{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZZQQB3CEOKIEB7KIGOGTD2S37F","short_pith_number":"pith:ZZQQB3CE","schema_version":"1.0","canonical_sha256":"ce6100ec44729040fd48338d31ea5bf97b20504e7edf7ec35561643b5e1a345f","source":{"kind":"arxiv","id":"2402.06606","version":1},"attestation_state":"computed","paper":{"title":"RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ce Feng, Parv Venkitasubramaniam","submitted_at":"2024-02-09T18:34:08Z","abstract_excerpt":"The rise of IoT devices has prompted the demand for deploying machine learning at-the-edge with real-time, efficient, and secure data processing. In this context, implementing machine learning (ML) models with real-valued weight parameters can prove to be impractical particularly for large models, and there is a need to train models with quantized discrete weights. At the same time, these low-dimensional models also need to preserve privacy of the underlying dataset. In this work, we present RQP-SGD, a new approach for privacy-preserving quantization to train machine learning models for low-me"},"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":"2402.06606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T18:34:08Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"0668123ae62407193fa6aa804acab9b4e3b8d0429c3a5660f4d8ffa186eaa9bd","abstract_canon_sha256":"2ae136668ab46d753863368f3600cc4986f84847a75ec3fa1662dd527b401b04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:27.722243Z","signature_b64":"FX6Xaw2LR77HaS8i3AD8vkaVBKRf7xTG0AIn/txDITgNsEmiJRvQH/ARYr/Nz4AtCN6+Wl6bXV8CUQwIZ8zSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce6100ec44729040fd48338d31ea5bf97b20504e7edf7ec35561643b5e1a345f","last_reissued_at":"2026-07-05T07:43:27.721630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:27.721630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ce Feng, Parv Venkitasubramaniam","submitted_at":"2024-02-09T18:34:08Z","abstract_excerpt":"The rise of IoT devices has prompted the demand for deploying machine learning at-the-edge with real-time, efficient, and secure data processing. In this context, implementing machine learning (ML) models with real-valued weight parameters can prove to be impractical particularly for large models, and there is a need to train models with quantized discrete weights. At the same time, these low-dimensional models also need to preserve privacy of the underlying dataset. In this work, we present RQP-SGD, a new approach for privacy-preserving quantization to train machine learning models for low-me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06606","kind":"arxiv","version":1},"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/2402.06606/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":"2402.06606","created_at":"2026-07-05T07:43:27.721739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06606v1","created_at":"2026-07-05T07:43:27.721739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06606","created_at":"2026-07-05T07:43:27.721739+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZQQB3CEOKIE","created_at":"2026-07-05T07:43:27.721739+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZQQB3CEOKIEB7KI","created_at":"2026-07-05T07:43:27.721739+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZQQB3CE","created_at":"2026-07-05T07:43:27.721739+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/ZZQQB3CEOKIEB7KIGOGTD2S37F","json":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F.json","graph_json":"https://pith.science/api/pith-number/ZZQQB3CEOKIEB7KIGOGTD2S37F/graph.json","events_json":"https://pith.science/api/pith-number/ZZQQB3CEOKIEB7KIGOGTD2S37F/events.json","paper":"https://pith.science/paper/ZZQQB3CE"},"agent_actions":{"view_html":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F","download_json":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F.json","view_paper":"https://pith.science/paper/ZZQQB3CE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06606&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZQQB3CEOKIEB7KIGOGTD2S37F/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZQQB3CEOKIEB7KIGOGTD2S37F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F/action/storage_attestation","attest_author":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F/action/author_attestation","sign_citation":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F/action/citation_signature","submit_replication":"https://pith.science/pith/ZZQQB3CEOKIEB7KIGOGTD2S37F/action/replication_record"}},"created_at":"2026-07-05T07:43:27.721739+00:00","updated_at":"2026-07-05T07:43:27.721739+00:00"}