{"id":"W2274624192","doi":"10.1080/10691898.2015.11889745","title":"Calibrating the Difficulty of an Assessment Tool: The Blooming of a Statistics Examination","year":2015,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Taxonomy (biology); Computer science; Bloom's taxonomy; Mathematics education; Test (biology); Statistics; Machine learning; Artificial intelligence; Cognition; Psychology; Mathematics; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03510248,0.001130809,0.001186875,0.01140677,0.002735357,0.008086781,0.002378178,0.001994285,0.002716786],"category_scores_gemma":[0.1815189,0.000694847,0.00132024,0.005072978,0.002952416,0.006762237,0.00719215,0.002810768,0.001264005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00373268,"about_ca_system_score_gemma":0.005936267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003409872,"about_ca_topic_score_gemma":0.003695758,"domain_scores_codex":[0.9691998,0.01046307,0.004705712,0.002259539,0.01235829,0.001013678],"domain_scores_gemma":[0.8243355,0.09185644,0.01289263,0.01248689,0.05387717,0.004551513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009991801,0.0005599986,0.2992655,0.001730429,0.0002569005,0.0006997746,0.02114368,0.008757399,0.02378637,0.06061696,0.01181589,0.5703679],"study_design_scores_gemma":[0.0001964818,0.00518051,0.4389589,0.003856749,0.0004125441,0.003745133,0.03644164,0.0917721,0.06138292,0.2190216,0.1377412,0.001290261],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4239754,0.001608681,0.5049596,0.003395276,0.0005572274,0.002591858,0.001048357,0.001941744,0.05992179],"genre_scores_gemma":[0.5674097,0.0007430277,0.4246071,0.0003784266,0.00008058096,0.001160966,0.0006484095,0.0002077978,0.004763967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03510248,"threshold_uncertainty_score":0.1856419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1948871322534769,"score_gpt":0.4764581347527667,"score_spread":0.2815710024992898,"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."}}