{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMBLKS2EJTAIKARH5RI7LUAUJK","short_pith_number":"pith:EMBLKS2E","schema_version":"1.0","canonical_sha256":"2302b54b444cc0850227ec51f5d0144aae18a77c7afbbb82a42ecf6709c8709e","source":{"kind":"arxiv","id":"2607.01474","version":1},"attestation_state":"computed","paper":{"title":"Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balakrishnan Ananthanarayanan, Diego Klabjan, Haemin Park, Martin W. Braun, Xiuqi Li","submitted_at":"2026-07-01T21:09:50Z","abstract_excerpt":"Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints. We propose FedCGNM (Federated Class-Grouped Normalized Momentum), a client-side optimizer in FL that partitions classes into a small number of groups based on minimum within-group variance, maintains a momentum per group, normalizes each group momentum to unit length, and uses the summation of the normalized group momentums as an update direction. Thi"},"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":"2607.01474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T21:09:50Z","cross_cats_sorted":[],"title_canon_sha256":"e088a5f44a13e483b7f4306f8aedcad832dfe43ff99910d32723d69478987022","abstract_canon_sha256":"cca31ddffef3a872db3c413698c85a0489210c8cea33dc47d4cb82c1c5379b37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:01.731901Z","signature_b64":"94S8b+JXu3Zp3X6J8wP/mCSOnLwbHT2K3rj74KAz9ymBtyjz/cZv6/qNb6BwAJ2lcOdcEjfptAiF/43MfvaNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2302b54b444cc0850227ec51f5d0144aae18a77c7afbbb82a42ecf6709c8709e","last_reissued_at":"2026-07-03T00:17:01.731495Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:01.731495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balakrishnan Ananthanarayanan, Diego Klabjan, Haemin Park, Martin W. Braun, Xiuqi Li","submitted_at":"2026-07-01T21:09:50Z","abstract_excerpt":"Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints. We propose FedCGNM (Federated Class-Grouped Normalized Momentum), a client-side optimizer in FL that partitions classes into a small number of groups based on minimum within-group variance, maintains a momentum per group, normalizes each group momentum to unit length, and uses the summation of the normalized group momentums as an update direction. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01474","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/2607.01474/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":"2607.01474","created_at":"2026-07-03T00:17:01.731551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01474v1","created_at":"2026-07-03T00:17:01.731551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01474","created_at":"2026-07-03T00:17:01.731551+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMBLKS2EJTAI","created_at":"2026-07-03T00:17:01.731551+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMBLKS2EJTAIKARH","created_at":"2026-07-03T00:17:01.731551+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMBLKS2E","created_at":"2026-07-03T00:17:01.731551+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/EMBLKS2EJTAIKARH5RI7LUAUJK","json":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK.json","graph_json":"https://pith.science/api/pith-number/EMBLKS2EJTAIKARH5RI7LUAUJK/graph.json","events_json":"https://pith.science/api/pith-number/EMBLKS2EJTAIKARH5RI7LUAUJK/events.json","paper":"https://pith.science/paper/EMBLKS2E"},"agent_actions":{"view_html":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK","download_json":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK.json","view_paper":"https://pith.science/paper/EMBLKS2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01474&json=true","fetch_graph":"https://pith.science/api/pith-number/EMBLKS2EJTAIKARH5RI7LUAUJK/graph.json","fetch_events":"https://pith.science/api/pith-number/EMBLKS2EJTAIKARH5RI7LUAUJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK/action/storage_attestation","attest_author":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK/action/author_attestation","sign_citation":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK/action/citation_signature","submit_replication":"https://pith.science/pith/EMBLKS2EJTAIKARH5RI7LUAUJK/action/replication_record"}},"created_at":"2026-07-03T00:17:01.731551+00:00","updated_at":"2026-07-03T00:17:01.731551+00:00"}