{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YUO6FERR5QI2YQTIWLUGZVXJI5","short_pith_number":"pith:YUO6FERR","schema_version":"1.0","canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","source":{"kind":"arxiv","id":"1808.00232","version":1},"attestation_state":"computed","paper":{"title":"Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boyi Liu, Jian Peng, Qiang Liu, Yuan Xie, Yuan Zhou, Zhaoran Wang","submitted_at":"2018-08-01T08:56:32Z","abstract_excerpt":"When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems"},"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":"1808.00232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a6a926fb7eceed2d638ca96b6b5ef66378e4b05c2e04ff04c0154cb528d70206","abstract_canon_sha256":"d649ff9c12654cd6dff0aeefdf0bc7645b9313b7b77c89c2ba1438e42a99791d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:08.344523Z","signature_b64":"5zXLHrBfSGO7UzKowEcaXhEhDT+zUllYaGeUkIWuveBW8XILHHYMUoM76RF/EyzB8CgARtmCTuXYHRRqLhujDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","last_reissued_at":"2026-05-18T00:09:08.344042Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:08.344042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boyi Liu, Jian Peng, Qiang Liu, Yuan Xie, Yuan Zhou, Zhaoran Wang","submitted_at":"2018-08-01T08:56:32Z","abstract_excerpt":"When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00232","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":"1808.00232","created_at":"2026-05-18T00:09:08.344106+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00232v1","created_at":"2026-05-18T00:09:08.344106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00232","created_at":"2026-05-18T00:09:08.344106+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUO6FERR5QI2","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUO6FERR5QI2YQTI","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUO6FERR","created_at":"2026-05-18T12:33:04.347982+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/YUO6FERR5QI2YQTIWLUGZVXJI5","json":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5.json","graph_json":"https://pith.science/api/pith-number/YUO6FERR5QI2YQTIWLUGZVXJI5/graph.json","events_json":"https://pith.science/api/pith-number/YUO6FERR5QI2YQTIWLUGZVXJI5/events.json","paper":"https://pith.science/paper/YUO6FERR"},"agent_actions":{"view_html":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5","download_json":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5.json","view_paper":"https://pith.science/paper/YUO6FERR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00232&json=true","fetch_graph":"https://pith.science/api/pith-number/YUO6FERR5QI2YQTIWLUGZVXJI5/graph.json","fetch_events":"https://pith.science/api/pith-number/YUO6FERR5QI2YQTIWLUGZVXJI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/action/storage_attestation","attest_author":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/action/author_attestation","sign_citation":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/action/citation_signature","submit_replication":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/action/replication_record"}},"created_at":"2026-05-18T00:09:08.344106+00:00","updated_at":"2026-05-18T00:09:08.344106+00:00"}