{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z2ZX3CCMBYKZR3NVX6HTETVQQB","short_pith_number":"pith:Z2ZX3CCM","schema_version":"1.0","canonical_sha256":"ceb37d884c0e1598edb5bf8f324eb080618f84b0b2292af2a92e6d5908a8f957","source":{"kind":"arxiv","id":"2110.11006","version":1},"attestation_state":"computed","paper":{"title":"Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Johan Pouwelse, Joost Verbraeken, Martijn de Vos","submitted_at":"2021-10-21T09:20:48Z","abstract_excerpt":"Federated learning (FL) is a privacy-friendly type of machine learning where devices locally train a model on their private data and typically communicate model updates with a server. In decentralized FL (DFL), peers communicate model updates with each other instead. However, DFL is challenging since (1) the training data possessed by different peers is often non-i.i.d. (i.e., distributed differently between the peers) and (2) malicious, or Byzantine, attackers can share arbitrary model updates with other peers to subvert the training process.\n  We address these two challenges and present Bris"},"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":"2110.11006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-10-21T09:20:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6b4415010c4b3c8a97ac35d075463f1f8a65d457842085e16a42ed8e23c2e58","abstract_canon_sha256":"af79de7f0473d231b85b285096ba3bb50588e81c3487fba3145b839c48070332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:35.096095Z","signature_b64":"TrsLkYEF3+GY/QrIsu2vdzv3jzuQZw7qzs7MsM9kktgIzPs+6lxKxxi0X3AGh+A1DzwG2k4kVNdMLw8OWNdQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb37d884c0e1598edb5bf8f324eb080618f84b0b2292af2a92e6d5908a8f957","last_reissued_at":"2026-07-05T03:24:35.095667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:35.095667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Johan Pouwelse, Joost Verbraeken, Martijn de Vos","submitted_at":"2021-10-21T09:20:48Z","abstract_excerpt":"Federated learning (FL) is a privacy-friendly type of machine learning where devices locally train a model on their private data and typically communicate model updates with a server. In decentralized FL (DFL), peers communicate model updates with each other instead. However, DFL is challenging since (1) the training data possessed by different peers is often non-i.i.d. (i.e., distributed differently between the peers) and (2) malicious, or Byzantine, attackers can share arbitrary model updates with other peers to subvert the training process.\n  We address these two challenges and present Bris"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11006","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/2110.11006/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":"2110.11006","created_at":"2026-07-05T03:24:35.095736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11006v1","created_at":"2026-07-05T03:24:35.095736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11006","created_at":"2026-07-05T03:24:35.095736+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2ZX3CCMBYKZ","created_at":"2026-07-05T03:24:35.095736+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2ZX3CCMBYKZR3NV","created_at":"2026-07-05T03:24:35.095736+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2ZX3CCM","created_at":"2026-07-05T03:24:35.095736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.09658","citing_title":"BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB","json":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB.json","graph_json":"https://pith.science/api/pith-number/Z2ZX3CCMBYKZR3NVX6HTETVQQB/graph.json","events_json":"https://pith.science/api/pith-number/Z2ZX3CCMBYKZR3NVX6HTETVQQB/events.json","paper":"https://pith.science/paper/Z2ZX3CCM"},"agent_actions":{"view_html":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB","download_json":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB.json","view_paper":"https://pith.science/paper/Z2ZX3CCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11006&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2ZX3CCMBYKZR3NVX6HTETVQQB/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2ZX3CCMBYKZR3NVX6HTETVQQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB/action/storage_attestation","attest_author":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB/action/author_attestation","sign_citation":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB/action/citation_signature","submit_replication":"https://pith.science/pith/Z2ZX3CCMBYKZR3NVX6HTETVQQB/action/replication_record"}},"created_at":"2026-07-05T03:24:35.095736+00:00","updated_at":"2026-07-05T03:24:35.095736+00:00"}