{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0167433,0.0002638387,0.0004926869,0.0005751604,0.0006368817,0.0008735781,0.0008323321,0.0001458406,0.00002061817],"category_scores_gemma":[0.001113127,0.0002718286,0.0001609736,0.001144945,0.00005103762,0.0007180818,0.0006046314,0.001005369,0.00000594502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009789624,"about_ca_system_score_gemma":0.0003352574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001473651,"about_ca_topic_score_gemma":0.000002568251,"domain_scores_codex":[0.9921859,0.004311707,0.0007955051,0.001045103,0.00075384,0.0009079316],"domain_scores_gemma":[0.9964983,0.001557561,0.0002200302,0.0005488929,0.0009496755,0.0002255654],"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":[0.00006717617,0.0007530221,0.003194235,0.0005482095,0.00005319062,0.00008443303,0.003057117,0.03287255,0.1568952,0.3114054,0.000009705252,0.4910598],"study_design_scores_gemma":[0.001052483,0.0005195944,0.0003793869,0.0004683323,0.00001297279,0.00006258443,0.005402162,0.9357188,0.03133292,0.0001040404,0.02453806,0.0004086476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01999917,0.00009618171,0.9775982,0.00007295905,0.0004887538,0.001151718,0.000001470478,0.0001966519,0.0003948188],"genre_scores_gemma":[0.1367025,0.00001363764,0.8605668,0.00001340604,0.000163768,0.0008780063,0.00004540803,0.00003764549,0.001578805],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9028463,"threshold_uncertainty_score":0.9999734,"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."}}