{"id":"W4416363396","doi":"10.1080/0047231x.2025.2576707","title":"Can a Small Change in Exam Question Format Help Students? Sadly, Not","year":2025,"lang":"en","type":"article","venue":"Journal of College Science Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Field (mathematics); Set (abstract data type); Feature (linguistics); Frequently asked questions","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":[],"consensus_categories":[],"category_scores_codex":[0.01228004,0.0001126184,0.0002500681,0.0008734784,0.001043108,0.0003674012,0.001265706,0.00006236548,0.00001994566],"category_scores_gemma":[0.0005455204,0.00009897736,0.0000830021,0.001302241,0.0003026331,0.001379467,0.0001817913,0.0004987028,0.000002955711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008677654,"about_ca_system_score_gemma":0.0007977225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001537268,"about_ca_topic_score_gemma":0.006187206,"domain_scores_codex":[0.9971356,0.0003419683,0.0004895494,0.0001723348,0.001402531,0.0004580006],"domain_scores_gemma":[0.999077,0.0001415865,0.0003242719,0.0001170104,0.0001961226,0.0001440733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008653326,0.0005044329,0.68319,0.00002286536,0.00002938072,0.00007384965,0.09259079,0.00002049601,0.002174478,0.1893001,0.0008206972,0.03118629],"study_design_scores_gemma":[0.001419194,0.0001922516,0.9175141,0.0006246895,0.00003425315,0.000008916876,0.07063901,0.0002553725,0.0001380375,0.001823109,0.007105868,0.0002452002],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720218,0.0001098933,0.0001542544,0.005972691,0.001376355,0.0003170887,0.000001663753,0.00001846553,0.02002778],"genre_scores_gemma":[0.9969568,0.0001197742,0.0009739269,0.0005927451,0.0003102502,0.000007734408,1.446083e-7,0.000004113681,0.001034574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.234324,"threshold_uncertainty_score":0.802285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04610037157081655,"score_gpt":0.4123545222884498,"score_spread":0.3662541507176333,"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."}}