{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T3N5SMRDDC6JRLAXCOVSFTJ3NF","short_pith_number":"pith:T3N5SMRD","schema_version":"1.0","canonical_sha256":"9edbd9322318bc98ac1713ab22cd3b694acbd4aa66c1cbef33bf2c5314432525","source":{"kind":"arxiv","id":"2006.09129","version":1},"attestation_state":"computed","paper":{"title":"Model Explanations with Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Neel Patel, Reza Shokri, Yair Zick","submitted_at":"2020-06-16T13:18:02Z","abstract_excerpt":"Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the explanation data used to generate them, thus undermining data privacy. To address this issue, we propose differentially private algorithms to construct feature-based model explanations. We design an adaptive differentially private gradient descent algorithm, that finds the minimal privacy budget required to produce accurate explanations. It reduces the overall "},"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":"2006.09129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T13:18:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"828fbe00499a21cba476dc42a13556f072970f3ce40b60d445fb74ac3a8a57bc","abstract_canon_sha256":"22ef29f6f6e78fad43bc650030b537a27c400f13875369c2f1e670483b0bdaed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:46.637499Z","signature_b64":"byOY4PFHmwbn3ixpj4rlXtjs6scrlIBKepLxUVWPU980oMtzGbDSZ08+UpPagtXFTRoPgB6EVTbE2z4IYEDFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9edbd9322318bc98ac1713ab22cd3b694acbd4aa66c1cbef33bf2c5314432525","last_reissued_at":"2026-07-05T01:10:46.637086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:46.637086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Explanations with Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Neel Patel, Reza Shokri, Yair Zick","submitted_at":"2020-06-16T13:18:02Z","abstract_excerpt":"Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the explanation data used to generate them, thus undermining data privacy. To address this issue, we propose differentially private algorithms to construct feature-based model explanations. We design an adaptive differentially private gradient descent algorithm, that finds the minimal privacy budget required to produce accurate explanations. It reduces the overall "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09129","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.09129/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":"2006.09129","created_at":"2026-07-05T01:10:46.637140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09129v1","created_at":"2026-07-05T01:10:46.637140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09129","created_at":"2026-07-05T01:10:46.637140+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3N5SMRDDC6J","created_at":"2026-07-05T01:10:46.637140+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3N5SMRDDC6JRLAX","created_at":"2026-07-05T01:10:46.637140+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3N5SMRD","created_at":"2026-07-05T01:10:46.637140+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/T3N5SMRDDC6JRLAXCOVSFTJ3NF","json":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF.json","graph_json":"https://pith.science/api/pith-number/T3N5SMRDDC6JRLAXCOVSFTJ3NF/graph.json","events_json":"https://pith.science/api/pith-number/T3N5SMRDDC6JRLAXCOVSFTJ3NF/events.json","paper":"https://pith.science/paper/T3N5SMRD"},"agent_actions":{"view_html":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF","download_json":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF.json","view_paper":"https://pith.science/paper/T3N5SMRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09129&json=true","fetch_graph":"https://pith.science/api/pith-number/T3N5SMRDDC6JRLAXCOVSFTJ3NF/graph.json","fetch_events":"https://pith.science/api/pith-number/T3N5SMRDDC6JRLAXCOVSFTJ3NF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF/action/storage_attestation","attest_author":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF/action/author_attestation","sign_citation":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF/action/citation_signature","submit_replication":"https://pith.science/pith/T3N5SMRDDC6JRLAXCOVSFTJ3NF/action/replication_record"}},"created_at":"2026-07-05T01:10:46.637140+00:00","updated_at":"2026-07-05T01:10:46.637140+00:00"}