{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FLPFQNT5QN4OLO744UBKUWM5X4","short_pith_number":"pith:FLPFQNT5","schema_version":"1.0","canonical_sha256":"2ade58367d8378e5bbfce502aa599dbf34c4580bfb1e72e0fdc58d2410f64726","source":{"kind":"arxiv","id":"1807.04369","version":2},"attestation_state":"computed","paper":{"title":"Differentially-Private \"Draw and Discard\" Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Aleksandra Korolova, Dachuan Huang, Frederick Liu, Moti Yung, Ruogu Zeng, Subhash Sankuratripati, Vasyl Pihur","submitted_at":"2018-07-11T22:28:50Z","abstract_excerpt":"In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all systems constraints using asynchronous client-server communication and provides attractive model learning properties. We call it \"Draw and Discard\" because it relies on random sampling of models for load distribution (scalability), which also provides additional server-side privacy protections and improved model quality through averaging. We present the mechanics "},"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":"1807.04369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-07-11T22:28:50Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"8f55f54fda8bd349c95cd5fde151ce9337446760782f924eacba6daff1823436","abstract_canon_sha256":"c1328f07694c5f4a61d775167b8d23f952b06541ab37176e6c5e7e30688332a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:36.703762Z","signature_b64":"pB0oCuCNm0mbVfpJfpN+2SmtLxZRuwNHjUXb78/0/8BS01YP5exrjLstUjOB2NN9rafU80bqftGStVN807+7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ade58367d8378e5bbfce502aa599dbf34c4580bfb1e72e0fdc58d2410f64726","last_reissued_at":"2026-05-18T00:03:36.703143Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:36.703143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially-Private \"Draw and Discard\" Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Aleksandra Korolova, Dachuan Huang, Frederick Liu, Moti Yung, Ruogu Zeng, Subhash Sankuratripati, Vasyl Pihur","submitted_at":"2018-07-11T22:28:50Z","abstract_excerpt":"In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all systems constraints using asynchronous client-server communication and provides attractive model learning properties. We call it \"Draw and Discard\" because it relies on random sampling of models for load distribution (scalability), which also provides additional server-side privacy protections and improved model quality through averaging. We present the mechanics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04369","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":""},"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":"1807.04369","created_at":"2026-05-18T00:03:36.703234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04369v2","created_at":"2026-05-18T00:03:36.703234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04369","created_at":"2026-05-18T00:03:36.703234+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLPFQNT5QN4O","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLPFQNT5QN4OLO74","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLPFQNT5","created_at":"2026-05-18T12:32:22.470017+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/FLPFQNT5QN4OLO744UBKUWM5X4","json":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4.json","graph_json":"https://pith.science/api/pith-number/FLPFQNT5QN4OLO744UBKUWM5X4/graph.json","events_json":"https://pith.science/api/pith-number/FLPFQNT5QN4OLO744UBKUWM5X4/events.json","paper":"https://pith.science/paper/FLPFQNT5"},"agent_actions":{"view_html":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4","download_json":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4.json","view_paper":"https://pith.science/paper/FLPFQNT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04369&json=true","fetch_graph":"https://pith.science/api/pith-number/FLPFQNT5QN4OLO744UBKUWM5X4/graph.json","fetch_events":"https://pith.science/api/pith-number/FLPFQNT5QN4OLO744UBKUWM5X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4/action/storage_attestation","attest_author":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4/action/author_attestation","sign_citation":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4/action/citation_signature","submit_replication":"https://pith.science/pith/FLPFQNT5QN4OLO744UBKUWM5X4/action/replication_record"}},"created_at":"2026-05-18T00:03:36.703234+00:00","updated_at":"2026-05-18T00:03:36.703234+00:00"}