{"id":"W3166958512","doi":"10.3758/s13428-021-01602-9","title":"Building an intelligent recommendation system for personalized test scheduling in computerized assessments: A reinforcement learning approach","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Pace; Computer science; Test (biology); Scheduling (production processes); Reinforcement learning; Machine learning; Mathematics education; Psychology; Engineering; Operations management","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":[0.00217754,0.0008142604,0.001365111,0.001335224,0.0005943567,0.001104692,0.002168379,0.001316612,0.002502658],"category_scores_gemma":[0.00722672,0.0006169715,0.0006135534,0.000682594,0.0003113306,0.001340871,0.0006445872,0.0013047,0.001322197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105329,"about_ca_system_score_gemma":0.001551555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01841088,"about_ca_topic_score_gemma":0.01996836,"domain_scores_codex":[0.9988502,0.0003315643,0.0001118358,0.0003394829,0.0002708179,0.00009609603],"domain_scores_gemma":[0.9962065,0.001649942,0.0002587133,0.0003983351,0.001262006,0.0002243367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008160949,0.002255848,0.02040615,0.0001730612,0.0003525894,0.0004131515,0.0003013519,0.1876486,0.02219383,0.002390473,0.009914628,0.7531343],"study_design_scores_gemma":[0.0000351153,0.00005462541,0.0009489658,0.000004897064,0.0000351072,0.00003527056,0.0000162823,0.9945984,0.003264574,0.0004972854,0.0004937414,0.00001569447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06510037,0.0001330589,0.9180284,0.000363091,0.0000722906,0.0004770686,0.0002058881,0.0139527,0.001667157],"genre_scores_gemma":[0.574775,0.00008438362,0.4218166,0.0001779099,0.00004076145,0.0003186413,0.000385037,0.0002049061,0.00219669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01841088,"threshold_uncertainty_score":0.03660744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3273825167922156,"score_gpt":0.5494179913574728,"score_spread":0.2220354745652572,"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."}}