{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6HWA4AULE5626EGNUE5U2R2JER","short_pith_number":"pith:6HWA4AUL","schema_version":"1.0","canonical_sha256":"f1ec0e028b277daf10cda13b4d4749245319110ef0cf8f77ac84b6fa6334e0e5","source":{"kind":"arxiv","id":"2211.05006","version":2},"attestation_state":"computed","paper":{"title":"Almost Tight Error Bounds on Differentially Private Continual Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS"],"primary_cat":"cs.LG","authors_text":"Jalaj Upadhyay, Monika Henzinger, Sarvagya Upadhyay","submitted_at":"2022-11-09T16:35:42Z","abstract_excerpt":"The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled \"Federated Learning with Formal Differential Privacy Guarantees\"). In this case, a concrete bound on the error is very relevant to reduce the privacy parameter. The standard mechanism for continual counting is the binary mechanism. We present a novel mechanism and show that its mean squared error is both asymptotically optimal and a factor 10 smaller than the error of the binary mechanism. We also show that the constants in ou"},"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":"2211.05006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T16:35:42Z","cross_cats_sorted":["cs.CR","cs.DS"],"title_canon_sha256":"2edaadd66990ffd00bb8b5b9b019b64f7220afec8b61c19ba09fd31d60b09ebf","abstract_canon_sha256":"ab18ec0d3221a67f8aa6401a312747c96a5fd0bd80900555bdede2657950a595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:50.446988Z","signature_b64":"ShumVY5lGdhnqXzk5CB8kys8EpzvcCDUG36slh2CHWyuWWTLCp2/Y/X+SJEo3d3uQQ7kyiay/Pk/ChlNdlHWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ec0e028b277daf10cda13b4d4749245319110ef0cf8f77ac84b6fa6334e0e5","last_reissued_at":"2026-07-05T07:40:50.446498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:50.446498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Almost Tight Error Bounds on Differentially Private Continual Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS"],"primary_cat":"cs.LG","authors_text":"Jalaj Upadhyay, Monika Henzinger, Sarvagya Upadhyay","submitted_at":"2022-11-09T16:35:42Z","abstract_excerpt":"The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled \"Federated Learning with Formal Differential Privacy Guarantees\"). In this case, a concrete bound on the error is very relevant to reduce the privacy parameter. The standard mechanism for continual counting is the binary mechanism. We present a novel mechanism and show that its mean squared error is both asymptotically optimal and a factor 10 smaller than the error of the binary mechanism. We also show that the constants in ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05006","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/2211.05006/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":"2211.05006","created_at":"2026-07-05T07:40:50.446577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05006v2","created_at":"2026-07-05T07:40:50.446577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05006","created_at":"2026-07-05T07:40:50.446577+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HWA4AULE562","created_at":"2026-07-05T07:40:50.446577+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HWA4AULE5626EGN","created_at":"2026-07-05T07:40:50.446577+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HWA4AUL","created_at":"2026-07-05T07:40:50.446577+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/6HWA4AULE5626EGNUE5U2R2JER","json":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER.json","graph_json":"https://pith.science/api/pith-number/6HWA4AULE5626EGNUE5U2R2JER/graph.json","events_json":"https://pith.science/api/pith-number/6HWA4AULE5626EGNUE5U2R2JER/events.json","paper":"https://pith.science/paper/6HWA4AUL"},"agent_actions":{"view_html":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER","download_json":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER.json","view_paper":"https://pith.science/paper/6HWA4AUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05006&json=true","fetch_graph":"https://pith.science/api/pith-number/6HWA4AULE5626EGNUE5U2R2JER/graph.json","fetch_events":"https://pith.science/api/pith-number/6HWA4AULE5626EGNUE5U2R2JER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER/action/storage_attestation","attest_author":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER/action/author_attestation","sign_citation":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER/action/citation_signature","submit_replication":"https://pith.science/pith/6HWA4AULE5626EGNUE5U2R2JER/action/replication_record"}},"created_at":"2026-07-05T07:40:50.446577+00:00","updated_at":"2026-07-05T07:40:50.446577+00:00"}