{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008508743,0.0001292842,0.0001218302,0.0001396016,0.0008392051,0.0002954292,0.00009743479,0.00007144999,0.00008419948],"category_scores_gemma":[0.002946589,0.0001310571,0.00003891409,0.0001711927,0.00002754486,0.00009836914,0.00004153162,0.0006052559,0.00004266129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001851932,"about_ca_system_score_gemma":0.0002345474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001394472,"about_ca_topic_score_gemma":0.0004226413,"domain_scores_codex":[0.9988123,0.0001660068,0.0001425024,0.0003251265,0.0002600505,0.0002940242],"domain_scores_gemma":[0.9967081,0.002964106,0.00003046127,0.00007770758,0.00003821812,0.0001814057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008565,0.001024351,0.3642799,0.0003892462,0.0004170374,0.00009525103,0.2375101,0.01180729,0.03052467,0.184576,0.02170468,0.1475858],"study_design_scores_gemma":[0.0003694,0.0002683675,0.01915502,0.0004856817,0.00005458845,0.00000288058,0.01101012,0.01755881,0.00009142607,0.0001898164,0.9503529,0.0004610066],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.938921,0.0002374727,0.001061252,0.007260359,0.001147402,0.0004574494,0.000007694287,0.0006118875,0.05029546],"genre_scores_gemma":[0.9801508,0.00002562233,0.0007037529,0.0001258139,0.0004968215,0.00004968348,0.000006305019,0.00002069908,0.01842047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9286482,"threshold_uncertainty_score":0.6454572,"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."}}