{"id":"W4393952200","doi":"10.22329/celt.v15i1.7856","title":"Reverse Engineering a Multiple-Choice Test Blueprint to Improve Course Alignment","year":2024,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Blueprint; Course (navigation); Test (biology); Mathematics education; Teaching method; Computer science; Course evaluation; Higher education; Management science; Engineering management; Engineering; Psychology; Mechanical engineering; Political science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.03975195,0.001225735,0.0008979611,0.005583451,0.001195348,0.003163011,0.002075578,0.00141073,0.01099652],"category_scores_gemma":[0.196665,0.0005322754,0.0008930904,0.003737747,0.001209902,0.003887393,0.003010209,0.002188209,0.004962299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808377,"about_ca_system_score_gemma":0.003611424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001191685,"about_ca_topic_score_gemma":0.0031058,"domain_scores_codex":[0.9636253,0.02076703,0.005531956,0.002282785,0.007159507,0.0006334744],"domain_scores_gemma":[0.7857347,0.1189056,0.008718815,0.01824631,0.06660001,0.0017946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006415167,0.001361268,0.01936957,0.001207705,0.00006889016,0.0003302864,0.006849168,0.003470304,0.02260597,0.0184436,0.03506333,0.8905883],"study_design_scores_gemma":[0.001065249,0.00752561,0.1316756,0.002662741,0.0002310525,0.002629547,0.01456631,0.1572208,0.1212301,0.09398092,0.4663725,0.0008396061],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1022514,0.000294516,0.8438669,0.002487448,0.00110866,0.01982095,0.001953147,0.005958945,0.022258],"genre_scores_gemma":[0.07777002,0.0000996128,0.9046267,0.0004509875,0.0000773681,0.01033545,0.0007932503,0.0004844752,0.005362102],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03975195,"threshold_uncertainty_score":0.210231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01599086976319733,"score_gpt":0.3443438390988004,"score_spread":0.3283529693356031,"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."}}