{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3TPTJS7WDFTJJILFBEIYMSTOQ6","short_pith_number":"pith:3TPTJS7W","schema_version":"1.0","canonical_sha256":"dcdf34cbf6196694a1650911864a6e87b7dfa1f87c6d57e6748b0a9a597fdcb0","source":{"kind":"arxiv","id":"2012.00632","version":1},"attestation_state":"computed","paper":{"title":"Communication-Efficient Federated Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arturo Marban, Felix Sattler, Roman Rischke, Wojciech Samek","submitted_at":"2020-12-01T16:57:25Z","abstract_excerpt":"Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally different communication properties, emerged. FD methods leverage ensemble distillation techniques and exchange model outputs, presented as soft labels on an unlabeled public data set, between the central server and the participating clients. While for conventional Federated Learning algorithms, like Federated Averaging (FA), communication scales with the size of th"},"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":"2012.00632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-01T16:57:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3e2c3e7f725d440ac0984a3e689760f8d8ce960dc5383171b4c6d53fb6808b74","abstract_canon_sha256":"81647ecb7f4caf2899bc1573a5b17f1de68ca9a42632fd6c67a5efc82fadeda8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:18.418972Z","signature_b64":"ctGv+ll7WX9kBSlYAemCy90MEQCHvr3C2JFpGI4rBe1fKU/ALbpGSE1o1iJKiWCG17tx6OsPBIIK66FTfQYJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdf34cbf6196694a1650911864a6e87b7dfa1f87c6d57e6748b0a9a597fdcb0","last_reissued_at":"2026-07-05T01:56:18.418541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:18.418541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Federated Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arturo Marban, Felix Sattler, Roman Rischke, Wojciech Samek","submitted_at":"2020-12-01T16:57:25Z","abstract_excerpt":"Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally different communication properties, emerged. FD methods leverage ensemble distillation techniques and exchange model outputs, presented as soft labels on an unlabeled public data set, between the central server and the participating clients. While for conventional Federated Learning algorithms, like Federated Averaging (FA), communication scales with the size of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00632","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/2012.00632/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":"2012.00632","created_at":"2026-07-05T01:56:18.418596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00632v1","created_at":"2026-07-05T01:56:18.418596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00632","created_at":"2026-07-05T01:56:18.418596+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TPTJS7WDFTJ","created_at":"2026-07-05T01:56:18.418596+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TPTJS7WDFTJJILF","created_at":"2026-07-05T01:56:18.418596+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TPTJS7W","created_at":"2026-07-05T01:56:18.418596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":125,"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":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6","json":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6.json","graph_json":"https://pith.science/api/pith-number/3TPTJS7WDFTJJILFBEIYMSTOQ6/graph.json","events_json":"https://pith.science/api/pith-number/3TPTJS7WDFTJJILFBEIYMSTOQ6/events.json","paper":"https://pith.science/paper/3TPTJS7W"},"agent_actions":{"view_html":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6","download_json":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6.json","view_paper":"https://pith.science/paper/3TPTJS7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00632&json=true","fetch_graph":"https://pith.science/api/pith-number/3TPTJS7WDFTJJILFBEIYMSTOQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/3TPTJS7WDFTJJILFBEIYMSTOQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6/action/storage_attestation","attest_author":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6/action/author_attestation","sign_citation":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6/action/citation_signature","submit_replication":"https://pith.science/pith/3TPTJS7WDFTJJILFBEIYMSTOQ6/action/replication_record"}},"created_at":"2026-07-05T01:56:18.418596+00:00","updated_at":"2026-07-05T01:56:18.418596+00:00"}