{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UHYAWGQXVDOOICYKJGSZE3JYUW","short_pith_number":"pith:UHYAWGQX","schema_version":"1.0","canonical_sha256":"a1f00b1a17a8dce40b0a49a5926d38a5b303529cc436b82463df8fbf9f8df4fd","source":{"kind":"arxiv","id":"1812.02890","version":1},"attestation_state":"computed","paper":{"title":"Three Tools for Practical Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Giorgio Patrini, Koen Lennart van der Veen, Peter Bloem, Ruben Seggers","submitted_at":"2018-12-07T03:28:41Z","abstract_excerpt":"Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to make differentially private machine learning more practical: (1) simple sanity checks which can be carried out in a centralized manner before training, (2) an adaptive clipping bound to reduce the effective number of tuneable privacy parameters, and (3) we show that large-batch tra"},"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":"1812.02890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-07T03:28:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cdd4958963ba9a944fce55e6fc799c516e75da06c52001b74f29fbdb14a9d822","abstract_canon_sha256":"c8ba2302f64a0eb620e0a5511694e67f7d6aa79d6765dd00007f68b1f2f0d518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:51.522040Z","signature_b64":"0Y/E1zZ0c56cEQg75jA5vEpRrGrZ4RoxPieHOaZoUZxFKCknhP5JXd/Mg0bWBdjQbMSgQ3y9nZ2lIKtCssxfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1f00b1a17a8dce40b0a49a5926d38a5b303529cc436b82463df8fbf9f8df4fd","last_reissued_at":"2026-05-17T23:58:51.521566Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:51.521566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Three Tools for Practical Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Giorgio Patrini, Koen Lennart van der Veen, Peter Bloem, Ruben Seggers","submitted_at":"2018-12-07T03:28:41Z","abstract_excerpt":"Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to make differentially private machine learning more practical: (1) simple sanity checks which can be carried out in a centralized manner before training, (2) an adaptive clipping bound to reduce the effective number of tuneable privacy parameters, and (3) we show that large-batch tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02890","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":""},"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":"1812.02890","created_at":"2026-05-17T23:58:51.521643+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02890v1","created_at":"2026-05-17T23:58:51.521643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02890","created_at":"2026-05-17T23:58:51.521643+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHYAWGQXVDOO","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHYAWGQXVDOOICYK","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHYAWGQX","created_at":"2026-05-18T12:32:56.356000+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/UHYAWGQXVDOOICYKJGSZE3JYUW","json":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW.json","graph_json":"https://pith.science/api/pith-number/UHYAWGQXVDOOICYKJGSZE3JYUW/graph.json","events_json":"https://pith.science/api/pith-number/UHYAWGQXVDOOICYKJGSZE3JYUW/events.json","paper":"https://pith.science/paper/UHYAWGQX"},"agent_actions":{"view_html":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW","download_json":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW.json","view_paper":"https://pith.science/paper/UHYAWGQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02890&json=true","fetch_graph":"https://pith.science/api/pith-number/UHYAWGQXVDOOICYKJGSZE3JYUW/graph.json","fetch_events":"https://pith.science/api/pith-number/UHYAWGQXVDOOICYKJGSZE3JYUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW/action/storage_attestation","attest_author":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW/action/author_attestation","sign_citation":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW/action/citation_signature","submit_replication":"https://pith.science/pith/UHYAWGQXVDOOICYKJGSZE3JYUW/action/replication_record"}},"created_at":"2026-05-17T23:58:51.521643+00:00","updated_at":"2026-05-17T23:58:51.521643+00:00"}