{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DWMZ72OTADYZ2BB7MWNY5UMZB6","short_pith_number":"pith:DWMZ72OT","schema_version":"1.0","canonical_sha256":"1d999fe9d300f19d043f659b8ed1990f8a8025e77cb85965e0c877d62c11fe6f","source":{"kind":"arxiv","id":"2410.11368","version":1},"attestation_state":"computed","paper":{"title":"Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Adria Gascon, James Bell-Clark, Marshall Ball, Peter Kairouz, Sewoong Oh, Zhiye Xie","submitted_at":"2024-10-15T07:45:18Z","abstract_excerpt":"Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent noise (DP-SGD). While DP-SGD is well-suited to federated learning with a single untrusted central server using lightweight secure aggregation protocols, secure aggregation is not conducive to implementing modern DP-FTRL techniques without assuming a trusted central server. DP-FTRL based approaches have already seen widespread deployment in industry, albeit wi"},"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":"2410.11368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-15T07:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"e41d0da5c068240c055d498ced9bd2e8e39b025b64dce2619d93ba3d6ee13178","abstract_canon_sha256":"792407c9c7f2eea2406e910e59461864ce6cb7661145027e12daf53f8bc12778"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:52.517668Z","signature_b64":"aBh9RYDH59QVvhuqXOhZCdfSd4GvlNKJqpDeGf4Sm1OZ83zOGQkItVxlMH6rJQa02LM0ynT6Qv9PAhZjCLvPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d999fe9d300f19d043f659b8ed1990f8a8025e77cb85965e0c877d62c11fe6f","last_reissued_at":"2026-07-05T09:20:52.517225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:52.517225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Adria Gascon, James Bell-Clark, Marshall Ball, Peter Kairouz, Sewoong Oh, Zhiye Xie","submitted_at":"2024-10-15T07:45:18Z","abstract_excerpt":"Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent noise (DP-SGD). While DP-SGD is well-suited to federated learning with a single untrusted central server using lightweight secure aggregation protocols, secure aggregation is not conducive to implementing modern DP-FTRL techniques without assuming a trusted central server. DP-FTRL based approaches have already seen widespread deployment in industry, albeit wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11368","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/2410.11368/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":"2410.11368","created_at":"2026-07-05T09:20:52.517298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11368v1","created_at":"2026-07-05T09:20:52.517298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11368","created_at":"2026-07-05T09:20:52.517298+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWMZ72OTADYZ","created_at":"2026-07-05T09:20:52.517298+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWMZ72OTADYZ2BB7","created_at":"2026-07-05T09:20:52.517298+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWMZ72OT","created_at":"2026-07-05T09:20:52.517298+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/DWMZ72OTADYZ2BB7MWNY5UMZB6","json":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6.json","graph_json":"https://pith.science/api/pith-number/DWMZ72OTADYZ2BB7MWNY5UMZB6/graph.json","events_json":"https://pith.science/api/pith-number/DWMZ72OTADYZ2BB7MWNY5UMZB6/events.json","paper":"https://pith.science/paper/DWMZ72OT"},"agent_actions":{"view_html":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6","download_json":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6.json","view_paper":"https://pith.science/paper/DWMZ72OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11368&json=true","fetch_graph":"https://pith.science/api/pith-number/DWMZ72OTADYZ2BB7MWNY5UMZB6/graph.json","fetch_events":"https://pith.science/api/pith-number/DWMZ72OTADYZ2BB7MWNY5UMZB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6/action/storage_attestation","attest_author":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6/action/author_attestation","sign_citation":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6/action/citation_signature","submit_replication":"https://pith.science/pith/DWMZ72OTADYZ2BB7MWNY5UMZB6/action/replication_record"}},"created_at":"2026-07-05T09:20:52.517298+00:00","updated_at":"2026-07-05T09:20:52.517298+00:00"}