{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ER3GS33FQ63I47UCOKVOEWWOUK","short_pith_number":"pith:ER3GS33F","schema_version":"1.0","canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","source":{"kind":"arxiv","id":"2303.11187","version":1},"attestation_state":"computed","paper":{"title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang","submitted_at":"2023-03-20T15:17:31Z","abstract_excerpt":"We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii) missing observations exist in the collected data. Unobserved confounders lead to a confounding bias and missing observations cause bias and inefficiency problems. To overcome these challenges and learn the optimal policy from the observed dataset, we present a new algorithm called Causal-Adjusted Pessimistic (CAP) policy learning, which forms the reward functi"},"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":"2303.11187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T15:17:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7b53b0fda7561063e19fe801fd62bc2420f8dd5b0cf72dcefe8998b281cbfc92","abstract_canon_sha256":"22599d3b24234d2766f8e85ebd70c765286fcf0952dd38e1e1b1e67dcfdbad28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:41.339800Z","signature_b64":"fVYtF/03kukfo9rCwIe9ooTd48OFCjTGcz1Jmbv1wO4sj+5tFyeuh7c0LGUgNPqMNlshh6HnoN1dFtbzu02hBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","last_reissued_at":"2026-07-05T05:52:41.339398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:41.339398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang","submitted_at":"2023-03-20T15:17:31Z","abstract_excerpt":"We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii) missing observations exist in the collected data. Unobserved confounders lead to a confounding bias and missing observations cause bias and inefficiency problems. To overcome these challenges and learn the optimal policy from the observed dataset, we present a new algorithm called Causal-Adjusted Pessimistic (CAP) policy learning, which forms the reward functi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11187","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.11187/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2303.11187","created_at":"2026-07-05T05:52:41.339458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11187v1","created_at":"2026-07-05T05:52:41.339458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11187","created_at":"2026-07-05T05:52:41.339458+00:00"},{"alias_kind":"pith_short_12","alias_value":"ER3GS33FQ63I","created_at":"2026-07-05T05:52:41.339458+00:00"},{"alias_kind":"pith_short_16","alias_value":"ER3GS33FQ63I47UC","created_at":"2026-07-05T05:52:41.339458+00:00"},{"alias_kind":"pith_short_8","alias_value":"ER3GS33F","created_at":"2026-07-05T05:52:41.339458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07140","citing_title":"Quantile-Optimal Policy Learning under Unmeasured Confounding","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK","json":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK.json","graph_json":"https://pith.science/api/pith-number/ER3GS33FQ63I47UCOKVOEWWOUK/graph.json","events_json":"https://pith.science/api/pith-number/ER3GS33FQ63I47UCOKVOEWWOUK/events.json","paper":"https://pith.science/paper/ER3GS33F"},"agent_actions":{"view_html":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK","download_json":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK.json","view_paper":"https://pith.science/paper/ER3GS33F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11187&json=true","fetch_graph":"https://pith.science/api/pith-number/ER3GS33FQ63I47UCOKVOEWWOUK/graph.json","fetch_events":"https://pith.science/api/pith-number/ER3GS33FQ63I47UCOKVOEWWOUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/action/storage_attestation","attest_author":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/action/author_attestation","sign_citation":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/action/citation_signature","submit_replication":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/action/replication_record"}},"created_at":"2026-07-05T05:52:41.339458+00:00","updated_at":"2026-07-05T05:52:41.339458+00:00"}