{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AYF4IHTVNFQGEMFQ4L5OYXH4DB","short_pith_number":"pith:AYF4IHTV","schema_version":"1.0","canonical_sha256":"060bc41e7569606230b0e2faec5cfc187f33288b1c981dc15af6b523c7bd01b2","source":{"kind":"arxiv","id":"2307.10507","version":1},"attestation_state":"computed","paper":{"title":"FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Meirui Jiang, Minghui Chen, Qi Dou, Xiaoxiao Li, Zehua Wang","submitted_at":"2023-07-20T00:07:29Z","abstract_excerpt":"Cross-silo federated learning (FL) enables the development of machine learning models on datasets distributed across data centers such as hospitals and clinical research laboratories. However, recent research has found that current FL algorithms face a trade-off between local and global performance when confronted with distribution shifts. Specifically, personalized FL methods have a tendency to overfit to local data, leading to a sharp valley in the local model and inhibiting its ability to generalize to out-of-distribution data. In this paper, we propose a novel federated model soup method ("},"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":"2307.10507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T00:07:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"839d1ecd3b09f30019adab364e92840a72390a2f4a0e5ef1965bafdc3e04d55a","abstract_canon_sha256":"89bd04efbef7dfbc4efec3a0267c24c8bbd1fdcb9fbb2f48df935378764db2b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:59.481751Z","signature_b64":"k5ShXsaqlBx6GySEAhZ2RtbIIgltaynCasMkQ48QF1tK/9tO3L7xHJFotiSrm+72deJXbcUJzkM+ViBCtmAeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"060bc41e7569606230b0e2faec5cfc187f33288b1c981dc15af6b523c7bd01b2","last_reissued_at":"2026-07-05T06:32:59.481264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:59.481264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Meirui Jiang, Minghui Chen, Qi Dou, Xiaoxiao Li, Zehua Wang","submitted_at":"2023-07-20T00:07:29Z","abstract_excerpt":"Cross-silo federated learning (FL) enables the development of machine learning models on datasets distributed across data centers such as hospitals and clinical research laboratories. However, recent research has found that current FL algorithms face a trade-off between local and global performance when confronted with distribution shifts. Specifically, personalized FL methods have a tendency to overfit to local data, leading to a sharp valley in the local model and inhibiting its ability to generalize to out-of-distribution data. In this paper, we propose a novel federated model soup method ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10507","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/2307.10507/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":"2307.10507","created_at":"2026-07-05T06:32:59.481321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10507v1","created_at":"2026-07-05T06:32:59.481321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10507","created_at":"2026-07-05T06:32:59.481321+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYF4IHTVNFQG","created_at":"2026-07-05T06:32:59.481321+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYF4IHTVNFQGEMFQ","created_at":"2026-07-05T06:32:59.481321+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYF4IHTV","created_at":"2026-07-05T06:32:59.481321+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/AYF4IHTVNFQGEMFQ4L5OYXH4DB","json":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB.json","graph_json":"https://pith.science/api/pith-number/AYF4IHTVNFQGEMFQ4L5OYXH4DB/graph.json","events_json":"https://pith.science/api/pith-number/AYF4IHTVNFQGEMFQ4L5OYXH4DB/events.json","paper":"https://pith.science/paper/AYF4IHTV"},"agent_actions":{"view_html":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB","download_json":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB.json","view_paper":"https://pith.science/paper/AYF4IHTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10507&json=true","fetch_graph":"https://pith.science/api/pith-number/AYF4IHTVNFQGEMFQ4L5OYXH4DB/graph.json","fetch_events":"https://pith.science/api/pith-number/AYF4IHTVNFQGEMFQ4L5OYXH4DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB/action/storage_attestation","attest_author":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB/action/author_attestation","sign_citation":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB/action/citation_signature","submit_replication":"https://pith.science/pith/AYF4IHTVNFQGEMFQ4L5OYXH4DB/action/replication_record"}},"created_at":"2026-07-05T06:32:59.481321+00:00","updated_at":"2026-07-05T06:32:59.481321+00:00"}