{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XP7NTOLSYDMDHZYD6ROYGWJICX","short_pith_number":"pith:XP7NTOLS","schema_version":"1.0","canonical_sha256":"bbfed9b972c0d833e703f45d83592815f0a4410ba9702a8c1fe46ed8e7fcd345","source":{"kind":"arxiv","id":"2310.07587","version":4},"attestation_state":"computed","paper":{"title":"Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Howard Hao Yang, Hualiang Wang, Jian Wu, Jin Hao, Joey Tianyi Zhou, Songshang Liu, Yang Feng, Zihan Chen, Zikai Xiao, Zuozhu Liu","submitted_at":"2023-10-11T15:28:39Z","abstract_excerpt":"Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks. This paper investigates a federated long-tailed learning (Fed-LT) task in which each client holds a locally heterogeneous dataset; if the datasets can be globally aggregated, they jointly exhibit a long-tailed distribution. Under such a setting, existing federated optimization and/or centralized long-tailed learning methods hardly apply due to challenges in (a) characterizing the global long-tailed distribution under privacy constraints and (b) adjusting the local learning strategy to co"},"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":"2310.07587","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T15:28:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"373fbc72cfa264a38ac7272bd29e546df30be4e9a8930eab0fe04a479a21211d","abstract_canon_sha256":"69e0ce5427d6a1b5d30684df9ae95b8bb90776cd4ad10ade31b09e507a4ba032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:47.378521Z","signature_b64":"N1mZH7eZehqVFp5nIsLfnErlOVA6hZK6PbuvyJPkTVRi2stNj69BMu4yDk3hk2QDsBYKTnffaB4ySloIAQmtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbfed9b972c0d833e703f45d83592815f0a4410ba9702a8c1fe46ed8e7fcd345","last_reissued_at":"2026-07-05T07:16:47.377999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:47.377999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Howard Hao Yang, Hualiang Wang, Jian Wu, Jin Hao, Joey Tianyi Zhou, Songshang Liu, Yang Feng, Zihan Chen, Zikai Xiao, Zuozhu Liu","submitted_at":"2023-10-11T15:28:39Z","abstract_excerpt":"Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks. This paper investigates a federated long-tailed learning (Fed-LT) task in which each client holds a locally heterogeneous dataset; if the datasets can be globally aggregated, they jointly exhibit a long-tailed distribution. Under such a setting, existing federated optimization and/or centralized long-tailed learning methods hardly apply due to challenges in (a) characterizing the global long-tailed distribution under privacy constraints and (b) adjusting the local learning strategy to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07587","kind":"arxiv","version":4},"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/2310.07587/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":"2310.07587","created_at":"2026-07-05T07:16:47.378066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07587v4","created_at":"2026-07-05T07:16:47.378066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07587","created_at":"2026-07-05T07:16:47.378066+00:00"},{"alias_kind":"pith_short_12","alias_value":"XP7NTOLSYDMD","created_at":"2026-07-05T07:16:47.378066+00:00"},{"alias_kind":"pith_short_16","alias_value":"XP7NTOLSYDMDHZYD","created_at":"2026-07-05T07:16:47.378066+00:00"},{"alias_kind":"pith_short_8","alias_value":"XP7NTOLS","created_at":"2026-07-05T07:16:47.378066+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/XP7NTOLSYDMDHZYD6ROYGWJICX","json":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX.json","graph_json":"https://pith.science/api/pith-number/XP7NTOLSYDMDHZYD6ROYGWJICX/graph.json","events_json":"https://pith.science/api/pith-number/XP7NTOLSYDMDHZYD6ROYGWJICX/events.json","paper":"https://pith.science/paper/XP7NTOLS"},"agent_actions":{"view_html":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX","download_json":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX.json","view_paper":"https://pith.science/paper/XP7NTOLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07587&json=true","fetch_graph":"https://pith.science/api/pith-number/XP7NTOLSYDMDHZYD6ROYGWJICX/graph.json","fetch_events":"https://pith.science/api/pith-number/XP7NTOLSYDMDHZYD6ROYGWJICX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX/action/storage_attestation","attest_author":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX/action/author_attestation","sign_citation":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX/action/citation_signature","submit_replication":"https://pith.science/pith/XP7NTOLSYDMDHZYD6ROYGWJICX/action/replication_record"}},"created_at":"2026-07-05T07:16:47.378066+00:00","updated_at":"2026-07-05T07:16:47.378066+00:00"}