{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01003803,0.00007732918,0.0000930668,0.00004445949,0.02819376,0.001692083,0.0006770862,0.00005289022,0.00002842194],"category_scores_gemma":[0.01395405,0.00004225763,0.00005581221,0.00002693434,0.0003350685,0.0007006975,0.000024514,0.001369992,9.831167e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344229,"about_ca_system_score_gemma":0.0004729149,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1383359,"about_ca_topic_score_gemma":0.3683629,"domain_scores_codex":[0.9983288,0.00086836,0.0001777209,0.0001025118,0.0002527171,0.0002698917],"domain_scores_gemma":[0.9957756,0.003338406,0.0003539696,0.0001433488,0.0002110247,0.0001776371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003410785,0.000005657341,0.9539603,0.000005721638,0.00002869648,3.578963e-7,0.02066138,0.0001848299,0.00002786404,0.003601096,0.0000737363,0.02144693],"study_design_scores_gemma":[0.0001424344,0.00002287271,0.8626196,0.00009253358,0.00003600709,0.000003207703,0.01970758,0.00008038271,0.000005156693,0.001474783,0.1157407,0.00007468052],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869995,0.0003026697,0.0001294596,0.01078013,0.000768354,0.0001641007,0.000009989623,0.00000768464,0.0008380902],"genre_scores_gemma":[0.9960612,0.00002835045,0.0001087477,0.00009216346,0.0007360155,0.000009002183,0.000005505703,0.000006834889,0.002952167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.230027,"threshold_uncertainty_score":0.9993442,"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."}}