{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:E7SFMNKJY4IWIE37VYIVXMX7EC","short_pith_number":"pith:E7SFMNKJ","schema_version":"1.0","canonical_sha256":"27e4563549c71164137fae115bb2ff20b3cae8e64cc666c69fb29618e62324d8","source":{"kind":"arxiv","id":"1806.02794","version":1},"attestation_state":"computed","paper":{"title":"Unbiased Estimation of the Value of an Optimized Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elon Portugaly, Joseph J. Pfeiffer III","submitted_at":"2018-06-07T17:12:50Z","abstract_excerpt":"Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased estimator for the value of deploying B (i.e., switching from policy A to B), direct application of those samples to learn the the optimized policy P generally does not provide an unbiased estimator of the value of P as the samples were observed when constructing P. In situations "},"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":"1806.02794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:12:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"51b73af78aa47c9e941cb18314f5ed3293e47c04be582c2c1f27e127f6d754c0","abstract_canon_sha256":"4d61884b5903af2d4eb4fbdbbde733ca5b1096cfd29457cba9e47dfa5fe1e56d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:55.634973Z","signature_b64":"VvQdtx3bazQUGmgSRRNsOCPK6bMuezyv8v56MaoGPd3L0lK5Ekg43msDX/DfJ5K6G6qOZze9DaRd4ft8N03tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27e4563549c71164137fae115bb2ff20b3cae8e64cc666c69fb29618e62324d8","last_reissued_at":"2026-05-18T00:13:55.634296Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:55.634296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiased Estimation of the Value of an Optimized Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elon Portugaly, Joseph J. Pfeiffer III","submitted_at":"2018-06-07T17:12:50Z","abstract_excerpt":"Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased estimator for the value of deploying B (i.e., switching from policy A to B), direct application of those samples to learn the the optimized policy P generally does not provide an unbiased estimator of the value of P as the samples were observed when constructing P. In situations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02794","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":"1806.02794","created_at":"2026-05-18T00:13:55.634383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02794v1","created_at":"2026-05-18T00:13:55.634383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02794","created_at":"2026-05-18T00:13:55.634383+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7SFMNKJY4IW","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7SFMNKJY4IWIE37","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7SFMNKJ","created_at":"2026-05-18T12:32:22.470017+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/E7SFMNKJY4IWIE37VYIVXMX7EC","json":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC.json","graph_json":"https://pith.science/api/pith-number/E7SFMNKJY4IWIE37VYIVXMX7EC/graph.json","events_json":"https://pith.science/api/pith-number/E7SFMNKJY4IWIE37VYIVXMX7EC/events.json","paper":"https://pith.science/paper/E7SFMNKJ"},"agent_actions":{"view_html":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC","download_json":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC.json","view_paper":"https://pith.science/paper/E7SFMNKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02794&json=true","fetch_graph":"https://pith.science/api/pith-number/E7SFMNKJY4IWIE37VYIVXMX7EC/graph.json","fetch_events":"https://pith.science/api/pith-number/E7SFMNKJY4IWIE37VYIVXMX7EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC/action/storage_attestation","attest_author":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC/action/author_attestation","sign_citation":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC/action/citation_signature","submit_replication":"https://pith.science/pith/E7SFMNKJY4IWIE37VYIVXMX7EC/action/replication_record"}},"created_at":"2026-05-18T00:13:55.634383+00:00","updated_at":"2026-05-18T00:13:55.634383+00:00"}