{"id":"W2970245835","doi":"","title":"Learning Reliable Policies in the Bandit Setting with Application to Adaptive Clinical Trials.","year":2019,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01792103,0.0002182958,0.0005059207,0.0005925326,0.0001499768,0.0006279714,0.001637517,0.0001038251,0.0008858098],"category_scores_gemma":[0.01399921,0.0001314567,0.0001458342,0.001029967,0.00019224,0.0003706022,0.0002019961,0.000906333,0.004686829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001377587,"about_ca_system_score_gemma":0.0002203892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002377277,"about_ca_topic_score_gemma":0.0003479225,"domain_scores_codex":[0.9930583,0.001247286,0.001843697,0.0008766131,0.00256191,0.0004121953],"domain_scores_gemma":[0.9908229,0.006625291,0.000623313,0.0006279367,0.001166019,0.0001345423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001174817,0.0002853914,0.00623862,0.000002475461,0.00003607382,0.00002140651,0.003087064,0.1453323,0.001109455,0.1468199,0.0004794746,0.6954131],"study_design_scores_gemma":[0.0002860669,0.002208359,0.01778691,0.0002633946,0.00001031044,0.00002181135,0.02809401,0.7145491,0.008568477,0.2142298,0.01338141,0.0006003323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.164951,0.000009589048,0.795641,0.01959862,0.0009166377,0.001830574,0.00002467011,0.00006491925,0.01696297],"genre_scores_gemma":[0.9956114,0.00001867661,0.002068752,0.0007399248,0.0003306181,0.0001282749,0.000008879069,0.00001495454,0.001078508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8306604,"threshold_uncertainty_score":0.9960881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4440932873400193,"score_gpt":0.5419922742734516,"score_spread":0.0978989869334323,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}