{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01139594,0.001648288,0.002573788,0.001800019,0.001273053,0.004239365,0.002226625,0.003110871,0.00871959],"category_scores_gemma":[0.06378179,0.001092015,0.0008146235,0.001997029,0.00306985,0.004892272,0.003226388,0.004106628,0.001445997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003680587,"about_ca_system_score_gemma":0.002303466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004216645,"about_ca_topic_score_gemma":0.005375932,"domain_scores_codex":[0.9952429,0.002322571,0.0002827422,0.0007991606,0.0007181064,0.0006345247],"domain_scores_gemma":[0.9225532,0.06674058,0.004412398,0.003094138,0.001750058,0.001449574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001107331,0.0001497986,0.003179238,0.0002498149,0.0000927221,0.0001783269,0.000233452,0.7755258,0.0008394341,0.1612481,0.003721463,0.05347449],"study_design_scores_gemma":[0.00005621295,0.0001042207,0.0007606653,0.00007433312,0.00002518794,0.00003225343,0.00002958736,0.8840758,0.0004648236,0.113712,0.0006409551,0.00002396624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2217297,0.003666059,0.754338,0.003989313,0.0003314522,0.0001485084,0.0006195654,0.0009551702,0.01422216],"genre_scores_gemma":[0.9254067,0.001502494,0.04916912,0.0002397167,0.000249314,0.000246369,0.0004472189,0.0002825046,0.02245657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01139594,"threshold_uncertainty_score":0.06026816,"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."}}