{"id":"W3091146840","doi":"10.30707/ijbe157.1.1648132890.915314","title":"The relationship between classified difficulty and implausible distractors in multiple-choice questions","year":2017,"lang":"en","type":"article","venue":"International journal for business education","topic":"Education and Critical Thinking Development","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Affect (linguistics); Multiple choice; Psychology; Incidence (geometry); Function (biology); Social psychology; Cognitive psychology; Linguistics; Communication; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0008203434,0.00007268334,0.0000717071,0.0000938306,0.003153891,0.001256157,0.0004511734,0.00007041632,0.00001176141],"category_scores_gemma":[0.02233349,0.00005841697,0.00003238724,0.0000759699,0.0002279566,0.0005580299,0.00003082681,0.0001919152,0.000004356878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003198744,"about_ca_system_score_gemma":0.000877357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001457129,"about_ca_topic_score_gemma":0.003663067,"domain_scores_codex":[0.9990368,0.00007249519,0.0002781438,0.0001235412,0.0003213029,0.0001676914],"domain_scores_gemma":[0.996176,0.002543783,0.0002328339,0.0001178266,0.0008237342,0.0001057881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001004694,0.00007059466,0.877519,0.000003548702,0.00001032442,2.142132e-7,0.001429351,0.000001350781,0.00000703972,0.09895393,0.001292931,0.02070169],"study_design_scores_gemma":[0.0002005195,0.000002629663,0.8470601,0.00007312986,0.000006840028,0.000003290553,0.00114136,0.000004941903,0.000002234943,0.04532326,0.1061147,0.00006692461],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8784998,0.00007743314,0.0006746945,0.1129691,0.006396233,0.0002237403,0.00001008794,0.00001562942,0.001133283],"genre_scores_gemma":[0.9957365,0.000125323,0.0004642339,0.0001325943,0.001407566,0.00005180797,0.00003014832,0.000006959748,0.002044818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1172368,"threshold_uncertainty_score":0.9997807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1465211754948774,"score_gpt":0.45764826075006,"score_spread":0.3111270852551826,"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."}}