{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LSLII7BUYCX7MBB6U57KZFB6XA","short_pith_number":"pith:LSLII7BU","schema_version":"1.0","canonical_sha256":"5c96847c34c0aff6043ea77eac943eb8251bf878b59bb4d1cd6470b3f87921f7","source":{"kind":"arxiv","id":"2108.00365","version":2},"attestation_state":"computed","paper":{"title":"A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chuan Chen, Chunjiang Che, Xiaoli Li, Xiaoyu He, Zibin Zheng","submitted_at":"2021-08-01T05:11:15Z","abstract_excerpt":"Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine clients, which interfere with the training of the global model by modifying the model or uploading the false gradient. In this paper, we propose a novel serverless federated learning framework Committee Mechanism based Federated Learning (CMFL), which can ensure the robustness of the algorithm with convergence guarantee. In CMFL, a committee system is set up to screen the uploaded"},"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":"2108.00365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-01T05:11:15Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"243beb57a02fc1344da9cd66dfbc092c0d4023be38b244e626256832fc4c0649","abstract_canon_sha256":"31988461478f01f12693031224c642f5191dffe245db052a9ecf39bf12b1ff86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:36.411650Z","signature_b64":"k/Sp9lm/cD8HoA3Mm4bNk4STjUv976ha7MrtDqJjMpT9IusSfCzrwUaWcKyZxoXzvo8TfWV+9rLO6RtxN5yXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c96847c34c0aff6043ea77eac943eb8251bf878b59bb4d1cd6470b3f87921f7","last_reissued_at":"2026-07-05T04:55:36.411235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:36.411235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chuan Chen, Chunjiang Che, Xiaoli Li, Xiaoyu He, Zibin Zheng","submitted_at":"2021-08-01T05:11:15Z","abstract_excerpt":"Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine clients, which interfere with the training of the global model by modifying the model or uploading the false gradient. In this paper, we propose a novel serverless federated learning framework Committee Mechanism based Federated Learning (CMFL), which can ensure the robustness of the algorithm with convergence guarantee. In CMFL, a committee system is set up to screen the uploaded"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00365","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/2108.00365/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":"2108.00365","created_at":"2026-07-05T04:55:36.411292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00365v2","created_at":"2026-07-05T04:55:36.411292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00365","created_at":"2026-07-05T04:55:36.411292+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSLII7BUYCX7","created_at":"2026-07-05T04:55:36.411292+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSLII7BUYCX7MBB6","created_at":"2026-07-05T04:55:36.411292+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSLII7BU","created_at":"2026-07-05T04:55:36.411292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA","json":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA.json","graph_json":"https://pith.science/api/pith-number/LSLII7BUYCX7MBB6U57KZFB6XA/graph.json","events_json":"https://pith.science/api/pith-number/LSLII7BUYCX7MBB6U57KZFB6XA/events.json","paper":"https://pith.science/paper/LSLII7BU"},"agent_actions":{"view_html":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA","download_json":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA.json","view_paper":"https://pith.science/paper/LSLII7BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00365&json=true","fetch_graph":"https://pith.science/api/pith-number/LSLII7BUYCX7MBB6U57KZFB6XA/graph.json","fetch_events":"https://pith.science/api/pith-number/LSLII7BUYCX7MBB6U57KZFB6XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA/action/storage_attestation","attest_author":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA/action/author_attestation","sign_citation":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA/action/citation_signature","submit_replication":"https://pith.science/pith/LSLII7BUYCX7MBB6U57KZFB6XA/action/replication_record"}},"created_at":"2026-07-05T04:55:36.411292+00:00","updated_at":"2026-07-05T04:55:36.411292+00:00"}