{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KZIFO5LVXHXZKIYJPKHUCLDMY4","short_pith_number":"pith:KZIFO5LV","schema_version":"1.0","canonical_sha256":"5650577575b9ef9523097a8f412c6cc71103236def01e8d2055984da8c21e7d4","source":{"kind":"arxiv","id":"2301.10904","version":3},"attestation_state":"computed","paper":{"title":"GPU-based Private Information Retrieval for On-Device Machine Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"David Brooks, G. Edward Suh, Gu-Yeon Wei, Hsien-Hsin S. Lee, Ilias Leontiadis, Jeff Johnson, Kiwan Maeng, Liangzhen Lai, Maximilian Lam, Minsoo Rhu, Udit Gupta, Vijay Janapa Reddi, Wenjie Xiong, Yang Li","submitted_at":"2023-01-26T02:24:01Z","abstract_excerpt":"On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to remote servers. However, a pure on-device solution to private ML inference is impractical for many applications that rely on embedding tables that are too large to be stored on-device. In particular, recommendation models typically use multiple embedding tables each on the order of 1-10 GBs of data, making them impractical to store on-device. To overcome this barrier, we propose the use of private information retrieval (PIR) to efficiently and privately retrieve embedding"},"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":"2301.10904","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-01-26T02:24:01Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"062a91c13f6ceeaef98b09d3a681b669ea01cee3664e223420c4b914f0735be8","abstract_canon_sha256":"07d7e301274eb038fa44c617bf18d003a14a8a1cfb0a6bf2958378914c14094f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:14.455623Z","signature_b64":"NJYXg6bH3zmCkEYHXxSUAIj8502p+4ljRBDxYOe0pm8gK7jUt9uQGwSVyiW2VXUqOtvioeTEudGfLJ6WtJ9HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5650577575b9ef9523097a8f412c6cc71103236def01e8d2055984da8c21e7d4","last_reissued_at":"2026-07-05T06:54:14.455145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:14.455145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPU-based Private Information Retrieval for On-Device Machine Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"David Brooks, G. Edward Suh, Gu-Yeon Wei, Hsien-Hsin S. Lee, Ilias Leontiadis, Jeff Johnson, Kiwan Maeng, Liangzhen Lai, Maximilian Lam, Minsoo Rhu, Udit Gupta, Vijay Janapa Reddi, Wenjie Xiong, Yang Li","submitted_at":"2023-01-26T02:24:01Z","abstract_excerpt":"On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to remote servers. However, a pure on-device solution to private ML inference is impractical for many applications that rely on embedding tables that are too large to be stored on-device. In particular, recommendation models typically use multiple embedding tables each on the order of 1-10 GBs of data, making them impractical to store on-device. To overcome this barrier, we propose the use of private information retrieval (PIR) to efficiently and privately retrieve embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10904","kind":"arxiv","version":3},"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/2301.10904/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":"2301.10904","created_at":"2026-07-05T06:54:14.455196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10904v3","created_at":"2026-07-05T06:54:14.455196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10904","created_at":"2026-07-05T06:54:14.455196+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZIFO5LVXHXZ","created_at":"2026-07-05T06:54:14.455196+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZIFO5LVXHXZKIYJ","created_at":"2026-07-05T06:54:14.455196+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZIFO5LV","created_at":"2026-07-05T06:54:14.455196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03631","citing_title":"QPADL: Post-Quantum Private Spectrum Access with Verified Location and DoS Resilience","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4","json":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4.json","graph_json":"https://pith.science/api/pith-number/KZIFO5LVXHXZKIYJPKHUCLDMY4/graph.json","events_json":"https://pith.science/api/pith-number/KZIFO5LVXHXZKIYJPKHUCLDMY4/events.json","paper":"https://pith.science/paper/KZIFO5LV"},"agent_actions":{"view_html":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4","download_json":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4.json","view_paper":"https://pith.science/paper/KZIFO5LV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10904&json=true","fetch_graph":"https://pith.science/api/pith-number/KZIFO5LVXHXZKIYJPKHUCLDMY4/graph.json","fetch_events":"https://pith.science/api/pith-number/KZIFO5LVXHXZKIYJPKHUCLDMY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4/action/storage_attestation","attest_author":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4/action/author_attestation","sign_citation":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4/action/citation_signature","submit_replication":"https://pith.science/pith/KZIFO5LVXHXZKIYJPKHUCLDMY4/action/replication_record"}},"created_at":"2026-07-05T06:54:14.455196+00:00","updated_at":"2026-07-05T06:54:14.455196+00:00"}