{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:E7SFMNKJY4IWIE37VYIVXMX7EC","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":"4d61884b5903af2d4eb4fbdbbde733ca5b1096cfd29457cba9e47dfa5fe1e56d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:12:50Z","title_canon_sha256":"51b73af78aa47c9e941cb18314f5ed3293e47c04be582c2c1f27e127f6d754c0"},"schema_version":"1.0","source":{"id":"1806.02794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02794","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02794v1","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02794","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"E7SFMNKJY4IW","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"E7SFMNKJY4IWIE37","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"E7SFMNKJ","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:36f29e3452ae2f834b46115b8aecf0ecf43c232aa7b410147d90c30992deee92","target":"graph","created_at":"2026-05-18T00:13:55Z","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":"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 ","authors_text":"Elon Portugaly, Joseph J. Pfeiffer III","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:12:50Z","title":"Unbiased Estimation of the Value of an Optimized Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02794","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":"sha256:85dcfc2fe7a0da7832c78347c3d4c34df030e1a1b8fbc328aba4d3088348d61f","target":"record","created_at":"2026-05-18T00:13:55Z","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":"4d61884b5903af2d4eb4fbdbbde733ca5b1096cfd29457cba9e47dfa5fe1e56d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:12:50Z","title_canon_sha256":"51b73af78aa47c9e941cb18314f5ed3293e47c04be582c2c1f27e127f6d754c0"},"schema_version":"1.0","source":{"id":"1806.02794","kind":"arxiv","version":1}},"canonical_sha256":"27e4563549c71164137fae115bb2ff20b3cae8e64cc666c69fb29618e62324d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27e4563549c71164137fae115bb2ff20b3cae8e64cc666c69fb29618e62324d8","first_computed_at":"2026-05-18T00:13:55.634296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:55.634296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VvQdtx3bazQUGmgSRRNsOCPK6bMuezyv8v56MaoGPd3L0lK5Ekg43msDX/DfJ5K6G6qOZze9DaRd4ft8N03tBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:55.634973Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85dcfc2fe7a0da7832c78347c3d4c34df030e1a1b8fbc328aba4d3088348d61f","sha256:36f29e3452ae2f834b46115b8aecf0ecf43c232aa7b410147d90c30992deee92"],"state_sha256":"6c20004693e79d4e23e5229c9974800c39e6e458349b8db354886016bb6f91a4"}