{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2UQ7BDOK2HVLZYMABHNT5ONV5A","short_pith_number":"pith:2UQ7BDOK","schema_version":"1.0","canonical_sha256":"d521f08dcad1eabce18009db3eb9b5e8070ddcd3dca664bbde67cfa9d8b3af41","source":{"kind":"arxiv","id":"1902.08874","version":4},"attestation_state":"computed","paper":{"title":"Evaluating Differentially Private Machine Learning in Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bargav Jayaraman, David Evans","submitted_at":"2019-02-24T01:48:53Z","abstract_excerpt":"Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of $\\epsilon$ in order to get acceptable utility of the model, with little understanding of the impact of such choices on meaningful privacy. Moreover, in scenarios where iterative learning procedures are used, differential privacy variants that offer tighter analyses are used which appear to reduce the needed privac"},"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":"1902.08874","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-24T01:48:53Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"76251385e3958666078517659a63454d0794719c7547dcad16426f545d1ecb53","abstract_canon_sha256":"14e1f9690a5d76abdd91df06d66fcb8812bac43384a010fe12bfda3c48b9e78d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:55:10.542397Z","signature_b64":"pKssVSO6iSmKj9g+sizH1pXw2Y7tfQvR1b70ERElLZl/KvtnWV7c4JHnfxr4JDj18T8sB87TLUYpHz8i6XNeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d521f08dcad1eabce18009db3eb9b5e8070ddcd3dca664bbde67cfa9d8b3af41","last_reissued_at":"2026-07-04T23:55:10.542016Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:55:10.542016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Differentially Private Machine Learning in Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bargav Jayaraman, David Evans","submitted_at":"2019-02-24T01:48:53Z","abstract_excerpt":"Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of $\\epsilon$ in order to get acceptable utility of the model, with little understanding of the impact of such choices on meaningful privacy. Moreover, in scenarios where iterative learning procedures are used, differential privacy variants that offer tighter analyses are used which appear to reduce the needed privac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08874","kind":"arxiv","version":4},"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/1902.08874/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":"1902.08874","created_at":"2026-07-04T23:55:10.542067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08874v4","created_at":"2026-07-04T23:55:10.542067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08874","created_at":"2026-07-04T23:55:10.542067+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UQ7BDOK2HVL","created_at":"2026-07-04T23:55:10.542067+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UQ7BDOK2HVLZYMA","created_at":"2026-07-04T23:55:10.542067+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UQ7BDOK","created_at":"2026-07-04T23:55:10.542067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14205","citing_title":"Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A","json":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A.json","graph_json":"https://pith.science/api/pith-number/2UQ7BDOK2HVLZYMABHNT5ONV5A/graph.json","events_json":"https://pith.science/api/pith-number/2UQ7BDOK2HVLZYMABHNT5ONV5A/events.json","paper":"https://pith.science/paper/2UQ7BDOK"},"agent_actions":{"view_html":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A","download_json":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A.json","view_paper":"https://pith.science/paper/2UQ7BDOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08874&json=true","fetch_graph":"https://pith.science/api/pith-number/2UQ7BDOK2HVLZYMABHNT5ONV5A/graph.json","fetch_events":"https://pith.science/api/pith-number/2UQ7BDOK2HVLZYMABHNT5ONV5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A/action/storage_attestation","attest_author":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A/action/author_attestation","sign_citation":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A/action/citation_signature","submit_replication":"https://pith.science/pith/2UQ7BDOK2HVLZYMABHNT5ONV5A/action/replication_record"}},"created_at":"2026-07-04T23:55:10.542067+00:00","updated_at":"2026-07-04T23:55:10.542067+00:00"}