and {\\em local steps}, two fundamental FL ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12780","kind":"arxiv","version":2},"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/2402.12780/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":"2402.12780","created_at":"2026-07-05T08:29:22.605624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12780v2","created_at":"2026-07-05T08:29:22.605624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12780","created_at":"2026-07-05T08:29:22.605624+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIATE423RH56","created_at":"2026-07-05T08:29:22.605624+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIATE423RH56FEBK","created_at":"2026-07-05T08:29:22.605624+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIATE423","created_at":"2026-07-05T08:29:22.605624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.12672","citing_title":"Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK","json":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK.json","graph_json":"https://pith.science/api/pith-number/GIATE423RH56FEBK7YEVYXBFZK/graph.json","events_json":"https://pith.science/api/pith-number/GIATE423RH56FEBK7YEVYXBFZK/events.json","paper":"https://pith.science/paper/GIATE423"},"agent_actions":{"view_html":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK","download_json":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK.json","view_paper":"https://pith.science/paper/GIATE423","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12780&json=true","fetch_graph":"https://pith.science/api/pith-number/GIATE423RH56FEBK7YEVYXBFZK/graph.json","fetch_events":"https://pith.science/api/pith-number/GIATE423RH56FEBK7YEVYXBFZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK/action/storage_attestation","attest_author":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK/action/author_attestation","sign_citation":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK/action/citation_signature","submit_replication":"https://pith.science/pith/GIATE423RH56FEBK7YEVYXBFZK/action/replication_record"}},"created_at":"2026-07-05T08:29:22.605624+00:00","updated_at":"2026-07-05T08:29:22.605624+00:00"}