{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ERRFMMHSUMYQN7RPC5L6QDELB7","short_pith_number":"pith:ERRFMMHS","schema_version":"1.0","canonical_sha256":"24625630f2a33106fe2f1757e80c8b0fdc967a7087af1c2f219d2f09e424fb70","source":{"kind":"arxiv","id":"2205.04134","version":3},"attestation_state":"computed","paper":{"title":"Federated Multi-Armed Bandits Under Byzantine Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artun Saday, Cem Tekin, \\.Ilker Demirel, Yi\\u{g}it Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2022-05-09T09:06:42Z","abstract_excerpt":"Multi-armed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multi-armed bandits (FMAB) is an emerging framework where a cohort of learners with heterogeneous local models play an MAB game and communicate their aggregated feedback to a server to learn a globally optimal arm. Two key hurdles in FMAB are communication-efficient learning and resilience to adversarial attacks. To address these issues, we study the FMAB problem in the presence of Byzantine clients who can"},"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":"2205.04134","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-09T09:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"21179bcbd6cfb0ea11e66a9c83d202be51e3cc9364f6f8d051fd6605ac50a1bf","abstract_canon_sha256":"7119d6d88e2aa56e4a544cfaa7d0d61e5d03f15477e4611f11749a9730c9c3b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:12.563139Z","signature_b64":"Tf/qQrie1zgGaW6bLsajC9nU3Yx1IO55iGwr578h8lg0jgB0szWwje0EZT7YC8ecquBFzNseyDu14sAIfWrXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24625630f2a33106fe2f1757e80c8b0fdc967a7087af1c2f219d2f09e424fb70","last_reissued_at":"2026-07-05T10:15:12.562580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:12.562580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Multi-Armed Bandits Under Byzantine Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artun Saday, Cem Tekin, \\.Ilker Demirel, Yi\\u{g}it Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2022-05-09T09:06:42Z","abstract_excerpt":"Multi-armed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multi-armed bandits (FMAB) is an emerging framework where a cohort of learners with heterogeneous local models play an MAB game and communicate their aggregated feedback to a server to learn a globally optimal arm. Two key hurdles in FMAB are communication-efficient learning and resilience to adversarial attacks. To address these issues, we study the FMAB problem in the presence of Byzantine clients who can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04134","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/2205.04134/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":"2205.04134","created_at":"2026-07-05T10:15:12.562639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04134v3","created_at":"2026-07-05T10:15:12.562639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04134","created_at":"2026-07-05T10:15:12.562639+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERRFMMHSUMYQ","created_at":"2026-07-05T10:15:12.562639+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERRFMMHSUMYQN7RP","created_at":"2026-07-05T10:15:12.562639+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERRFMMHS","created_at":"2026-07-05T10:15:12.562639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10147","citing_title":"Near Optimal Best Arm Identification for Clustered Bandits","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7","json":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7.json","graph_json":"https://pith.science/api/pith-number/ERRFMMHSUMYQN7RPC5L6QDELB7/graph.json","events_json":"https://pith.science/api/pith-number/ERRFMMHSUMYQN7RPC5L6QDELB7/events.json","paper":"https://pith.science/paper/ERRFMMHS"},"agent_actions":{"view_html":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7","download_json":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7.json","view_paper":"https://pith.science/paper/ERRFMMHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04134&json=true","fetch_graph":"https://pith.science/api/pith-number/ERRFMMHSUMYQN7RPC5L6QDELB7/graph.json","fetch_events":"https://pith.science/api/pith-number/ERRFMMHSUMYQN7RPC5L6QDELB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7/action/storage_attestation","attest_author":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7/action/author_attestation","sign_citation":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7/action/citation_signature","submit_replication":"https://pith.science/pith/ERRFMMHSUMYQN7RPC5L6QDELB7/action/replication_record"}},"created_at":"2026-07-05T10:15:12.562639+00:00","updated_at":"2026-07-05T10:15:12.562639+00:00"}