{"id":"W2596780180","doi":"10.5206/cjsotl-rcacea.2017.1.11","title":"Does Correct Answer Distribution Influence Student Choices When Writing Multiple Choice Examinations?","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"McMaster University; University of Ottawa","keywords":"Summative assessment; Multiple choice; Cheating; Mathematics education; Selection (genetic algorithm); Computer science; Psychology; Formative assessment; Mathematics; Statistics; Social psychology; Artificial intelligence; Significant difference","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01307955,0.0003085236,0.0005610564,0.001253659,0.0004972704,0.002371555,0.0006474208,0.000841772,0.003373382],"category_scores_gemma":[0.1262549,0.0003147901,0.0005756014,0.001003915,0.0008145156,0.001657013,0.001161638,0.000829407,0.00148327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005281133,"about_ca_system_score_gemma":0.00072973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001836715,"about_ca_topic_score_gemma":0.002459841,"domain_scores_codex":[0.9809775,0.009505193,0.001637054,0.001821233,0.005206502,0.0008526342],"domain_scores_gemma":[0.8195949,0.1166748,0.04055101,0.005922636,0.01103215,0.00622449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007725682,0.0006003289,0.9438437,0.00007580929,0.0001217274,0.0001215606,0.003730898,0.0003796271,0.002562118,0.0001372454,0.0003412338,0.04731313],"study_design_scores_gemma":[0.00003682432,0.001183535,0.9901068,0.00005509112,0.0000540471,0.0001781673,0.003251907,0.001276177,0.002427933,0.0004131811,0.0009708723,0.00004546234],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965361,0.0001644286,0.001170523,0.0003131321,0.00001628897,0.00002693303,0.00005428587,0.00002410978,0.001694099],"genre_scores_gemma":[0.9988005,0.00008176629,0.0005039409,0.00006040763,0.0000133357,0.00001699155,0.00004574298,0.00001631022,0.000460946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01307955,"threshold_uncertainty_score":0.06917214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06562502054918723,"score_gpt":0.4119930685369743,"score_spread":0.346368047987787,"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."}}