{"id":"W6968595109","doi":"10.5281/zenodo.3554750","title":"Statistical Consequences of using Multi-armed Bandits to Conduct Adaptive Educational Experiments","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Key (lock); Statistical power; Randomized experiment; Design of experiments; Statistical hypothesis testing; Statistical analysis","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001599358,0.0001478962,0.0002725586,0.0005149897,0.0007816284,0.0004613457,0.001467096,0.00005465814,0.04440981],"category_scores_gemma":[0.005763982,0.0001317866,0.00004824425,0.001082783,0.0004803362,0.0004340929,0.001064317,0.000210905,0.01214629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002175542,"about_ca_system_score_gemma":0.0000425738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003173538,"about_ca_topic_score_gemma":3.151032e-7,"domain_scores_codex":[0.9961064,0.0006663897,0.0005233326,0.0006464984,0.001639628,0.0004176855],"domain_scores_gemma":[0.9965966,0.0004618858,0.0001926468,0.0005485708,0.001892124,0.0003082253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001631777,0.002097306,0.0009669947,0.0001202718,0.0003352811,0.00006259904,0.01433507,0.01081387,0.6333885,0.04753217,0.1354626,0.1532536],"study_design_scores_gemma":[0.005115182,0.002339801,0.02068908,0.0002141923,0.00003422887,0.0003367284,0.01406615,0.03114451,0.08258038,0.01171952,0.8304108,0.001349445],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4966344,0.000171169,0.4721998,0.001470505,0.0007857726,0.002647946,0.001721312,0.0002782169,0.02409089],"genre_scores_gemma":[0.9794933,0.000005328907,0.01833523,0.00006559668,0.00006676427,1.090864e-7,0.0001956338,0.000353702,0.001484366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6949482,"threshold_uncertainty_score":0.9886228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3190968909175737,"score_gpt":0.4519885797029352,"score_spread":0.1328916887853615,"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."}}