{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XQQ4CPV2LMPXD57HUWC2D3DADS","short_pith_number":"pith:XQQ4CPV2","schema_version":"1.0","canonical_sha256":"bc21c13eba5b1f71f7e7a585a1ec601ca985052a9a1b3167181a99a450bb6c50","source":{"kind":"arxiv","id":"2109.04094","version":2},"attestation_state":"computed","paper":{"title":"An Experimental Study of Class Imbalance in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C. Xiao, S. Wang","submitted_at":"2021-09-09T08:26:16Z","abstract_excerpt":"Federated learning is a distributed machine learning paradigm that trains a global model for prediction based on a number of local models at clients while local data privacy is preserved. Class imbalance is believed to be one of the factors that degrades the global model performance. However, there has been very little research on if and how class imbalance can affect the global performance. class imbalance in federated learning is much more complex than that in traditional non-distributed machine learning, due to different class imbalance situations at local clients. Class imbalance needs to "},"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":"2109.04094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T08:26:16Z","cross_cats_sorted":[],"title_canon_sha256":"4b5da58635671b5bb7a29f4ee21db7af395e73c6ac5b2b28c8dc8f2dba4824c7","abstract_canon_sha256":"c97e87a63b8f3e141c124a57e6c3cd723291c0aa21578265d82fba9e09c5f96c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:15.183851Z","signature_b64":"KapbH+CnQ4Csn3MgRE81k+3qibJUxYFjNQoZCyxfR7BtJMzzlz8ncgL2Wj2s8E7eycH2TMNksRLwowiK6HkTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc21c13eba5b1f71f7e7a585a1ec601ca985052a9a1b3167181a99a450bb6c50","last_reissued_at":"2026-07-05T04:09:15.183441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:15.183441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Experimental Study of Class Imbalance in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C. Xiao, S. Wang","submitted_at":"2021-09-09T08:26:16Z","abstract_excerpt":"Federated learning is a distributed machine learning paradigm that trains a global model for prediction based on a number of local models at clients while local data privacy is preserved. Class imbalance is believed to be one of the factors that degrades the global model performance. However, there has been very little research on if and how class imbalance can affect the global performance. class imbalance in federated learning is much more complex than that in traditional non-distributed machine learning, due to different class imbalance situations at local clients. Class imbalance needs to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04094","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/2109.04094/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":"2109.04094","created_at":"2026-07-05T04:09:15.183498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04094v2","created_at":"2026-07-05T04:09:15.183498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04094","created_at":"2026-07-05T04:09:15.183498+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQQ4CPV2LMPX","created_at":"2026-07-05T04:09:15.183498+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQQ4CPV2LMPXD57H","created_at":"2026-07-05T04:09:15.183498+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQQ4CPV2","created_at":"2026-07-05T04:09:15.183498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23849","citing_title":"CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS","json":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS.json","graph_json":"https://pith.science/api/pith-number/XQQ4CPV2LMPXD57HUWC2D3DADS/graph.json","events_json":"https://pith.science/api/pith-number/XQQ4CPV2LMPXD57HUWC2D3DADS/events.json","paper":"https://pith.science/paper/XQQ4CPV2"},"agent_actions":{"view_html":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS","download_json":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS.json","view_paper":"https://pith.science/paper/XQQ4CPV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04094&json=true","fetch_graph":"https://pith.science/api/pith-number/XQQ4CPV2LMPXD57HUWC2D3DADS/graph.json","fetch_events":"https://pith.science/api/pith-number/XQQ4CPV2LMPXD57HUWC2D3DADS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS/action/storage_attestation","attest_author":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS/action/author_attestation","sign_citation":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS/action/citation_signature","submit_replication":"https://pith.science/pith/XQQ4CPV2LMPXD57HUWC2D3DADS/action/replication_record"}},"created_at":"2026-07-05T04:09:15.183498+00:00","updated_at":"2026-07-05T04:09:15.183498+00:00"}