{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3TQQY67MCJICJ7LXX7AIJU4VP","short_pith_number":"pith:B3TQQY67","schema_version":"1.0","canonical_sha256":"0ee70863df60928127ebbdfe04269cabe44b06a7e501602665018cdd31f70fd3","source":{"kind":"arxiv","id":"2412.04785","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Random Feature Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Alexander Xue, Chunyang Liao, Deanna Needell, Hayden Schaeffer","submitted_at":"2024-12-06T05:31:08Z","abstract_excerpt":"Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data analysis with privacy guarantees. In this paper, we produce a differentially private random feature model. Random features, which were proposed to approximate large-scale kernel machines, have been used to study privacy-preserving kernel machines as well. We consider the over-parametrized regime (more features than samples) where the non-private random feature "},"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":"2412.04785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T05:31:08Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"210512ab3f8bcae2f168b42f8505d11faf88cdf1257b626f0b0c88641b44e773","abstract_canon_sha256":"ae2700b5f3005dc189a79a4c096e18d7adb2265da71a532863e84c19f165beb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:56.835044Z","signature_b64":"SVBBt0pL8d5bxqPDRPcu42vwdwO2BuVDCEZxt7sSF2FImc20964hj1nglRTLirh12ZcSSAa74Nrp7vC4lTl1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee70863df60928127ebbdfe04269cabe44b06a7e501602665018cdd31f70fd3","last_reissued_at":"2026-07-05T12:07:56.834516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:56.834516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Random Feature Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Alexander Xue, Chunyang Liao, Deanna Needell, Hayden Schaeffer","submitted_at":"2024-12-06T05:31:08Z","abstract_excerpt":"Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data analysis with privacy guarantees. In this paper, we produce a differentially private random feature model. Random features, which were proposed to approximate large-scale kernel machines, have been used to study privacy-preserving kernel machines as well. We consider the over-parametrized regime (more features than samples) where the non-private random feature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04785","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/2412.04785/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":"2412.04785","created_at":"2026-07-05T12:07:56.834580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04785v2","created_at":"2026-07-05T12:07:56.834580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04785","created_at":"2026-07-05T12:07:56.834580+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3TQQY67MCJI","created_at":"2026-07-05T12:07:56.834580+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3TQQY67MCJICJ7L","created_at":"2026-07-05T12:07:56.834580+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3TQQY67","created_at":"2026-07-05T12:07:56.834580+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/B3TQQY67MCJICJ7LXX7AIJU4VP","json":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP.json","graph_json":"https://pith.science/api/pith-number/B3TQQY67MCJICJ7LXX7AIJU4VP/graph.json","events_json":"https://pith.science/api/pith-number/B3TQQY67MCJICJ7LXX7AIJU4VP/events.json","paper":"https://pith.science/paper/B3TQQY67"},"agent_actions":{"view_html":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP","download_json":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP.json","view_paper":"https://pith.science/paper/B3TQQY67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04785&json=true","fetch_graph":"https://pith.science/api/pith-number/B3TQQY67MCJICJ7LXX7AIJU4VP/graph.json","fetch_events":"https://pith.science/api/pith-number/B3TQQY67MCJICJ7LXX7AIJU4VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP/action/storage_attestation","attest_author":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP/action/author_attestation","sign_citation":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP/action/citation_signature","submit_replication":"https://pith.science/pith/B3TQQY67MCJICJ7LXX7AIJU4VP/action/replication_record"}},"created_at":"2026-07-05T12:07:56.834580+00:00","updated_at":"2026-07-05T12:07:56.834580+00:00"}