{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:V7GV5H4DOBB4F7ENKWXYTTJ4FP","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":"ae8f964e1b05664159ea13d14eee4ba4c9d5edea0d84e30a81a91e80da7083c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-03-10T09:51:50Z","title_canon_sha256":"71ad85f3dfa1c79299740b4f1867b7676f7274250812c6acdb451a988d4dbff1"},"schema_version":"1.0","source":{"id":"1503.02834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.02834","created_at":"2026-05-18T02:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"1503.02834v1","created_at":"2026-05-18T02:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.02834","created_at":"2026-05-18T02:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"V7GV5H4DOBB4","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"V7GV5H4DOBB4F7EN","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"V7GV5H4D","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:7e22c4bd9debc4451d242f8542d3f379af6a0bdc98a23f88388678284bdc0638","target":"graph","created_at":"2026-05-18T02:25:12Z","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 sequential decision making in environments where rewards are only partially observed, but can be modeled as a function of observed contexts and the chosen action by the decision maker. This setting, known as contextual bandits, encompasses a wide variety of applications such as health care, content recommendation and Internet advertising. A central task is evaluation of a new policy given historic data consisting of contexts, actions and received rewards. The key challenge is that the past data typically does not faithfully represent proportions of actions taken by a new policy. Previ","authors_text":"Dumitru Erhan, John Langford, Lihong Li, Miroslav Dud\\'ik","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-03-10T09:51:50Z","title":"Doubly Robust Policy Evaluation and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.02834","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":"sha256:8fe4ef3a3ff083e3ba8037342bf16d1c8e4512dc1b701bd62d76f4fc89aeb954","target":"record","created_at":"2026-05-18T02:25:12Z","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":"ae8f964e1b05664159ea13d14eee4ba4c9d5edea0d84e30a81a91e80da7083c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-03-10T09:51:50Z","title_canon_sha256":"71ad85f3dfa1c79299740b4f1867b7676f7274250812c6acdb451a988d4dbff1"},"schema_version":"1.0","source":{"id":"1503.02834","kind":"arxiv","version":1}},"canonical_sha256":"afcd5e9f837043c2fc8d55af89cd3c2bf32f5385bb0943ff685db392150bf6b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afcd5e9f837043c2fc8d55af89cd3c2bf32f5385bb0943ff685db392150bf6b1","first_computed_at":"2026-05-18T02:25:12.996940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:25:12.996940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fUxp+9yyE1ya3RSVqywXGjtauQjSPttgVQnN9nD8j6HvtJFHIxF5+6d4JoEnYPIBQUpfLuDfSrzIk0f7GuAHDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:25:12.997576Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.02834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fe4ef3a3ff083e3ba8037342bf16d1c8e4512dc1b701bd62d76f4fc89aeb954","sha256:7e22c4bd9debc4451d242f8542d3f379af6a0bdc98a23f88388678284bdc0638"],"state_sha256":"e823731f7c3271990d7130d66ff30e2caffa82b1df85d2d7040bf4b8a4a84dcd"}