{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:U2OQJAISNUBVCZMP6R7FENSHVF","short_pith_number":"pith:U2OQJAIS","schema_version":"1.0","canonical_sha256":"a69d0481126d0351658ff47e523647a95922129a41a6499ac5eb3c02c6f9ded0","source":{"kind":"arxiv","id":"1603.02010","version":1},"attestation_state":"computed","paper":{"title":"Differentially Private Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Balle, Doina Precup, Maziar Gomrokchi","submitted_at":"2016-03-07T11:23:57Z","abstract_excerpt":"We present the first differentially private algorithms for reinforcement learning, which apply to the task of evaluating a fixed policy. We establish two approaches for achieving differential privacy, provide a theoretical analysis of the privacy and utility of the two algorithms, and show promising results on simple empirical examples."},"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":"1603.02010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-07T11:23:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a1aeb7ae0d93e7f0db20a88f212115750c8555cf86431eaf1b8b507c123000a","abstract_canon_sha256":"b5e94d2acb84e0ac763e6fe43afcf3aa24eb291b7d64b2a4f358f77f2eeb173f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:31.855518Z","signature_b64":"8Pg6nYGisLVLzfNfpfwOSgXuopmvOctYnIURuiXwVxNhYbf5+V4FmkkUDvpuFIZK601jQWwfej1532tRj4XtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a69d0481126d0351658ff47e523647a95922129a41a6499ac5eb3c02c6f9ded0","last_reissued_at":"2026-05-18T01:19:31.855056Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:31.855056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Balle, Doina Precup, Maziar Gomrokchi","submitted_at":"2016-03-07T11:23:57Z","abstract_excerpt":"We present the first differentially private algorithms for reinforcement learning, which apply to the task of evaluating a fixed policy. We establish two approaches for achieving differential privacy, provide a theoretical analysis of the privacy and utility of the two algorithms, and show promising results on simple empirical examples."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02010","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":"1603.02010","created_at":"2026-05-18T01:19:31.855123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.02010v1","created_at":"2026-05-18T01:19:31.855123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02010","created_at":"2026-05-18T01:19:31.855123+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2OQJAISNUBV","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2OQJAISNUBVCZMP","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2OQJAIS","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05266","citing_title":"Differential Privacy in the Extensive-Form Bandit Problem","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF","json":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF.json","graph_json":"https://pith.science/api/pith-number/U2OQJAISNUBVCZMP6R7FENSHVF/graph.json","events_json":"https://pith.science/api/pith-number/U2OQJAISNUBVCZMP6R7FENSHVF/events.json","paper":"https://pith.science/paper/U2OQJAIS"},"agent_actions":{"view_html":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF","download_json":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF.json","view_paper":"https://pith.science/paper/U2OQJAIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.02010&json=true","fetch_graph":"https://pith.science/api/pith-number/U2OQJAISNUBVCZMP6R7FENSHVF/graph.json","fetch_events":"https://pith.science/api/pith-number/U2OQJAISNUBVCZMP6R7FENSHVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF/action/storage_attestation","attest_author":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF/action/author_attestation","sign_citation":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF/action/citation_signature","submit_replication":"https://pith.science/pith/U2OQJAISNUBVCZMP6R7FENSHVF/action/replication_record"}},"created_at":"2026-05-18T01:19:31.855123+00:00","updated_at":"2026-05-18T01:19:31.855123+00:00"}