{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OQOQCHIBYGX4R7X3BBM6X2XSVD","short_pith_number":"pith:OQOQCHIB","schema_version":"1.0","canonical_sha256":"741d011d01c1afc8fefb0859ebeaf2a8f6a348acbfe0064d6a5de9289d79ce68","source":{"kind":"arxiv","id":"2606.26037","version":1},"attestation_state":"computed","paper":{"title":"FedReLa: Imbalanced Federated Learning via Re-Labeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Feng Liu, Guanghui Wang, Guangzheng Hu, Liuhua Peng, Mingming Gong, Patricia Men\\'endez","submitted_at":"2026-06-24T17:13:41Z","abstract_excerpt":"Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach that tackles the coexistence of data heteroge"},"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":"2606.26037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T17:13:41Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"a6162593a1c681cfbccc7350eaa6b74f93e29127c9485fa6af95427d02717d3b","abstract_canon_sha256":"948df6125f17c08ca5d84315c22c3b47f747fd2a6b5afb8769e5ff5fb55cbea8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:46.497134Z","signature_b64":"6RaBjwU2Gft4+LRQIFzaZvdnxrEaFGAJTAiecN2YOn23Wff/C3EVP02pzXWfUPytYlb1cthB2qZ8c07oGMO6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741d011d01c1afc8fefb0859ebeaf2a8f6a348acbfe0064d6a5de9289d79ce68","last_reissued_at":"2026-06-25T01:18:46.496752Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:46.496752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedReLa: Imbalanced Federated Learning via Re-Labeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Feng Liu, Guanghui Wang, Guangzheng Hu, Liuhua Peng, Mingming Gong, Patricia Men\\'endez","submitted_at":"2026-06-24T17:13:41Z","abstract_excerpt":"Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach that tackles the coexistence of data heteroge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26037","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/2606.26037/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":"2606.26037","created_at":"2026-06-25T01:18:46.496817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26037v1","created_at":"2026-06-25T01:18:46.496817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26037","created_at":"2026-06-25T01:18:46.496817+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQOQCHIBYGX4","created_at":"2026-06-25T01:18:46.496817+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQOQCHIBYGX4R7X3","created_at":"2026-06-25T01:18:46.496817+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQOQCHIB","created_at":"2026-06-25T01:18:46.496817+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/OQOQCHIBYGX4R7X3BBM6X2XSVD","json":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD.json","graph_json":"https://pith.science/api/pith-number/OQOQCHIBYGX4R7X3BBM6X2XSVD/graph.json","events_json":"https://pith.science/api/pith-number/OQOQCHIBYGX4R7X3BBM6X2XSVD/events.json","paper":"https://pith.science/paper/OQOQCHIB"},"agent_actions":{"view_html":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD","download_json":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD.json","view_paper":"https://pith.science/paper/OQOQCHIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26037&json=true","fetch_graph":"https://pith.science/api/pith-number/OQOQCHIBYGX4R7X3BBM6X2XSVD/graph.json","fetch_events":"https://pith.science/api/pith-number/OQOQCHIBYGX4R7X3BBM6X2XSVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD/action/storage_attestation","attest_author":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD/action/author_attestation","sign_citation":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD/action/citation_signature","submit_replication":"https://pith.science/pith/OQOQCHIBYGX4R7X3BBM6X2XSVD/action/replication_record"}},"created_at":"2026-06-25T01:18:46.496817+00:00","updated_at":"2026-06-25T01:18:46.496817+00:00"}