{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQ7YMGSTJGSKC7HH5J5REC6TXB","short_pith_number":"pith:DQ7YMGST","schema_version":"1.0","canonical_sha256":"1c3f861a5349a4a17ce7ea7b120bd3b867ddb1c471a8cdce6734bae7e9188f40","source":{"kind":"arxiv","id":"2412.05186","version":1},"attestation_state":"computed","paper":{"title":"One-shot Federated Learning via Synthetic Distiller-Distillate Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Junyuan Zhang, Songhua Liu, Xinchao Wang","submitted_at":"2024-12-06T17:05:34Z","abstract_excerpt":"One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication. While its superiority lies in communication efficiency and privacy preservation compared to iterative FL, one-shot FL often compromises model performance. Prior research has primarily focused on employing data-free knowledge distillation to optimize data generators and ensemble models for better aggregating local knowledge into the server model. However, these methods typically struggle with data heterogeneity, where inconsistent local dat"},"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":"2412.05186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T17:05:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e58135531ba36a7d26b2a9de2c03ec5eb6b3ec41418c2ced205b8e56f9bfe8d9","abstract_canon_sha256":"a3351c2dc80337aeea51426aa04fc2fc429cd2dcd2c25aac67faa4ce4e165232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:30.086098Z","signature_b64":"PKa2UzX1fkzXvckcs/nGF5msdYeFJsp+OkgUYtWU6kJNbhOKxqvF66qrGEKcZ+r3emnoHZd6aP7KWj9pTsvwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3f861a5349a4a17ce7ea7b120bd3b867ddb1c471a8cdce6734bae7e9188f40","last_reissued_at":"2026-07-05T09:45:30.085707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:30.085707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-shot Federated Learning via Synthetic Distiller-Distillate Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Junyuan Zhang, Songhua Liu, Xinchao Wang","submitted_at":"2024-12-06T17:05:34Z","abstract_excerpt":"One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication. While its superiority lies in communication efficiency and privacy preservation compared to iterative FL, one-shot FL often compromises model performance. Prior research has primarily focused on employing data-free knowledge distillation to optimize data generators and ensemble models for better aggregating local knowledge into the server model. However, these methods typically struggle with data heterogeneity, where inconsistent local dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05186","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/2412.05186/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":"2412.05186","created_at":"2026-07-05T09:45:30.085760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05186v1","created_at":"2026-07-05T09:45:30.085760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05186","created_at":"2026-07-05T09:45:30.085760+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQ7YMGSTJGSK","created_at":"2026-07-05T09:45:30.085760+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQ7YMGSTJGSKC7HH","created_at":"2026-07-05T09:45:30.085760+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQ7YMGST","created_at":"2026-07-05T09:45:30.085760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08368","citing_title":"FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00656","citing_title":"Demystifying the Optimal Fair Classifier in Multi-Class Classification","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB","json":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB.json","graph_json":"https://pith.science/api/pith-number/DQ7YMGSTJGSKC7HH5J5REC6TXB/graph.json","events_json":"https://pith.science/api/pith-number/DQ7YMGSTJGSKC7HH5J5REC6TXB/events.json","paper":"https://pith.science/paper/DQ7YMGST"},"agent_actions":{"view_html":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB","download_json":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB.json","view_paper":"https://pith.science/paper/DQ7YMGST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05186&json=true","fetch_graph":"https://pith.science/api/pith-number/DQ7YMGSTJGSKC7HH5J5REC6TXB/graph.json","fetch_events":"https://pith.science/api/pith-number/DQ7YMGSTJGSKC7HH5J5REC6TXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB/action/storage_attestation","attest_author":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB/action/author_attestation","sign_citation":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB/action/citation_signature","submit_replication":"https://pith.science/pith/DQ7YMGSTJGSKC7HH5J5REC6TXB/action/replication_record"}},"created_at":"2026-07-05T09:45:30.085760+00:00","updated_at":"2026-07-05T09:45:30.085760+00:00"}