{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01498115,0.00009400176,0.0002754567,0.00116532,0.00005146527,0.00007633074,0.0005590285,0.00006554406,0.0004576826],"category_scores_gemma":[0.07021046,0.00005482994,0.00002809183,0.004486549,0.0000826951,0.0001712362,0.0001649968,0.0001590193,0.00002052716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009468169,"about_ca_system_score_gemma":0.000153315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001770789,"about_ca_topic_score_gemma":0.00008117689,"domain_scores_codex":[0.9959951,0.001020776,0.001028884,0.0006006953,0.0009732498,0.0003812971],"domain_scores_gemma":[0.9086093,0.08995135,0.0002030901,0.0007486544,0.0004093647,0.00007825415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000149847,0.0003560311,0.2589294,0.0000065674,0.000002225028,0.000005341642,0.0003376983,0.0004498616,0.01741533,0.001128245,0.008074255,0.7131452],"study_design_scores_gemma":[0.002492555,0.0006942733,0.8904154,0.0004002338,0.000001034399,0.00000148256,0.001931105,0.002872544,0.08510581,0.01444817,0.00143092,0.0002064583],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770925,0.00009481504,0.005464356,0.009930975,0.0005879939,0.0001754776,0.000001317497,0.00002488663,0.006627658],"genre_scores_gemma":[0.8845589,0.000001232657,0.1143568,0.0001828847,0.0001655726,0.00001855064,1.972939e-7,0.000004933737,0.0007108787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7129388,"threshold_uncertainty_score":0.9376215,"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."}}