{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:V7GV5H4DOBB4F7ENKWXYTTJ4FP","short_pith_number":"pith:V7GV5H4D","schema_version":"1.0","canonical_sha256":"afcd5e9f837043c2fc8d55af89cd3c2bf32f5385bb0943ff685db392150bf6b1","source":{"kind":"arxiv","id":"1503.02834","version":1},"attestation_state":"computed","paper":{"title":"Doubly Robust Policy Evaluation and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ME","authors_text":"Dumitru Erhan, John Langford, Lihong Li, Miroslav Dud\\'ik","submitted_at":"2015-03-10T09:51:50Z","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"},"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":"1503.02834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-03-10T09:51:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71ad85f3dfa1c79299740b4f1867b7676f7274250812c6acdb451a988d4dbff1","abstract_canon_sha256":"ae8f964e1b05664159ea13d14eee4ba4c9d5edea0d84e30a81a91e80da7083c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:25:12.997576Z","signature_b64":"fUxp+9yyE1ya3RSVqywXGjtauQjSPttgVQnN9nD8j6HvtJFHIxF5+6d4JoEnYPIBQUpfLuDfSrzIk0f7GuAHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afcd5e9f837043c2fc8d55af89cd3c2bf32f5385bb0943ff685db392150bf6b1","last_reissued_at":"2026-05-18T02:25:12.996940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:25:12.996940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Robust Policy Evaluation and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ME","authors_text":"Dumitru Erhan, John Langford, Lihong Li, Miroslav Dud\\'ik","submitted_at":"2015-03-10T09:51:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.02834","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":"1503.02834","created_at":"2026-05-18T02:25:12.997053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.02834v1","created_at":"2026-05-18T02:25:12.997053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.02834","created_at":"2026-05-18T02:25:12.997053+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7GV5H4DOBB4","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7GV5H4DOBB4F7EN","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7GV5H4D","created_at":"2026-05-18T12:29:44.643036+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/V7GV5H4DOBB4F7ENKWXYTTJ4FP","json":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP.json","graph_json":"https://pith.science/api/pith-number/V7GV5H4DOBB4F7ENKWXYTTJ4FP/graph.json","events_json":"https://pith.science/api/pith-number/V7GV5H4DOBB4F7ENKWXYTTJ4FP/events.json","paper":"https://pith.science/paper/V7GV5H4D"},"agent_actions":{"view_html":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP","download_json":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP.json","view_paper":"https://pith.science/paper/V7GV5H4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.02834&json=true","fetch_graph":"https://pith.science/api/pith-number/V7GV5H4DOBB4F7ENKWXYTTJ4FP/graph.json","fetch_events":"https://pith.science/api/pith-number/V7GV5H4DOBB4F7ENKWXYTTJ4FP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP/action/storage_attestation","attest_author":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP/action/author_attestation","sign_citation":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP/action/citation_signature","submit_replication":"https://pith.science/pith/V7GV5H4DOBB4F7ENKWXYTTJ4FP/action/replication_record"}},"created_at":"2026-05-18T02:25:12.997053+00:00","updated_at":"2026-05-18T02:25:12.997053+00:00"}