{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7OEREQYWGUBWPTCRPJENHYDJLQ","short_pith_number":"pith:7OEREQYW","schema_version":"1.0","canonical_sha256":"fb89124316350367cc517a48d3e0695c3e828da3a61d68d7b43d66aec2c7a289","source":{"kind":"arxiv","id":"2306.11913","version":1},"attestation_state":"computed","paper":{"title":"Randomized Quantization is All You Need for Differential Privacy in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jacob Abernethy, Juba Ziani, Yeojoon Youn, Zihao Hu","submitted_at":"2023-06-20T21:54:13Z","abstract_excerpt":"Federated learning (FL) is a common and practical framework for learning a machine model in a decentralized fashion. A primary motivation behind this decentralized approach is data privacy, ensuring that the learner never sees the data of each local source itself. Federated learning then comes with two majors challenges: one is handling potentially complex model updates between a server and a large number of data sources; the other is that de-centralization may, in fact, be insufficient for privacy, as the local updates themselves can reveal information about the sources' data. To address thes"},"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":"2306.11913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T21:54:13Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"cc8f76968843ce751896953afc2fa0374010e7ae2aeaceb49c359b95d2066571","abstract_canon_sha256":"d96d878526424668818ee33a4d48503361545192cf35bfb8b50427064bd852f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:08.458151Z","signature_b64":"STwDE3s2E9L3yl2LfjxnuWX7699Kq6M6epHud4u0bei0+d7J33B83tSR9og4ce63LqvMLHEBlVqEkGLrKlXHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb89124316350367cc517a48d3e0695c3e828da3a61d68d7b43d66aec2c7a289","last_reissued_at":"2026-07-05T06:23:08.457765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:08.457765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Quantization is All You Need for Differential Privacy in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Jacob Abernethy, Juba Ziani, Yeojoon Youn, Zihao Hu","submitted_at":"2023-06-20T21:54:13Z","abstract_excerpt":"Federated learning (FL) is a common and practical framework for learning a machine model in a decentralized fashion. A primary motivation behind this decentralized approach is data privacy, ensuring that the learner never sees the data of each local source itself. Federated learning then comes with two majors challenges: one is handling potentially complex model updates between a server and a large number of data sources; the other is that de-centralization may, in fact, be insufficient for privacy, as the local updates themselves can reveal information about the sources' data. To address thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11913","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/2306.11913/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":"2306.11913","created_at":"2026-07-05T06:23:08.457814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11913v1","created_at":"2026-07-05T06:23:08.457814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11913","created_at":"2026-07-05T06:23:08.457814+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OEREQYWGUBW","created_at":"2026-07-05T06:23:08.457814+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OEREQYWGUBWPTCR","created_at":"2026-07-05T06:23:08.457814+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OEREQYW","created_at":"2026-07-05T06:23:08.457814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.03472","citing_title":"DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23426","citing_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ","json":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ.json","graph_json":"https://pith.science/api/pith-number/7OEREQYWGUBWPTCRPJENHYDJLQ/graph.json","events_json":"https://pith.science/api/pith-number/7OEREQYWGUBWPTCRPJENHYDJLQ/events.json","paper":"https://pith.science/paper/7OEREQYW"},"agent_actions":{"view_html":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ","download_json":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ.json","view_paper":"https://pith.science/paper/7OEREQYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11913&json=true","fetch_graph":"https://pith.science/api/pith-number/7OEREQYWGUBWPTCRPJENHYDJLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7OEREQYWGUBWPTCRPJENHYDJLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ/action/storage_attestation","attest_author":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ/action/author_attestation","sign_citation":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ/action/citation_signature","submit_replication":"https://pith.science/pith/7OEREQYWGUBWPTCRPJENHYDJLQ/action/replication_record"}},"created_at":"2026-07-05T06:23:08.457814+00:00","updated_at":"2026-07-05T06:23:08.457814+00:00"}