{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FGRZYU6HYDML26JRJIABNGGVEW","short_pith_number":"pith:FGRZYU6H","schema_version":"1.0","canonical_sha256":"29a39c53c7c0d8bd79314a001698d525be2b0d42b86d88057bd24567ef30fa61","source":{"kind":"arxiv","id":"2404.08564","version":1},"attestation_state":"computed","paper":{"title":"Federated Distillation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baosheng Yu, Jianping Gou, Lan Du, Lin Li, Zhang Yiand Dacheng Tao","submitted_at":"2024-04-02T03:42:18Z","abstract_excerpt":"Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients. Despite its promise, FL encounters challenges such as high communication costs for large-scale models and the necessity for uniform model architectures across all clients and the server. These challenges severely restrict the practical applications of FL. To address these limitations, the integration of knowledge distillation (KD) into FL has been proposed, forming what is known as Federated Distillation (FD). FD enables more flexible knowledge transfer between clients "},"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":"2404.08564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T03:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"e4af13d925cbc6816b41d1953dbb90d065d5f59d5d2bbec625536e06d1a37638","abstract_canon_sha256":"809b794968193adc3979d792f883afba8c09f11bc82c9b07d60ac60eb1e9ed8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:23.651911Z","signature_b64":"cI/zmoHXFJzxk6x+BMHaT3g56ncIt1PAFBzzJiLC3HAckVIJg9E1EfbKDqx5ivT3GcLHIcxLIFtjlyOZG9WWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a39c53c7c0d8bd79314a001698d525be2b0d42b86d88057bd24567ef30fa61","last_reissued_at":"2026-07-05T08:07:23.651499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:23.651499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Distillation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baosheng Yu, Jianping Gou, Lan Du, Lin Li, Zhang Yiand Dacheng Tao","submitted_at":"2024-04-02T03:42:18Z","abstract_excerpt":"Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients. Despite its promise, FL encounters challenges such as high communication costs for large-scale models and the necessity for uniform model architectures across all clients and the server. These challenges severely restrict the practical applications of FL. To address these limitations, the integration of knowledge distillation (KD) into FL has been proposed, forming what is known as Federated Distillation (FD). FD enables more flexible knowledge transfer between clients "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08564","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/2404.08564/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":"2404.08564","created_at":"2026-07-05T08:07:23.651555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08564v1","created_at":"2026-07-05T08:07:23.651555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08564","created_at":"2026-07-05T08:07:23.651555+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGRZYU6HYDML","created_at":"2026-07-05T08:07:23.651555+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGRZYU6HYDML26JR","created_at":"2026-07-05T08:07:23.651555+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGRZYU6H","created_at":"2026-07-05T08:07:23.651555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.04066","citing_title":"Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.14769","citing_title":"Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17778","citing_title":"Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03226","citing_title":"Enhancing Robustness of Federated Learning via Server Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW","json":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW.json","graph_json":"https://pith.science/api/pith-number/FGRZYU6HYDML26JRJIABNGGVEW/graph.json","events_json":"https://pith.science/api/pith-number/FGRZYU6HYDML26JRJIABNGGVEW/events.json","paper":"https://pith.science/paper/FGRZYU6H"},"agent_actions":{"view_html":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW","download_json":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW.json","view_paper":"https://pith.science/paper/FGRZYU6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08564&json=true","fetch_graph":"https://pith.science/api/pith-number/FGRZYU6HYDML26JRJIABNGGVEW/graph.json","fetch_events":"https://pith.science/api/pith-number/FGRZYU6HYDML26JRJIABNGGVEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW/action/storage_attestation","attest_author":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW/action/author_attestation","sign_citation":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW/action/citation_signature","submit_replication":"https://pith.science/pith/FGRZYU6HYDML26JRJIABNGGVEW/action/replication_record"}},"created_at":"2026-07-05T08:07:23.651555+00:00","updated_at":"2026-07-05T08:07:23.651555+00:00"}