{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PRMHRQDJGFLWNLMFIOMNBMTLVC","short_pith_number":"pith:PRMHRQDJ","schema_version":"1.0","canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","source":{"kind":"arxiv","id":"1809.03084","version":3},"attestation_state":"computed","paper":{"title":"Efficient Counterfactual Learning from Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kohei Yata, Shota Yasui, Yusuke Narita","submitted_at":"2018-09-10T02:08:14Z","abstract_excerpt":"What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in a wide class of estimators, achieving variance reduction relative to standard estimators. We then apply our estimators to improve advertisement design by a major advertisement company. Consistent with the theoretical result, our estimators allow us to improve on the existing ban"},"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":"1809.03084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ME","stat.ML"],"title_canon_sha256":"0c4a6b9675fc6918b02cfd037ed966196569c0003b0163bf772e314f2d008529","abstract_canon_sha256":"2fe7af45a6cdefba26d3752803ab34ae98b26d6913b3042bace2b0380a603fa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:57.111297Z","signature_b64":"ZYh0Hoqs+nwQbpAOVBkUqV2SH5JkDm2qioRsaHmDWZvg6XTa95l8oeu/Hc1YdfY1w5GLXlGRskX8Pf+q6nI5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","last_reissued_at":"2026-05-17T23:58:57.110864Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:57.110864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Counterfactual Learning from Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kohei Yata, Shota Yasui, Yusuke Narita","submitted_at":"2018-09-10T02:08:14Z","abstract_excerpt":"What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in a wide class of estimators, achieving variance reduction relative to standard estimators. We then apply our estimators to improve advertisement design by a major advertisement company. Consistent with the theoretical result, our estimators allow us to improve on the existing ban"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03084","kind":"arxiv","version":3},"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":"1809.03084","created_at":"2026-05-17T23:58:57.110930+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03084v3","created_at":"2026-05-17T23:58:57.110930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03084","created_at":"2026-05-17T23:58:57.110930+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRMHRQDJGFLW","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRMHRQDJGFLWNLMF","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRMHRQDJ","created_at":"2026-05-18T12:32:46.962924+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/PRMHRQDJGFLWNLMFIOMNBMTLVC","json":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC.json","graph_json":"https://pith.science/api/pith-number/PRMHRQDJGFLWNLMFIOMNBMTLVC/graph.json","events_json":"https://pith.science/api/pith-number/PRMHRQDJGFLWNLMFIOMNBMTLVC/events.json","paper":"https://pith.science/paper/PRMHRQDJ"},"agent_actions":{"view_html":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC","download_json":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC.json","view_paper":"https://pith.science/paper/PRMHRQDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03084&json=true","fetch_graph":"https://pith.science/api/pith-number/PRMHRQDJGFLWNLMFIOMNBMTLVC/graph.json","fetch_events":"https://pith.science/api/pith-number/PRMHRQDJGFLWNLMFIOMNBMTLVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/action/storage_attestation","attest_author":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/action/author_attestation","sign_citation":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/action/citation_signature","submit_replication":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/action/replication_record"}},"created_at":"2026-05-17T23:58:57.110930+00:00","updated_at":"2026-05-17T23:58:57.110930+00:00"}