{"id":"W2611974834","doi":"","title":"Rewards and errors in multi-arm bandits for interactive education","year":2016,"lang":"en","type":"preprint","venue":"LillOA (Université de Lille (University Of Lille))","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Maximization; Utility maximization; Estimation; Artificial intelligence; Machine learning; Mathematical optimization; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013489,0.000436053,0.0009542367,0.002187635,0.0005230444,0.00006614005,0.001867004,0.0006544993,0.0006676796],"category_scores_gemma":[0.001003106,0.0004653283,0.0004050045,0.0008270225,0.0005967364,0.0009130174,0.003471129,0.0006954896,0.0000554303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001661457,"about_ca_system_score_gemma":0.0009759205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000824808,"about_ca_topic_score_gemma":0.002265452,"domain_scores_codex":[0.9960415,0.0003558577,0.0004268634,0.001451802,0.001055778,0.0006681589],"domain_scores_gemma":[0.9952641,0.001490233,0.0008569869,0.001013497,0.000967725,0.0004075133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01307561,0.004372185,0.03978112,0.001488938,0.00168402,0.0008609564,0.1605854,0.004667657,0.004144285,0.008636041,0.08097049,0.6797333],"study_design_scores_gemma":[0.0257941,0.001903399,0.1665791,0.003244466,0.0005383415,0.0001655308,0.2703954,0.06190445,0.001909612,0.1709327,0.2917942,0.004838779],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.716697,0.001665856,0.2434159,0.01028691,0.002361648,0.003985689,0.00181516,0.0001936062,0.01957827],"genre_scores_gemma":[0.8896959,0.001157803,0.03112953,0.00009438111,0.0001487935,0.000008088464,0.0001139381,0.00007461512,0.07757697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6748945,"threshold_uncertainty_score":0.9997798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07773655344355909,"score_gpt":0.3737362547816234,"score_spread":0.2959997013380643,"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."}}