{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OJ6D735MQ6AOGXWHCFKNEJKAIL","short_pith_number":"pith:OJ6D735M","schema_version":"1.0","canonical_sha256":"727c3fefac8780e35ec71154d2254042f65ee74ba3d09dd56e6737822c51ba52","source":{"kind":"arxiv","id":"1905.09982","version":2},"attestation_state":"computed","paper":{"title":"Hypothesis Testing Interpretations and Renyi Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Balle, Gilles Barthe, Justin Hsu, Marco Gaboardi, Tetsuya Sato","submitted_at":"2019-05-24T00:53:24Z","abstract_excerpt":"Differential privacy is a de facto standard in data privacy, with applications in the public and private sectors. A way to explain differential privacy, which is particularly appealing to statistician and social scientists is by means of its statistical hypothesis testing interpretation. Informally, one cannot effectively test whether a specific individual has contributed her data by observing the output of a private mechanism---any test cannot have both high significance and high power.\n  In this paper, we identify some conditions under which a privacy definition given in terms of a statistic"},"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":"1905.09982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T00:53:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b597b7a09231005dc3fd773ce08e84c8ad13e07fb526a6638af174b4c4d0fd54","abstract_canon_sha256":"d7a80b6eccca3d142b14dacffc95979ee5f350db23db8328b09d34c7c3badde4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:24.912228Z","signature_b64":"bYTsQ9GcLRhdr5wEA7NOI1Y71H80AkbIERyAf0pHBdGS9DB4dcFZVAS2/EPac9VI9cALgj9gipDIK25SagClAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"727c3fefac8780e35ec71154d2254042f65ee74ba3d09dd56e6737822c51ba52","last_reissued_at":"2026-07-05T06:44:24.911785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:24.911785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypothesis Testing Interpretations and Renyi Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Balle, Gilles Barthe, Justin Hsu, Marco Gaboardi, Tetsuya Sato","submitted_at":"2019-05-24T00:53:24Z","abstract_excerpt":"Differential privacy is a de facto standard in data privacy, with applications in the public and private sectors. A way to explain differential privacy, which is particularly appealing to statistician and social scientists is by means of its statistical hypothesis testing interpretation. Informally, one cannot effectively test whether a specific individual has contributed her data by observing the output of a private mechanism---any test cannot have both high significance and high power.\n  In this paper, we identify some conditions under which a privacy definition given in terms of a statistic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09982","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/1905.09982/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":"1905.09982","created_at":"2026-07-05T06:44:24.911843+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09982v2","created_at":"2026-07-05T06:44:24.911843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09982","created_at":"2026-07-05T06:44:24.911843+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ6D735MQ6AO","created_at":"2026-07-05T06:44:24.911843+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ6D735MQ6AOGXWH","created_at":"2026-07-05T06:44:24.911843+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ6D735M","created_at":"2026-07-05T06:44:24.911843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20621","citing_title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL","json":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL.json","graph_json":"https://pith.science/api/pith-number/OJ6D735MQ6AOGXWHCFKNEJKAIL/graph.json","events_json":"https://pith.science/api/pith-number/OJ6D735MQ6AOGXWHCFKNEJKAIL/events.json","paper":"https://pith.science/paper/OJ6D735M"},"agent_actions":{"view_html":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL","download_json":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL.json","view_paper":"https://pith.science/paper/OJ6D735M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09982&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ6D735MQ6AOGXWHCFKNEJKAIL/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ6D735MQ6AOGXWHCFKNEJKAIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL/action/storage_attestation","attest_author":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL/action/author_attestation","sign_citation":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL/action/citation_signature","submit_replication":"https://pith.science/pith/OJ6D735MQ6AOGXWHCFKNEJKAIL/action/replication_record"}},"created_at":"2026-07-05T06:44:24.911843+00:00","updated_at":"2026-07-05T06:44:24.911843+00:00"}