{"id":"W2072764341","doi":"10.1080/09695940600563611","title":"Differential effects of global modifications to large‐scale high stakes examination programmes","year":2006,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Scholarship; Accountability; Scale (ratio); Session (web analytics); Test (biology); Empirical examination; Identification (biology); Psychology; Political science; Medical education; Medicine; Geography; Law; Actuarial science; Business; Advertising","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":[0.0006905198,0.000121077,0.000154245,0.0001473022,0.0002752735,0.0001648278,0.0001768419,0.00008220212,0.00002681152],"category_scores_gemma":[0.0008336612,0.0001286358,0.00002934244,0.0007467506,0.0000848611,0.0006062538,0.00006017355,0.0001003176,0.000004992301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004017673,"about_ca_system_score_gemma":0.001068906,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01515504,"about_ca_topic_score_gemma":0.005486237,"domain_scores_codex":[0.9981055,0.0005899787,0.0003274526,0.0002528485,0.0004319766,0.0002922973],"domain_scores_gemma":[0.9983203,0.0009493798,0.0002561419,0.0001730527,0.0002073121,0.00009383414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001767984,0.002034014,0.09850462,0.00004563762,0.00001593483,3.029056e-7,0.008124891,0.00001722241,0.0002389501,0.88168,0.0002097574,0.009110951],"study_design_scores_gemma":[0.0003659113,0.00006621101,0.9349887,0.000034015,0.00004658782,6.742089e-7,0.02214925,0.00002527831,0.00009678698,0.003450616,0.03863537,0.000140544],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9377885,0.00007474767,0.001558819,0.009446842,0.0004132239,0.0009260873,0.00001408504,0.00003851156,0.04973916],"genre_scores_gemma":[0.9910107,0.0001607793,0.006846962,0.0001874566,0.0004142008,0.0002371277,0.00004560089,0.000007180022,0.001090026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8782294,"threshold_uncertainty_score":0.9914031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02697556704776101,"score_gpt":0.4168892970341898,"score_spread":0.3899137299864288,"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."}}