{"id":"W7096040788","doi":"","title":"RESEARCH ARTICLE Introducing Computer-Based Testing in High- Stakes Exams in Higher Education: Results of a Field Experiment","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Quarter (Canadian coin); Sample (material); Sample size determination; Student achievement; Research design; Higher education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0165484,0.0009975591,0.0007861489,0.0006786337,0.001019316,0.001536996,0.001349358,0.00150047,0.005916476],"category_scores_gemma":[0.03069153,0.000644175,0.0007245119,0.0003793686,0.001097328,0.00171531,0.0007615011,0.001942868,0.0009227431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005351711,"about_ca_system_score_gemma":0.001426462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001283062,"about_ca_topic_score_gemma":0.001234756,"domain_scores_codex":[0.9925085,0.004707686,0.0005955999,0.0006937814,0.0009043482,0.0005901887],"domain_scores_gemma":[0.9268747,0.05921539,0.003162945,0.003940331,0.002654393,0.00415232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.05438296,0.6822877,0.06392827,0.001245075,0.000269099,0.0007974989,0.01875627,0.002116761,0.05759483,0.001104332,0.001974378,0.1155427],"study_design_scores_gemma":[0.01226371,0.7838295,0.145832,0.0002808512,0.0003502876,0.0004132291,0.008571044,0.005663502,0.03457804,0.00129462,0.006676345,0.0002469056],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979049,0.00001999086,0.0004993124,0.00004855956,0.00002716794,0.0006663883,0.00004099077,0.00002041479,0.0007722426],"genre_scores_gemma":[0.988188,0.0001127766,0.005561149,0.0003019316,0.0000687494,0.001490795,0.000157776,0.00002041848,0.0040984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0165484,"threshold_uncertainty_score":0.08751732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7312558407360974,"score_gpt":0.5363079835911067,"score_spread":0.1949478571449907,"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."}}