{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SGGTUFWMMDOAMWBUSBXB3EGFZB","short_pith_number":"pith:SGGTUFWM","schema_version":"1.0","canonical_sha256":"918d3a16cc60dc065834906e1d90c5c85fc535d6bb1ac4965aa19b36136a2eb8","source":{"kind":"arxiv","id":"1803.05101","version":1},"attestation_state":"computed","paper":{"title":"Model-Agnostic Private Learning via Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Om Thakkar, Raef Bassily","submitted_at":"2018-03-14T02:09:15Z","abstract_excerpt":"We design differentially private learning algorithms that are agnostic to the learning model. Our algorithms are interactive in nature, i.e., instead of outputting a model based on the training data, they provide predictions for a set of $m$ feature vectors that arrive online. We show that, for the feature vectors on which an ensemble of models (trained on random disjoint subsets of a dataset) makes consistent predictions, there is almost no-cost of privacy in generating accurate predictions for those feature vectors. To that end, we provide a novel coupling of the distance to instability fram"},"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":"1803.05101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-14T02:09:15Z","cross_cats_sorted":[],"title_canon_sha256":"162c22501013f41b1c04506524cb6780d63a119142b48e3a9823fd32943f564d","abstract_canon_sha256":"360d84cddf0b3498f9e25dffc8448b74bb74d23b9dfc0e8d63caf253a8c6c481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:02.074246Z","signature_b64":"gdMgRGyAujWXTKqxJCHS2niZQQyBoEO0OpbtRuseIok/KrWg7Ax+nnLreSdKOKxNgZ74HV042aCFTNTDnfgoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918d3a16cc60dc065834906e1d90c5c85fc535d6bb1ac4965aa19b36136a2eb8","last_reissued_at":"2026-05-18T00:21:02.073752Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:02.073752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Agnostic Private Learning via Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Om Thakkar, Raef Bassily","submitted_at":"2018-03-14T02:09:15Z","abstract_excerpt":"We design differentially private learning algorithms that are agnostic to the learning model. Our algorithms are interactive in nature, i.e., instead of outputting a model based on the training data, they provide predictions for a set of $m$ feature vectors that arrive online. We show that, for the feature vectors on which an ensemble of models (trained on random disjoint subsets of a dataset) makes consistent predictions, there is almost no-cost of privacy in generating accurate predictions for those feature vectors. To that end, we provide a novel coupling of the distance to instability fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05101","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":"1803.05101","created_at":"2026-05-18T00:21:02.073821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05101v1","created_at":"2026-05-18T00:21:02.073821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05101","created_at":"2026-05-18T00:21:02.073821+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGGTUFWMMDOA","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGGTUFWMMDOAMWBU","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGGTUFWM","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.15791","citing_title":"Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Stud","ref_index":227,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB","json":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB.json","graph_json":"https://pith.science/api/pith-number/SGGTUFWMMDOAMWBUSBXB3EGFZB/graph.json","events_json":"https://pith.science/api/pith-number/SGGTUFWMMDOAMWBUSBXB3EGFZB/events.json","paper":"https://pith.science/paper/SGGTUFWM"},"agent_actions":{"view_html":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB","download_json":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB.json","view_paper":"https://pith.science/paper/SGGTUFWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05101&json=true","fetch_graph":"https://pith.science/api/pith-number/SGGTUFWMMDOAMWBUSBXB3EGFZB/graph.json","fetch_events":"https://pith.science/api/pith-number/SGGTUFWMMDOAMWBUSBXB3EGFZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB/action/storage_attestation","attest_author":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB/action/author_attestation","sign_citation":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB/action/citation_signature","submit_replication":"https://pith.science/pith/SGGTUFWMMDOAMWBUSBXB3EGFZB/action/replication_record"}},"created_at":"2026-05-18T00:21:02.073821+00:00","updated_at":"2026-05-18T00:21:02.073821+00:00"}