{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004115537,0.0001417982,0.000329681,0.0001276152,0.0001091822,0.00006169231,0.0003426806,0.00005666216,0.00003656299],"category_scores_gemma":[0.01278865,0.00008536291,0.00004358197,0.0002200858,0.0001870174,0.0001612085,0.00003708181,0.0002626671,6.644945e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001294481,"about_ca_system_score_gemma":0.001681513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004636003,"about_ca_topic_score_gemma":0.00002453212,"domain_scores_codex":[0.9969844,0.0008870491,0.001181647,0.0001056411,0.0006971044,0.0001441527],"domain_scores_gemma":[0.9895817,0.005441489,0.002357526,0.0003196909,0.002212108,0.00008748514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005754524,0.001299378,0.00150885,0.000338211,0.000140317,0.000002439088,0.02097678,0.0002897135,0.001958633,0.778139,0.07070149,0.1245877],"study_design_scores_gemma":[0.001192541,0.001032118,0.09778121,0.0002844609,0.0007967423,0.0001520713,0.0709053,0.01023431,0.003911373,0.8113042,0.002064595,0.0003410477],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1730675,0.00007461601,0.8239279,0.0003221327,0.001665015,0.0002720327,0.0003449256,0.000007129645,0.0003187926],"genre_scores_gemma":[0.3117265,0.00003289925,0.6877437,0.00004520527,0.0002024496,0.000008960176,0.00003864851,0.00001670219,0.000184987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.138659,"threshold_uncertainty_score":0.995527,"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."}}