{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OQIHQC4PHQNFERBQSFI3ICR2YA","short_pith_number":"pith:OQIHQC4P","schema_version":"1.0","canonical_sha256":"7410780b8f3c1a5244309151b40a3ac0207ea32df9be1d0e4d4705e8f173507d","source":{"kind":"arxiv","id":"2302.06079","version":2},"attestation_state":"computed","paper":{"title":"Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Fangzhao Wu, Gang Chen, Lingjuan Lyu, Sai Wu, Yuchen Liu","submitted_at":"2023-02-13T03:31:50Z","abstract_excerpt":"Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent robust AGRs when data is non-Identically and Independently Distributed (non-IID). In this paper, we first reveal the root causes of performance degradation of current robust AGRs in non-IID settings: the curse of dimensionality and gradie"},"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":"2302.06079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T03:31:50Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"b4b67a39f91d451923d3e22bbfea5cb0dae7fcf8a3298d1b75bca13b9afdc076","abstract_canon_sha256":"c87f63c9973d65302a8f529e71bc5adda37ae962618f75ab21ff6cf9c3b36ddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:04.813485Z","signature_b64":"C1t/JH8cRQNVnTe0Uv/087wxgcvoDpoM5btAyDQxfbnQLgvKoNilfcA9JDPMBiGjr63ikpyA7FGt3NRkBGhICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7410780b8f3c1a5244309151b40a3ac0207ea32df9be1d0e4d4705e8f173507d","last_reissued_at":"2026-07-05T06:17:04.813040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:04.813040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Fangzhao Wu, Gang Chen, Lingjuan Lyu, Sai Wu, Yuchen Liu","submitted_at":"2023-02-13T03:31:50Z","abstract_excerpt":"Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent robust AGRs when data is non-Identically and Independently Distributed (non-IID). In this paper, we first reveal the root causes of performance degradation of current robust AGRs in non-IID settings: the curse of dimensionality and gradie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06079","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/2302.06079/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":"2302.06079","created_at":"2026-07-05T06:17:04.813095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06079v2","created_at":"2026-07-05T06:17:04.813095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06079","created_at":"2026-07-05T06:17:04.813095+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQIHQC4PHQNF","created_at":"2026-07-05T06:17:04.813095+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQIHQC4PHQNFERBQ","created_at":"2026-07-05T06:17:04.813095+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQIHQC4P","created_at":"2026-07-05T06:17:04.813095+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/OQIHQC4PHQNFERBQSFI3ICR2YA","json":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA.json","graph_json":"https://pith.science/api/pith-number/OQIHQC4PHQNFERBQSFI3ICR2YA/graph.json","events_json":"https://pith.science/api/pith-number/OQIHQC4PHQNFERBQSFI3ICR2YA/events.json","paper":"https://pith.science/paper/OQIHQC4P"},"agent_actions":{"view_html":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA","download_json":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA.json","view_paper":"https://pith.science/paper/OQIHQC4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06079&json=true","fetch_graph":"https://pith.science/api/pith-number/OQIHQC4PHQNFERBQSFI3ICR2YA/graph.json","fetch_events":"https://pith.science/api/pith-number/OQIHQC4PHQNFERBQSFI3ICR2YA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA/action/storage_attestation","attest_author":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA/action/author_attestation","sign_citation":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA/action/citation_signature","submit_replication":"https://pith.science/pith/OQIHQC4PHQNFERBQSFI3ICR2YA/action/replication_record"}},"created_at":"2026-07-05T06:17:04.813095+00:00","updated_at":"2026-07-05T06:17:04.813095+00:00"}