{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KXELCQWRQOZ2M5NTOUEGAI5R5Y","short_pith_number":"pith:KXELCQWR","schema_version":"1.0","canonical_sha256":"55c8b142d183b3a675b375086023b1ee393a78926a9f1844e6f3f7e727291a48","source":{"kind":"arxiv","id":"2607.07565","version":1},"attestation_state":"computed","paper":{"title":"Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Karsten Mueller, Maximilian Andreas Hoefler, Wojciech Samek","submitted_at":"2026-07-08T15:56:58Z","abstract_excerpt":"One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge. Recent work has addressed this challenge by aggregating client knowledge on the server through the construction of transferable synthetic datasets or distillates. However, most of these methods lack formal privacy guarantees, leaving a gap in jointly achieving low communication, robustness to heterogeneity, and rigorous privacy. We propose FedKT-CS"},"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":"2607.07565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T15:56:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bb99a3b9169e80d3cf46aad7ded642ce72697a93cf02a1ec6b8a7f59c81c80a","abstract_canon_sha256":"cd263179bdd4b023c477c31ed9b881890f3284031fbe3529625c616918a1f00d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:29.664782Z","signature_b64":"0/B0pTVtg7S8aH8z0aX/hFVeISUdgMOLToi9WvQwcDvnbzwRdzET9h36ILSIWqg00cEza1pi9Xs68xxe9hl1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c8b142d183b3a675b375086023b1ee393a78926a9f1844e6f3f7e727291a48","last_reissued_at":"2026-07-09T01:20:29.664329Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:29.664329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Karsten Mueller, Maximilian Andreas Hoefler, Wojciech Samek","submitted_at":"2026-07-08T15:56:58Z","abstract_excerpt":"One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge. Recent work has addressed this challenge by aggregating client knowledge on the server through the construction of transferable synthetic datasets or distillates. However, most of these methods lack formal privacy guarantees, leaving a gap in jointly achieving low communication, robustness to heterogeneity, and rigorous privacy. We propose FedKT-CS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07565","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/2607.07565/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":"2607.07565","created_at":"2026-07-09T01:20:29.664401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07565v1","created_at":"2026-07-09T01:20:29.664401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07565","created_at":"2026-07-09T01:20:29.664401+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXELCQWRQOZ2","created_at":"2026-07-09T01:20:29.664401+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXELCQWRQOZ2M5NT","created_at":"2026-07-09T01:20:29.664401+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXELCQWR","created_at":"2026-07-09T01:20:29.664401+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/KXELCQWRQOZ2M5NTOUEGAI5R5Y","json":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y.json","graph_json":"https://pith.science/api/pith-number/KXELCQWRQOZ2M5NTOUEGAI5R5Y/graph.json","events_json":"https://pith.science/api/pith-number/KXELCQWRQOZ2M5NTOUEGAI5R5Y/events.json","paper":"https://pith.science/paper/KXELCQWR"},"agent_actions":{"view_html":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y","download_json":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y.json","view_paper":"https://pith.science/paper/KXELCQWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07565&json=true","fetch_graph":"https://pith.science/api/pith-number/KXELCQWRQOZ2M5NTOUEGAI5R5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/KXELCQWRQOZ2M5NTOUEGAI5R5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y/action/storage_attestation","attest_author":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y/action/author_attestation","sign_citation":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y/action/citation_signature","submit_replication":"https://pith.science/pith/KXELCQWRQOZ2M5NTOUEGAI5R5Y/action/replication_record"}},"created_at":"2026-07-09T01:20:29.664401+00:00","updated_at":"2026-07-09T01:20:29.664401+00:00"}