{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YZMKLX3LSTZ3HE7VHXLFO6C2YO","short_pith_number":"pith:YZMKLX3L","schema_version":"1.0","canonical_sha256":"c658a5df6b94f3b393f53dd657785ac393a9dd6f65fb88a3ddd869001d2b213b","source":{"kind":"arxiv","id":"2112.06053","version":2},"attestation_state":"computed","paper":{"title":"FedSoft: Soft Clustered Federated Learning with Proximal Local Updating","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Yichen Ruan","submitted_at":"2021-12-11T19:26:30Z","abstract_excerpt":"Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution. We relax this hard association assumption to soft clustered federated learning, which allows every local dataset to follow a mixture of multiple source distributions. We propose FedSoft, which trains both locally personalized models and high-quality cluster models in this setting. FedSoft limits client workload by using proximal updates to require the completion of only on"},"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":"2112.06053","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-11T19:26:30Z","cross_cats_sorted":[],"title_canon_sha256":"6d19cebfe0eb1cff0d5c7648e9a0852c85a2c72ccd4f925690432894b57a133e","abstract_canon_sha256":"6241b2f5be69905f8ce25ff40b20fba316ca7b1df04688b60a1de023274b11a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:42.945721Z","signature_b64":"flbbXpo6RZ04Hyo6xhXfR7mB6FdHjLgD7yNQJS7LWIQMRsrncvxwZ932JTASEs+/suPQL0ylyKIPrQzMg1gyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c658a5df6b94f3b393f53dd657785ac393a9dd6f65fb88a3ddd869001d2b213b","last_reissued_at":"2026-07-05T04:07:42.945120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:42.945120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSoft: Soft Clustered Federated Learning with Proximal Local Updating","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Yichen Ruan","submitted_at":"2021-12-11T19:26:30Z","abstract_excerpt":"Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution. We relax this hard association assumption to soft clustered federated learning, which allows every local dataset to follow a mixture of multiple source distributions. We propose FedSoft, which trains both locally personalized models and high-quality cluster models in this setting. FedSoft limits client workload by using proximal updates to require the completion of only on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06053","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/2112.06053/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":"2112.06053","created_at":"2026-07-05T04:07:42.945226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06053v2","created_at":"2026-07-05T04:07:42.945226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06053","created_at":"2026-07-05T04:07:42.945226+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZMKLX3LSTZ3","created_at":"2026-07-05T04:07:42.945226+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZMKLX3LSTZ3HE7V","created_at":"2026-07-05T04:07:42.945226+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZMKLX3L","created_at":"2026-07-05T04:07:42.945226+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/YZMKLX3LSTZ3HE7VHXLFO6C2YO","json":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO.json","graph_json":"https://pith.science/api/pith-number/YZMKLX3LSTZ3HE7VHXLFO6C2YO/graph.json","events_json":"https://pith.science/api/pith-number/YZMKLX3LSTZ3HE7VHXLFO6C2YO/events.json","paper":"https://pith.science/paper/YZMKLX3L"},"agent_actions":{"view_html":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO","download_json":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO.json","view_paper":"https://pith.science/paper/YZMKLX3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06053&json=true","fetch_graph":"https://pith.science/api/pith-number/YZMKLX3LSTZ3HE7VHXLFO6C2YO/graph.json","fetch_events":"https://pith.science/api/pith-number/YZMKLX3LSTZ3HE7VHXLFO6C2YO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO/action/storage_attestation","attest_author":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO/action/author_attestation","sign_citation":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO/action/citation_signature","submit_replication":"https://pith.science/pith/YZMKLX3LSTZ3HE7VHXLFO6C2YO/action/replication_record"}},"created_at":"2026-07-05T04:07:42.945226+00:00","updated_at":"2026-07-05T04:07:42.945226+00:00"}