{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AGJSQXDDQPV64UWDGWGI4OBGNR","short_pith_number":"pith:AGJSQXDD","canonical_record":{"source":{"id":"1902.00174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:26:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"53200f268bf82ff6b8359ec384a9487d853f7dd36083248f3dcb8072dd74c925","abstract_canon_sha256":"ba0205709e727d29fba4482cea5068c266f38d9895c934d9fc23df08fcb48911"},"schema_version":"1.0"},"canonical_sha256":"0193285c6383ebee52c3358c8e38266c4356c435170dad938b2196a888446b0d","source":{"kind":"arxiv","id":"1902.00174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00174","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00174v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00174","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"AGJSQXDDQPV6","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AGJSQXDDQPV64UWD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AGJSQXDD","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AGJSQXDDQPV64UWDGWGI4OBGNR","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:26:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"53200f268bf82ff6b8359ec384a9487d853f7dd36083248f3dcb8072dd74c925","abstract_canon_sha256":"ba0205709e727d29fba4482cea5068c266f38d9895c934d9fc23df08fcb48911"},"schema_version":"1.0"},"canonical_sha256":"0193285c6383ebee52c3358c8e38266c4356c435170dad938b2196a888446b0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:58.097519Z","signature_b64":"8zQGgaEgDFsbdrOoCxm3XmI+G6tGkXEL0X3uJlugqsECgWmIzz/DFS4XiDbjJKPU3Vq11S3jZVIXnw4IxRXPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0193285c6383ebee52c3358c8e38266c4356c435170dad938b2196a888446b0d","last_reissued_at":"2026-05-17T23:54:58.097028Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:58.097028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00174","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StVcmbDAXDgKa1Gt3TkI/0vrnPNG/HOKSCMSdx7KoKvLW1T0kFCZ+UNTPIP/uQQJa6tHIyLRdVDMRQIyqRHABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:40:38.553295Z"},"content_sha256":"fd377858566a70add24084280a64d4d05cb8fac58abc000a784f90f4a20a9d45","schema_version":"1.0","event_id":"sha256:fd377858566a70add24084280a64d4d05cb8fac58abc000a784f90f4a20a9d45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AGJSQXDDQPV64UWDGWGI4OBGNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Privacy Preserving Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerome Miklau, Philip S. Thomas, Tengyang Xie","submitted_at":"2019-02-01T04:26:34Z","abstract_excerpt":"Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, we present the first differentially private approach for off-policy evaluation. We provide a theoretical analysis of the privacy-preserving properties of our algorithm and analyze its utility (speed of convergence). After describing some results of this theoretical analysis, we sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00174","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1NmJPibrtKYmRGIoRUW7gitGKHJsJ+Q+CLuZ4sX0LDWZGUUlJ3KBJvP2ShhC8gwvNN5lUYrBAe7++l4yN9VAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:40:38.553668Z"},"content_sha256":"766ce0ca660f1c5050a97419243e9aea26d45b51efb78c86e73208a027bcbb25","schema_version":"1.0","event_id":"sha256:766ce0ca660f1c5050a97419243e9aea26d45b51efb78c86e73208a027bcbb25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/bundle.json","state_url":"https://pith.science/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T14:40:38Z","links":{"resolver":"https://pith.science/pith/AGJSQXDDQPV64UWDGWGI4OBGNR","bundle":"https://pith.science/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/bundle.json","state":"https://pith.science/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGJSQXDDQPV64UWDGWGI4OBGNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AGJSQXDDQPV64UWDGWGI4OBGNR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ba0205709e727d29fba4482cea5068c266f38d9895c934d9fc23df08fcb48911","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:26:34Z","title_canon_sha256":"53200f268bf82ff6b8359ec384a9487d853f7dd36083248f3dcb8072dd74c925"},"schema_version":"1.0","source":{"id":"1902.00174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00174","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00174v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00174","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"AGJSQXDDQPV6","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AGJSQXDDQPV64UWD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AGJSQXDD","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:766ce0ca660f1c5050a97419243e9aea26d45b51efb78c86e73208a027bcbb25","target":"graph","created_at":"2026-05-17T23:54:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, we present the first differentially private approach for off-policy evaluation. We provide a theoretical analysis of the privacy-preserving properties of our algorithm and analyze its utility (speed of convergence). After describing some results of this theoretical analysis, we sh","authors_text":"Gerome Miklau, Philip S. Thomas, Tengyang Xie","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:26:34Z","title":"Privacy Preserving Off-Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00174","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd377858566a70add24084280a64d4d05cb8fac58abc000a784f90f4a20a9d45","target":"record","created_at":"2026-05-17T23:54:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ba0205709e727d29fba4482cea5068c266f38d9895c934d9fc23df08fcb48911","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:26:34Z","title_canon_sha256":"53200f268bf82ff6b8359ec384a9487d853f7dd36083248f3dcb8072dd74c925"},"schema_version":"1.0","source":{"id":"1902.00174","kind":"arxiv","version":1}},"canonical_sha256":"0193285c6383ebee52c3358c8e38266c4356c435170dad938b2196a888446b0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0193285c6383ebee52c3358c8e38266c4356c435170dad938b2196a888446b0d","first_computed_at":"2026-05-17T23:54:58.097028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:58.097028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zQGgaEgDFsbdrOoCxm3XmI+G6tGkXEL0X3uJlugqsECgWmIzz/DFS4XiDbjJKPU3Vq11S3jZVIXnw4IxRXPAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:58.097519Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd377858566a70add24084280a64d4d05cb8fac58abc000a784f90f4a20a9d45","sha256:766ce0ca660f1c5050a97419243e9aea26d45b51efb78c86e73208a027bcbb25"],"state_sha256":"8f9cbfecf255ee233d974df9ec05fe97c21ed1a6e9cf466f0d3b1166c6cecf8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ScHqKNCRgx7xs3SFX3Incic1HZyzYy4cmmXJnOaM6QhiuqZzQMGaDmTyoGrErZIeOrHHE97P0AZHL4o+2Z7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:40:38.555702Z","bundle_sha256":"ba3bbd75f2a66d25af82b8629c4a5dab29c94bc2dd02e577cc1863406decabb5"}}