{"id":"W4407681617","doi":"10.1145/3641555.3705092","title":"Experiences with Computer-Based Testing (CBT)","year":2025,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0001475044,0.00009420434,0.0001023323,0.00008677427,0.0001702667,0.0002157388,0.0004421635,0.00002096398,0.00000856012],"category_scores_gemma":[0.00002029689,0.00006566577,0.00002151607,0.0004665862,0.00002531392,0.0001679807,0.0000790443,0.00007588557,0.00001877561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002472433,"about_ca_system_score_gemma":0.00009965698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008799146,"about_ca_topic_score_gemma":0.00000332051,"domain_scores_codex":[0.9992208,0.00003405839,0.0001301593,0.0002793312,0.0001478142,0.000187857],"domain_scores_gemma":[0.9994157,0.0001697847,0.0000438963,0.000239338,0.00009973521,0.00003156731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008699617,0.00009942835,0.02751198,0.00006622633,0.00003648933,0.00006353782,0.005728832,0.01844348,0.0004968091,0.8503328,0.0009022562,0.09630948],"study_design_scores_gemma":[0.0004024432,0.000482193,0.003469498,0.000588145,0.00000442175,0.00001269994,0.002669801,0.933768,0.01621214,0.0001625673,0.04178883,0.0004392474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0431522,0.00002026517,0.9396873,0.0001750612,0.0003282999,0.0000713497,2.9225e-8,0.0002909115,0.01627462],"genre_scores_gemma":[0.799809,3.921506e-8,0.1947597,0.0003456721,0.00004753528,0.00001704708,1.06747e-7,0.000002629387,0.005018252],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153245,"threshold_uncertainty_score":0.2677772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02372857991071591,"score_gpt":0.2469192499318323,"score_spread":0.2231906700211163,"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."}}