{"id":"W2158712864","doi":"10.5206/cjsotl-rcacea.2011.2.4","title":"Examination of the Quality of Multiple-choice Items on Classroom Tests","year":2011,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Multiple choice; Psychology; Selection (genetic algorithm); Quality (philosophy); Test (biology); Social psychology; Statistical analysis; Statistics; Significant difference; Mathematics; Computer science; Biology; Artificial intelligence; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04849466,0.00008185893,0.0001455423,0.0001012944,0.004991377,0.0001037168,0.0006601373,0.00007980943,0.00002856286],"category_scores_gemma":[0.09836846,0.00004614037,0.0001131481,0.0001148674,0.0004026341,0.0003462486,0.00002097795,0.002111376,6.576758e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009594596,"about_ca_system_score_gemma":0.0003914585,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1073831,"about_ca_topic_score_gemma":0.1443451,"domain_scores_codex":[0.9910782,0.007746034,0.0003738338,0.0000950051,0.0005024025,0.0002045488],"domain_scores_gemma":[0.9871651,0.01123171,0.001036259,0.0002017718,0.0002448741,0.0001202739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007027935,0.00004451288,0.6635009,0.00004745121,0.0001312481,2.661274e-7,0.2057923,0.001197668,0.001052863,0.04094853,0.0000761574,0.08713785],"study_design_scores_gemma":[0.000288305,0.0001111568,0.9705538,0.0001827701,0.00006841606,0.000003322104,0.01718001,0.0001775415,0.0001361647,0.002238932,0.008982045,0.00007760509],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906896,0.0002542544,0.00007288946,0.003667284,0.000354373,0.0002152651,0.000003812445,0.000006360874,0.004736197],"genre_scores_gemma":[0.9983848,0.000009344221,0.0003281744,0.00008542017,0.0001198571,0.0000025945,4.01313e-7,0.000009961051,0.001059487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3070529,"threshold_uncertainty_score":0.996304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3066813021309989,"score_gpt":0.440101905591797,"score_spread":0.133420603460798,"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."}}