{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IGOWQIXAGP6FDJF3JJETS5FCQF","short_pith_number":"pith:IGOWQIXA","schema_version":"1.0","canonical_sha256":"419d6822e033fc51a4bb4a493974a28170ea7c98aff432e69c9229169e2a8dbc","source":{"kind":"arxiv","id":"2502.02727","version":3},"attestation_state":"computed","paper":{"title":"Gradient Correction in Federated Learning with Adaptive Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chaoyue Liu, Christopher Brinton, Dong-Jun Han, Evan Chen, Jianing Zhang, Shiqiang Wang","submitted_at":"2025-02-04T21:21:30Z","abstract_excerpt":"In federated learning (FL), model training performance is strongly impacted by data heterogeneity across clients. Client-drift compensation methods have recently emerged as a solution to this issue, introducing correction terms into local model updates. To date, these methods have only been considered under stochastic gradient descent (SGD)-based model training, while modern FL frameworks also employ adaptive optimizers (e.g., Adam) for improved convergence. However, due to the complex interplay between first and second moments found in most adaptive optimization methods, naively injecting cor"},"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":"2502.02727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:21:30Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"76e0ccd65ed9eccddf2feba7b5f84c97906b58141c06ae40d5bc4f2d3f57448c","abstract_canon_sha256":"0ceb5afee41f7cadebc0b33b82d2b5153d9108b3b84e49f0466e49d8b6b2d793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:45.009050Z","signature_b64":"oCgQ0NTiZqIlacz2acmHSLvKBW9ojc8aAuTryK6IyVdwj3Sc8yajD/XI1eRBpbKpXTc2/kp20TQqk1C5/16OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"419d6822e033fc51a4bb4a493974a28170ea7c98aff432e69c9229169e2a8dbc","last_reissued_at":"2026-07-05T11:04:45.008502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:45.008502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Correction in Federated Learning with Adaptive Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chaoyue Liu, Christopher Brinton, Dong-Jun Han, Evan Chen, Jianing Zhang, Shiqiang Wang","submitted_at":"2025-02-04T21:21:30Z","abstract_excerpt":"In federated learning (FL), model training performance is strongly impacted by data heterogeneity across clients. Client-drift compensation methods have recently emerged as a solution to this issue, introducing correction terms into local model updates. To date, these methods have only been considered under stochastic gradient descent (SGD)-based model training, while modern FL frameworks also employ adaptive optimizers (e.g., Adam) for improved convergence. However, due to the complex interplay between first and second moments found in most adaptive optimization methods, naively injecting cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02727","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/2502.02727/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":"2502.02727","created_at":"2026-07-05T11:04:45.008562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02727v3","created_at":"2026-07-05T11:04:45.008562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02727","created_at":"2026-07-05T11:04:45.008562+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGOWQIXAGP6F","created_at":"2026-07-05T11:04:45.008562+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGOWQIXAGP6FDJF3","created_at":"2026-07-05T11:04:45.008562+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGOWQIXA","created_at":"2026-07-05T11:04:45.008562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12968","citing_title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF","json":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF.json","graph_json":"https://pith.science/api/pith-number/IGOWQIXAGP6FDJF3JJETS5FCQF/graph.json","events_json":"https://pith.science/api/pith-number/IGOWQIXAGP6FDJF3JJETS5FCQF/events.json","paper":"https://pith.science/paper/IGOWQIXA"},"agent_actions":{"view_html":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF","download_json":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF.json","view_paper":"https://pith.science/paper/IGOWQIXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02727&json=true","fetch_graph":"https://pith.science/api/pith-number/IGOWQIXAGP6FDJF3JJETS5FCQF/graph.json","fetch_events":"https://pith.science/api/pith-number/IGOWQIXAGP6FDJF3JJETS5FCQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF/action/storage_attestation","attest_author":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF/action/author_attestation","sign_citation":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF/action/citation_signature","submit_replication":"https://pith.science/pith/IGOWQIXAGP6FDJF3JJETS5FCQF/action/replication_record"}},"created_at":"2026-07-05T11:04:45.008562+00:00","updated_at":"2026-07-05T11:04:45.008562+00:00"}