{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VXHJVIKTU63ZMZXEXZTZLRSEX","short_pith_number":"pith:2VXHJVIK","schema_version":"1.0","canonical_sha256":"d56e74d50a9d3dbcb33725f33cae3225eab7b1813f01d1580533ae02ca5d58b3","source":{"kind":"arxiv","id":"2402.13087","version":3},"attestation_state":"computed","paper":{"title":"Revisiting Differentially Private Hyper-parameter Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chenglong Wang, Di Wang, Tianhao Wang, Zihang Xiang","submitted_at":"2024-02-20T15:29:49Z","abstract_excerpt":"We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the prevalent DP-SGD, the privacy implications of tuning remain insufficiently understood or often totally ignored. Recent works propose a generic private selection solution for the tuning process, yet a fundamental question persists: is this privacy bound tight?\n  This paper provides an in-depth examination of this question. Initially, we provide studies affirmi"},"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":"2402.13087","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T15:29:49Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"062749a3ebbd743b713d3f71ad007fa6f591e46e2f87955184a13c59f906a703","abstract_canon_sha256":"763541ae8e55acf384bcda0d0d2c07ed5afec3c1f78497163d8c8a2360aa485a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:17.505101Z","signature_b64":"0g0EPXM2DMz0gtGjbEV5Vb/j7/blfzwpm1BZAP9zZD7D6Cs2IPL+QEBhAf7vqx+BYg3OkfRcjJ9Vnc1fxt79Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56e74d50a9d3dbcb33725f33cae3225eab7b1813f01d1580533ae02ca5d58b3","last_reissued_at":"2026-07-05T11:58:17.504649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:17.504649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Differentially Private Hyper-parameter Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chenglong Wang, Di Wang, Tianhao Wang, Zihang Xiang","submitted_at":"2024-02-20T15:29:49Z","abstract_excerpt":"We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the prevalent DP-SGD, the privacy implications of tuning remain insufficiently understood or often totally ignored. Recent works propose a generic private selection solution for the tuning process, yet a fundamental question persists: is this privacy bound tight?\n  This paper provides an in-depth examination of this question. Initially, we provide studies affirmi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13087","kind":"arxiv","version":3},"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/2402.13087/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":"2402.13087","created_at":"2026-07-05T11:58:17.504708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13087v3","created_at":"2026-07-05T11:58:17.504708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13087","created_at":"2026-07-05T11:58:17.504708+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VXHJVIKTU63","created_at":"2026-07-05T11:58:17.504708+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VXHJVIKTU63ZMZX","created_at":"2026-07-05T11:58:17.504708+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VXHJVIK","created_at":"2026-07-05T11:58:17.504708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06112","citing_title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX","json":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX.json","graph_json":"https://pith.science/api/pith-number/2VXHJVIKTU63ZMZXEXZTZLRSEX/graph.json","events_json":"https://pith.science/api/pith-number/2VXHJVIKTU63ZMZXEXZTZLRSEX/events.json","paper":"https://pith.science/paper/2VXHJVIK"},"agent_actions":{"view_html":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX","download_json":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX.json","view_paper":"https://pith.science/paper/2VXHJVIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13087&json=true","fetch_graph":"https://pith.science/api/pith-number/2VXHJVIKTU63ZMZXEXZTZLRSEX/graph.json","fetch_events":"https://pith.science/api/pith-number/2VXHJVIKTU63ZMZXEXZTZLRSEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX/action/storage_attestation","attest_author":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX/action/author_attestation","sign_citation":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX/action/citation_signature","submit_replication":"https://pith.science/pith/2VXHJVIKTU63ZMZXEXZTZLRSEX/action/replication_record"}},"created_at":"2026-07-05T11:58:17.504708+00:00","updated_at":"2026-07-05T11:58:17.504708+00:00"}