{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7PWVSRV7AM7WHFHVIPJPAFKM5I","short_pith_number":"pith:7PWVSRV7","schema_version":"1.0","canonical_sha256":"fbed5946bf033f6394f543d2f0154cea2f2d948c8994fb416558f6c5457b2813","source":{"kind":"arxiv","id":"2305.05900","version":2},"attestation_state":"computed","paper":{"title":"DPMLBench: Holistic Evaluation of Differentially Private Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Chengkun Wei, Min Chen, Minghu Zhao, Wenlong Meng, Wenzhi Chen, Yuan Fan, Zhikun Zhang","submitted_at":"2023-05-10T05:08:36Z","abstract_excerpt":"Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning techniques, differentially private machine learning (DPML) is increasingly important. As the most classic DPML algorithm, DP-SGD incurs a significant loss of utility, which hinders DPML's deployment in practice. Many studies have recently proposed improved algorithms based on DP-SGD to mitigate utility loss. However, these studies are isolated and cannot comprehensively measure the performance of improv"},"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":"2305.05900","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T05:08:36Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"ce17e6e9147c1de0f2f6fc92139de3ac11c726e3ffecc1c732af162e192d88f0","abstract_canon_sha256":"05778f5aa3ee3c53ddb7844da5f485afcbae480f52c2fe02a49d0ad2f4949563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:44.490477Z","signature_b64":"lbem4IxX3TBG6rkTImM/NCninEo7GiLkI5FM8wT8S14CIE8Am0+N9/6vlWoXpw1Pugmiv0C1NQeJcqPMBKSJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbed5946bf033f6394f543d2f0154cea2f2d948c8994fb416558f6c5457b2813","last_reissued_at":"2026-07-05T07:00:44.489999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:44.489999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPMLBench: Holistic Evaluation of Differentially Private Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Chengkun Wei, Min Chen, Minghu Zhao, Wenlong Meng, Wenzhi Chen, Yuan Fan, Zhikun Zhang","submitted_at":"2023-05-10T05:08:36Z","abstract_excerpt":"Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning techniques, differentially private machine learning (DPML) is increasingly important. As the most classic DPML algorithm, DP-SGD incurs a significant loss of utility, which hinders DPML's deployment in practice. Many studies have recently proposed improved algorithms based on DP-SGD to mitigate utility loss. However, these studies are isolated and cannot comprehensively measure the performance of improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05900","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/2305.05900/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":"2305.05900","created_at":"2026-07-05T07:00:44.490058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05900v2","created_at":"2026-07-05T07:00:44.490058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05900","created_at":"2026-07-05T07:00:44.490058+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PWVSRV7AM7W","created_at":"2026-07-05T07:00:44.490058+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PWVSRV7AM7WHFHV","created_at":"2026-07-05T07:00:44.490058+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PWVSRV7","created_at":"2026-07-05T07:00:44.490058+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/7PWVSRV7AM7WHFHVIPJPAFKM5I","json":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I.json","graph_json":"https://pith.science/api/pith-number/7PWVSRV7AM7WHFHVIPJPAFKM5I/graph.json","events_json":"https://pith.science/api/pith-number/7PWVSRV7AM7WHFHVIPJPAFKM5I/events.json","paper":"https://pith.science/paper/7PWVSRV7"},"agent_actions":{"view_html":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I","download_json":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I.json","view_paper":"https://pith.science/paper/7PWVSRV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05900&json=true","fetch_graph":"https://pith.science/api/pith-number/7PWVSRV7AM7WHFHVIPJPAFKM5I/graph.json","fetch_events":"https://pith.science/api/pith-number/7PWVSRV7AM7WHFHVIPJPAFKM5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I/action/storage_attestation","attest_author":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I/action/author_attestation","sign_citation":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I/action/citation_signature","submit_replication":"https://pith.science/pith/7PWVSRV7AM7WHFHVIPJPAFKM5I/action/replication_record"}},"created_at":"2026-07-05T07:00:44.490058+00:00","updated_at":"2026-07-05T07:00:44.490058+00:00"}