{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A5KMWL7K5SKVJIDEOWQUBVRHSS","short_pith_number":"pith:A5KMWL7K","schema_version":"1.0","canonical_sha256":"0754cb2feaec9554a06475a140d627949e643d3ff04aeea04e3d5e4e5d8a95c2","source":{"kind":"arxiv","id":"1911.02254","version":2},"attestation_state":"computed","paper":{"title":"Secure Federated Submodel Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaoyue Niu, Chengfei Lv, Fan Wu, Guihai Chen, Lifeng Hua, Rongfei Jia, Shaojie Tang, Zhihua Wu","submitted_at":"2019-11-06T08:49:23Z","abstract_excerpt":"Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the \"posi"},"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":"1911.02254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-06T08:49:23Z","cross_cats_sorted":["cs.CR","cs.DC","stat.ML"],"title_canon_sha256":"6980087d3f3f89d4aeb5af1719116d77d44524f559831d05e4d8915a14d21763","abstract_canon_sha256":"b83add5e465254752eb6c53fc092a941260f17b1e2068ab95b28e603754b85a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:12.397957Z","signature_b64":"nn+NOVD4+UNBdw56E67KRwHDSctq2ucf59GcHe3Uj6+Kn9+pS3WGVz8EFmYb+DWPY03UgFNguDm8zZXQCjvxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0754cb2feaec9554a06475a140d627949e643d3ff04aeea04e3d5e4e5d8a95c2","last_reissued_at":"2026-07-05T00:18:12.397452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:12.397452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Secure Federated Submodel Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaoyue Niu, Chengfei Lv, Fan Wu, Guihai Chen, Lifeng Hua, Rongfei Jia, Shaojie Tang, Zhihua Wu","submitted_at":"2019-11-06T08:49:23Z","abstract_excerpt":"Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the \"posi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02254","kind":"arxiv","version":2},"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/1911.02254/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":"1911.02254","created_at":"2026-07-05T00:18:12.397518+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.02254v2","created_at":"2026-07-05T00:18:12.397518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02254","created_at":"2026-07-05T00:18:12.397518+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5KMWL7K5SKV","created_at":"2026-07-05T00:18:12.397518+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5KMWL7K5SKVJIDE","created_at":"2026-07-05T00:18:12.397518+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5KMWL7K","created_at":"2026-07-05T00:18:12.397518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30425","citing_title":"Lossy Compression for Sparse Aggregation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS","json":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS.json","graph_json":"https://pith.science/api/pith-number/A5KMWL7K5SKVJIDEOWQUBVRHSS/graph.json","events_json":"https://pith.science/api/pith-number/A5KMWL7K5SKVJIDEOWQUBVRHSS/events.json","paper":"https://pith.science/paper/A5KMWL7K"},"agent_actions":{"view_html":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS","download_json":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS.json","view_paper":"https://pith.science/paper/A5KMWL7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.02254&json=true","fetch_graph":"https://pith.science/api/pith-number/A5KMWL7K5SKVJIDEOWQUBVRHSS/graph.json","fetch_events":"https://pith.science/api/pith-number/A5KMWL7K5SKVJIDEOWQUBVRHSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS/action/storage_attestation","attest_author":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS/action/author_attestation","sign_citation":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS/action/citation_signature","submit_replication":"https://pith.science/pith/A5KMWL7K5SKVJIDEOWQUBVRHSS/action/replication_record"}},"created_at":"2026-07-05T00:18:12.397518+00:00","updated_at":"2026-07-05T00:18:12.397518+00:00"}