{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KVHWSFQR7X35KQG42ENRVKBLNE","short_pith_number":"pith:KVHWSFQR","schema_version":"1.0","canonical_sha256":"554f691611fdf7d540dcd11b1aa82b693fc7fbd7587fea3db0ad37b5847f4461","source":{"kind":"arxiv","id":"2407.13621","version":2},"attestation_state":"computed","paper":{"title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jiuxiang Gu, Yingyu Liang, Zhao Song, Zhenmei Shi, Zhizhou Sha","submitted_at":"2024-07-18T15:57:55Z","abstract_excerpt":"Training data privacy is a fundamental problem in modern Artificial Intelligence (AI) applications, such as face recognition, recommendation systems, language generation, and many others, as it may contain sensitive user information related to legal issues. To fundamentally understand how privacy mechanisms work in AI applications, we study differential privacy (DP) in the Neural Tangent Kernel (NTK) regression setting, where DP is one of the most powerful tools for measuring privacy under statistical learning, and NTK is one of the most popular analysis frameworks for studying the learning me"},"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":"2407.13621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T15:57:55Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"6731aeebb4d30a620aad12ebf1382f14cdcd3d158b0d980c5ca08461ea383fa1","abstract_canon_sha256":"88af8a3d88835a2eef955bafd8578464b4e5dae168da777b49f5c88776b77a03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:19.143135Z","signature_b64":"g8dSKw0vpR4s4MeIroW4J05nJ4549v91HlDDkoVZZx+m86nwc9mpgcUNDm15b0U5JijLPkqXTjRGOoMiPScIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"554f691611fdf7d540dcd11b1aa82b693fc7fbd7587fea3db0ad37b5847f4461","last_reissued_at":"2026-07-05T09:30:19.142651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:19.142651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jiuxiang Gu, Yingyu Liang, Zhao Song, Zhenmei Shi, Zhizhou Sha","submitted_at":"2024-07-18T15:57:55Z","abstract_excerpt":"Training data privacy is a fundamental problem in modern Artificial Intelligence (AI) applications, such as face recognition, recommendation systems, language generation, and many others, as it may contain sensitive user information related to legal issues. To fundamentally understand how privacy mechanisms work in AI applications, we study differential privacy (DP) in the Neural Tangent Kernel (NTK) regression setting, where DP is one of the most powerful tools for measuring privacy under statistical learning, and NTK is one of the most popular analysis frameworks for studying the learning me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13621","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/2407.13621/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":"2407.13621","created_at":"2026-07-05T09:30:19.142710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13621v2","created_at":"2026-07-05T09:30:19.142710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13621","created_at":"2026-07-05T09:30:19.142710+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVHWSFQR7X35","created_at":"2026-07-05T09:30:19.142710+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVHWSFQR7X35KQG4","created_at":"2026-07-05T09:30:19.142710+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVHWSFQR","created_at":"2026-07-05T09:30:19.142710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16284","citing_title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE","json":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE.json","graph_json":"https://pith.science/api/pith-number/KVHWSFQR7X35KQG42ENRVKBLNE/graph.json","events_json":"https://pith.science/api/pith-number/KVHWSFQR7X35KQG42ENRVKBLNE/events.json","paper":"https://pith.science/paper/KVHWSFQR"},"agent_actions":{"view_html":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE","download_json":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE.json","view_paper":"https://pith.science/paper/KVHWSFQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13621&json=true","fetch_graph":"https://pith.science/api/pith-number/KVHWSFQR7X35KQG42ENRVKBLNE/graph.json","fetch_events":"https://pith.science/api/pith-number/KVHWSFQR7X35KQG42ENRVKBLNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE/action/storage_attestation","attest_author":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE/action/author_attestation","sign_citation":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE/action/citation_signature","submit_replication":"https://pith.science/pith/KVHWSFQR7X35KQG42ENRVKBLNE/action/replication_record"}},"created_at":"2026-07-05T09:30:19.142710+00:00","updated_at":"2026-07-05T09:30:19.142710+00:00"}