{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KESWA6O3G5FDM3272K66Q7GRLE","short_pith_number":"pith:KESWA6O3","schema_version":"1.0","canonical_sha256":"51256079db374a366f5fd2bde87cd1591d0b0fa49ee5a0c369fb038e91541b5b","source":{"kind":"arxiv","id":"1911.00972","version":2},"attestation_state":"computed","paper":{"title":"Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tian Li, Virginia Smith, Vyas Sekar, Zaoxing Liu","submitted_at":"2019-11-03T21:19:13Z","abstract_excerpt":"Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we prove that Count Sketch, a simple method for data stream summarization, has inherent differential privacy properties. Using these derived privacy guarantees, we propose a novel sketch-based framework (DiffSketch) for distributed learning, where we compress the transmitted messag"},"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":"1911.00972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T21:19:13Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"74bc528b7c015207685f2004753deead39530207185661db141f75d22cfdcf60","abstract_canon_sha256":"ee3bace0d2691c1be8c7349284201c43fcf3aa325fa2c9e514fc3c097f715608"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:27.924859Z","signature_b64":"6hzZ+23iSxt7b599ueUvIHppg31Uj6BS6P4ZBCkgBDS5idRquEIHrH8avLtN16V/BJosBiIlAgatdrzXGODFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51256079db374a366f5fd2bde87cd1591d0b0fa49ee5a0c369fb038e91541b5b","last_reissued_at":"2026-07-05T00:24:27.924466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:27.924466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tian Li, Virginia Smith, Vyas Sekar, Zaoxing Liu","submitted_at":"2019-11-03T21:19:13Z","abstract_excerpt":"Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we prove that Count Sketch, a simple method for data stream summarization, has inherent differential privacy properties. Using these derived privacy guarantees, we propose a novel sketch-based framework (DiffSketch) for distributed learning, where we compress the transmitted messag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00972","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/1911.00972/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":"1911.00972","created_at":"2026-07-05T00:24:27.924528+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00972v2","created_at":"2026-07-05T00:24:27.924528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00972","created_at":"2026-07-05T00:24:27.924528+00:00"},{"alias_kind":"pith_short_12","alias_value":"KESWA6O3G5FD","created_at":"2026-07-05T00:24:27.924528+00:00"},{"alias_kind":"pith_short_16","alias_value":"KESWA6O3G5FDM327","created_at":"2026-07-05T00:24:27.924528+00:00"},{"alias_kind":"pith_short_8","alias_value":"KESWA6O3","created_at":"2026-07-05T00:24:27.924528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08195","citing_title":"Sketched Gaussian Mechanism for Private Federated Learning","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE","json":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE.json","graph_json":"https://pith.science/api/pith-number/KESWA6O3G5FDM3272K66Q7GRLE/graph.json","events_json":"https://pith.science/api/pith-number/KESWA6O3G5FDM3272K66Q7GRLE/events.json","paper":"https://pith.science/paper/KESWA6O3"},"agent_actions":{"view_html":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE","download_json":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE.json","view_paper":"https://pith.science/paper/KESWA6O3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00972&json=true","fetch_graph":"https://pith.science/api/pith-number/KESWA6O3G5FDM3272K66Q7GRLE/graph.json","fetch_events":"https://pith.science/api/pith-number/KESWA6O3G5FDM3272K66Q7GRLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE/action/storage_attestation","attest_author":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE/action/author_attestation","sign_citation":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE/action/citation_signature","submit_replication":"https://pith.science/pith/KESWA6O3G5FDM3272K66Q7GRLE/action/replication_record"}},"created_at":"2026-07-05T00:24:27.924528+00:00","updated_at":"2026-07-05T00:24:27.924528+00:00"}