{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003495364,0.001524701,0.001287334,0.0008654398,0.0008815264,0.0009030444,0.002641384,0.001305287,0.006046774],"category_scores_gemma":[0.008879366,0.0005190131,0.00076532,0.0004690174,0.0008115852,0.001403521,0.003868593,0.00208374,0.001127309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008206798,"about_ca_system_score_gemma":0.001711116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004029226,"about_ca_topic_score_gemma":0.006806278,"domain_scores_codex":[0.9980544,0.0007337182,0.00009418186,0.0003152897,0.0006455557,0.0001568619],"domain_scores_gemma":[0.9969575,0.001371416,0.0002258717,0.0003639541,0.0008766287,0.0002045366],"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":[0.0005055499,0.0005114389,0.001757377,0.0002527329,0.0001706647,0.0001611816,0.0003903123,0.484384,0.007757111,0.01174991,0.009038102,0.4833217],"study_design_scores_gemma":[0.00003022877,0.00008884027,0.0001541852,0.00001140889,0.00001418663,0.00001574951,0.00001869116,0.9928948,0.001698831,0.003842122,0.001221981,0.000008917425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007633956,0.00009299658,0.9864162,0.0001005958,0.00006164962,0.0001408372,0.00005031163,0.003474684,0.002028732],"genre_scores_gemma":[0.3401281,0.00006657244,0.6531715,0.000201275,0.00005074558,0.0005002867,0.0002840371,0.000461523,0.005135815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006046774,"threshold_uncertainty_score":0.02022845,"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."}}