{"id":"W2887474951","doi":"10.5430/ijhe.v7n4p33","title":"A Quantitative Framework for the Analysis of Two-Stage Exams","year":2018,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Perspective (graphical); Mathematics education; Psychology; Computer science; Pedagogy; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003698461,0.00005403784,0.0001219584,0.0003223166,0.00004425378,0.00008259822,0.0008151176,0.0000238463,0.00007245988],"category_scores_gemma":[0.0001800965,0.00003662647,0.0001649255,0.0004687782,0.00005609456,0.000214985,0.00003591843,0.0001050567,0.00000404469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004153615,"about_ca_system_score_gemma":0.0001866798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000277715,"about_ca_topic_score_gemma":0.000005647657,"domain_scores_codex":[0.9991695,0.00004054325,0.0003054512,0.00008585878,0.0003331859,0.00006545086],"domain_scores_gemma":[0.9973352,0.0005729554,0.0005805607,0.0001572488,0.001325016,0.00002904413],"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":[0.00003472855,0.0001840264,0.003880851,0.0000026003,0.001345142,6.045067e-7,0.001422498,0.002327008,0.0002454695,0.972136,0.0009781788,0.01744289],"study_design_scores_gemma":[0.001021279,0.001084255,0.2489126,0.0002802042,0.001503386,0.00002129883,0.001159146,0.2798168,0.002291482,0.3909403,0.0726142,0.0003549343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0971104,0.0003468339,0.8730269,0.02530337,0.003876086,0.00004844042,0.000006754934,0.000007926253,0.0002732511],"genre_scores_gemma":[0.8868784,0.00001350152,0.110896,0.0003794945,0.0007375809,0.000001678277,0.000002460137,0.000003345169,0.00108753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.789768,"threshold_uncertainty_score":0.1514705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03700379806537274,"score_gpt":0.4328743779453875,"score_spread":0.3958705798800148,"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."}}