{"id":"W3205427743","doi":"","title":"MASAI: Multi-agent Summative Assessment Improvement for Unsupervised Environment Design","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Summative assessment; Computer science; Formative assessment; Psychology; Mathematics education","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":[0.0005755951,0.0002734027,0.0002255115,0.0001335926,0.0002568379,0.0004320809,0.0009005707,0.0000682838,0.000602897],"category_scores_gemma":[0.0002053327,0.0002695992,0.0001276826,0.00009802659,0.00003520135,0.0002934088,0.0004338417,0.0004726638,0.0001161484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003657406,"about_ca_system_score_gemma":0.0001696115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001624952,"about_ca_topic_score_gemma":0.000002466276,"domain_scores_codex":[0.9976009,0.0002299398,0.0004335707,0.0006445195,0.000739989,0.0003510861],"domain_scores_gemma":[0.9986582,0.0002886009,0.0002615919,0.0003960329,0.0002822224,0.0001133889],"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":[0.0000251297,0.0001649815,0.00115464,0.00001655596,0.0001570711,0.00002819704,0.0004609342,0.877563,0.01138355,0.08721632,0.0000757185,0.02175393],"study_design_scores_gemma":[0.001303363,0.0004540687,0.001146212,0.00005556077,0.00001140627,0.000004409866,0.0001343084,0.9841159,0.004897569,0.0006184634,0.006973761,0.0002849674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006269036,0.00002399945,0.9919725,0.003106141,0.0005740955,0.0004634531,0.000008102868,0.0001257898,0.003099005],"genre_scores_gemma":[0.6086093,0.000107414,0.3835815,0.0005600161,0.00007065202,0.0001653397,0.000143234,0.00002557198,0.006737045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.608391,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09432305776176142,"score_gpt":0.3331575425502579,"score_spread":0.2388344847884965,"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."}}