{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ER3GS33FQ63I47UCOKVOEWWOUK","short_pith_number":"pith:ER3GS33F","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"},"canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","source":{"kind":"arxiv","id":"2303.11187","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11187","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11187v1","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11187","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"ER3GS33FQ63I","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_16","alias_value":"ER3GS33FQ63I47UC","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_8","alias_value":"ER3GS33F","created_at":"2026-07-05T05:52:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ER3GS33FQ63I47UCOKVOEWWOUK","target":"record","payload":{"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"},"canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","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"},"source_kind":"arxiv","source_id":"2303.11187","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsTQd1lBEddibbj0/2a0Jd8yhm+np9hfUCaMUjt4nTqovN+D5oNr4S9c4M5Vo64q8z7UGYjK3CSTK0fmFQuTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:18.568031Z"},"content_sha256":"84d5a1bb8fcb460fb426d15c1cce4455d40863aab558926ff97413e94106fed4","schema_version":"1.0","event_id":"sha256:84d5a1bb8fcb460fb426d15c1cce4455d40863aab558926ff97413e94106fed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ER3GS33FQ63I47UCOKVOEWWOUK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BA1mnSAYIs203hNpC7EZylq0TNZcz7KjtpjaHcWL4JznkFR3ePEOAGk+i522xL18qAuUQbhH+dpGX5TlTHJ7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:18.568982Z"},"content_sha256":"20004cc60e6cd954a093f8975ad293f61430ff48235aeb10d51c5a2df67dec92","schema_version":"1.0","event_id":"sha256:20004cc60e6cd954a093f8975ad293f61430ff48235aeb10d51c5a2df67dec92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/bundle.json","state_url":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ER3GS33FQ63I47UCOKVOEWWOUK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T20:26:18Z","links":{"resolver":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK","bundle":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/bundle.json","state":"https://pith.science/pith/ER3GS33FQ63I47UCOKVOEWWOUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ER3GS33FQ63I47UCOKVOEWWOUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ER3GS33FQ63I47UCOKVOEWWOUK","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":"22599d3b24234d2766f8e85ebd70c765286fcf0952dd38e1e1b1e67dcfdbad28","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T15:17:31Z","title_canon_sha256":"7b53b0fda7561063e19fe801fd62bc2420f8dd5b0cf72dcefe8998b281cbfc92"},"schema_version":"1.0","source":{"id":"2303.11187","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11187","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11187v1","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11187","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"ER3GS33FQ63I","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_16","alias_value":"ER3GS33FQ63I47UC","created_at":"2026-07-05T05:52:41Z"},{"alias_kind":"pith_short_8","alias_value":"ER3GS33F","created_at":"2026-07-05T05:52:41Z"}],"graph_snapshots":[{"event_id":"sha256:20004cc60e6cd954a093f8975ad293f61430ff48235aeb10d51c5a2df67dec92","target":"graph","created_at":"2026-07-05T05:52:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.11187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T15:17:31Z","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11187","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":"sha256:84d5a1bb8fcb460fb426d15c1cce4455d40863aab558926ff97413e94106fed4","target":"record","created_at":"2026-07-05T05:52:41Z","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":"22599d3b24234d2766f8e85ebd70c765286fcf0952dd38e1e1b1e67dcfdbad28","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T15:17:31Z","title_canon_sha256":"7b53b0fda7561063e19fe801fd62bc2420f8dd5b0cf72dcefe8998b281cbfc92"},"schema_version":"1.0","source":{"id":"2303.11187","kind":"arxiv","version":1}},"canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2476696f6587b68e7e8272aae25acea288bb98f6b01969376eedec31a5aed4b8","first_computed_at":"2026-07-05T05:52:41.339398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:41.339398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVYtF/03kukfo9rCwIe9ooTd48OFCjTGcz1Jmbv1wO4sj+5tFyeuh7c0LGUgNPqMNlshh6HnoN1dFtbzu02hBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:41.339800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11187","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84d5a1bb8fcb460fb426d15c1cce4455d40863aab558926ff97413e94106fed4","sha256:20004cc60e6cd954a093f8975ad293f61430ff48235aeb10d51c5a2df67dec92"],"state_sha256":"b199d1b5360643af7f08a6618383901900e1d698db714f6a46683c3a221e9d25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxwdHAYUanzxi+lYnve7cKmQj8fTEf25KG8d6y56IRIYQSNCORc5hpBABYuVphUxJ4izdXSbT3F35VXZLWeeCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:26:18.574120Z","bundle_sha256":"7d912f40795daf1deee6aa59360104ddf7cbea7d3822593a69bcebb2b00206cd"}}