{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FBELENUSQEYN5NER4U2I3BO2RR","short_pith_number":"pith:FBELENUS","schema_version":"1.0","canonical_sha256":"2848b236928130deb491e5348d85da8c498e32c5bfe1f5fe94ceaa4219498595","source":{"kind":"arxiv","id":"2506.20285","version":1},"attestation_state":"computed","paper":{"title":"Distilling A Universal Expert from Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Yang, Chunxu Zhang, Guodong Long, Riting Xia, Zeqi Leng","submitted_at":"2025-06-25T09:44:39Z","abstract_excerpt":"Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed"},"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":"2506.20285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:44:39Z","cross_cats_sorted":[],"title_canon_sha256":"cf40f9328cb09a434ddc2768aba3e565b65b9632b23368a73a4efcd927547ce1","abstract_canon_sha256":"62ae8dcb08398a2bad0b514625b70e8a1f28c6800d7a0eaa1b4ac1447b89f113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:03.215274Z","signature_b64":"pNyvoCupxvI4gz5Ie0rrXt+BCBnBgLJs182cC69dzNdAcBHZqpXuvy+mYNIh6CUmjtyijb6fi0WtHzMLa6MOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2848b236928130deb491e5348d85da8c498e32c5bfe1f5fe94ceaa4219498595","last_reissued_at":"2026-07-05T11:27:03.214805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:03.214805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling A Universal Expert from Clustered Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Yang, Chunxu Zhang, Guodong Long, Riting Xia, Zeqi Leng","submitted_at":"2025-06-25T09:44:39Z","abstract_excerpt":"Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20285","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/2506.20285/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":"2506.20285","created_at":"2026-07-05T11:27:03.214864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20285v1","created_at":"2026-07-05T11:27:03.214864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20285","created_at":"2026-07-05T11:27:03.214864+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBELENUSQEYN","created_at":"2026-07-05T11:27:03.214864+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBELENUSQEYN5NER","created_at":"2026-07-05T11:27:03.214864+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBELENUS","created_at":"2026-07-05T11:27:03.214864+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/FBELENUSQEYN5NER4U2I3BO2RR","json":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR.json","graph_json":"https://pith.science/api/pith-number/FBELENUSQEYN5NER4U2I3BO2RR/graph.json","events_json":"https://pith.science/api/pith-number/FBELENUSQEYN5NER4U2I3BO2RR/events.json","paper":"https://pith.science/paper/FBELENUS"},"agent_actions":{"view_html":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR","download_json":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR.json","view_paper":"https://pith.science/paper/FBELENUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20285&json=true","fetch_graph":"https://pith.science/api/pith-number/FBELENUSQEYN5NER4U2I3BO2RR/graph.json","fetch_events":"https://pith.science/api/pith-number/FBELENUSQEYN5NER4U2I3BO2RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR/action/storage_attestation","attest_author":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR/action/author_attestation","sign_citation":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR/action/citation_signature","submit_replication":"https://pith.science/pith/FBELENUSQEYN5NER4U2I3BO2RR/action/replication_record"}},"created_at":"2026-07-05T11:27:03.214864+00:00","updated_at":"2026-07-05T11:27:03.214864+00:00"}