{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Z2XRN42N254OSJKQTS2SN7X6VA","short_pith_number":"pith:Z2XRN42N","canonical_record":{"source":{"id":"1802.03493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"86a4ae1339d9ea158370f88afcc3db475f43c072e6b52d82ba7d497e5443549f","abstract_canon_sha256":"96a4ea45a6f67d33dd101da440908a1ec728547ecff4ac47b8c573b806d7b56b"},"schema_version":"1.0"},"canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","source":{"kind":"arxiv","id":"1802.03493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03493","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03493v2","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03493","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z2XRN42N254O","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z2XRN42N254OSJKQ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z2XRN42N","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Z2XRN42N254OSJKQTS2SN7X6VA","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"86a4ae1339d9ea158370f88afcc3db475f43c072e6b52d82ba7d497e5443549f","abstract_canon_sha256":"96a4ea45a6f67d33dd101da440908a1ec728547ecff4ac47b8c573b806d7b56b"},"schema_version":"1.0"},"canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.972870Z","signature_b64":"940bcyZXK2zKyYXsgvFi7fDm3DAlkWfEHgZADb+voA75RzzJyuo+tCGwpQ+A66py37La3ThDCxoRxVWvSE10Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","last_reissued_at":"2026-05-18T00:15:04.972252Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.972252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03493","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFfjtH1jvZsXSCYC5cJIpm6tNsy7KJw4i3rGoOAyOcEnhV+zKYJyIoDc12+IC9y33r60gvIWapyVosGXBnVaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:07:18.564331Z"},"content_sha256":"c6448a802e6b7ae6a79dd3bd52124001fd21cad59f7c0baf86e1086bda8d256c","schema_version":"1.0","event_id":"sha256:c6448a802e6b7ae6a79dd3bd52124001fd21cad59f7c0baf86e1086bda8d256c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Z2XRN42N254OSJKQTS2SN7X6VA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"More Robust Doubly Robust Off-policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mehrdad Farajtabar, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2018-02-10T01:32:03Z","abstract_excerpt":"We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03493","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":""},"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":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvDut8evCVDYnzC9bIDPheFF0D1XZcuE03EUIru+OzsAj8yiiwvwr5BHgKPRBeeXXQUH0RRnlXo359UUrOCSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:07:18.564716Z"},"content_sha256":"dcb6f44fcd1afab640fcbde336678bb8bb197cabc2b09ec4f197728555018940","schema_version":"1.0","event_id":"sha256:dcb6f44fcd1afab640fcbde336678bb8bb197cabc2b09ec4f197728555018940"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/bundle.json","state_url":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2XRN42N254OSJKQTS2SN7X6VA/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":"2026-06-03T20:07:18Z","links":{"resolver":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA","bundle":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/bundle.json","state":"https://pith.science/pith/Z2XRN42N254OSJKQTS2SN7X6VA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2XRN42N254OSJKQTS2SN7X6VA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Z2XRN42N254OSJKQTS2SN7X6VA","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":"96a4ea45a6f67d33dd101da440908a1ec728547ecff4ac47b8c573b806d7b56b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","title_canon_sha256":"86a4ae1339d9ea158370f88afcc3db475f43c072e6b52d82ba7d497e5443549f"},"schema_version":"1.0","source":{"id":"1802.03493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03493","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03493v2","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03493","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z2XRN42N254O","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z2XRN42N254OSJKQ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z2XRN42N","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:dcb6f44fcd1afab640fcbde336678bb8bb197cabc2b09ec4f197728555018940","target":"graph","created_at":"2026-05-18T00:15:04Z","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":"We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, ","authors_text":"Mehrdad Farajtabar, Mohammad Ghavamzadeh, Yinlam Chow","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","title":"More Robust Doubly Robust Off-policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03493","kind":"arxiv","version":2},"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:c6448a802e6b7ae6a79dd3bd52124001fd21cad59f7c0baf86e1086bda8d256c","target":"record","created_at":"2026-05-18T00:15:04Z","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":"96a4ea45a6f67d33dd101da440908a1ec728547ecff4ac47b8c573b806d7b56b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-10T01:32:03Z","title_canon_sha256":"86a4ae1339d9ea158370f88afcc3db475f43c072e6b52d82ba7d497e5443549f"},"schema_version":"1.0","source":{"id":"1802.03493","kind":"arxiv","version":2}},"canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceaf16f34dd778e925509cb526fefea837440aaaa9ed3fc07eab0f1a1a4c1794","first_computed_at":"2026-05-18T00:15:04.972252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:04.972252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"940bcyZXK2zKyYXsgvFi7fDm3DAlkWfEHgZADb+voA75RzzJyuo+tCGwpQ+A66py37La3ThDCxoRxVWvSE10Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:04.972870Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6448a802e6b7ae6a79dd3bd52124001fd21cad59f7c0baf86e1086bda8d256c","sha256:dcb6f44fcd1afab640fcbde336678bb8bb197cabc2b09ec4f197728555018940"],"state_sha256":"1efd7acc9c223021d7790d8c3cd8a1510446c96e0ebf5837a06d20f1f4e57aaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MPoYuqByZNmqPCxPpxw4G97aHpUYutIce3IHrmrCeYS4fp4/ZlTbLakcQ9MeRYYae8Bs3IjMt7IEDGKgTNowAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:07:18.566849Z","bundle_sha256":"8d8974b4cb97c553750de9e9ee86d5511ffa70fea12029232beeac98d848a0af"}}