{"id":"W2606448176","doi":"","title":"Oral vs. written exams: What are we assessing in Mathematics?","year":2017,"lang":"en","type":"article","venue":"Philologist – Journal Of Langugage, Literary And Cultural Studies (University of Banja Luka)","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Pedagogy; Mathematics; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001021757,0.0001056222,0.0003989598,0.00009599257,0.001020863,0.0002723265,0.0004525873,0.00007345335,0.00004683328],"category_scores_gemma":[0.0004303958,0.00008608036,0.00009290682,0.00007037973,0.0007039814,0.002057313,0.0001508297,0.0002464746,0.000001028877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005993113,"about_ca_system_score_gemma":0.00003120778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002487217,"about_ca_topic_score_gemma":0.0004676261,"domain_scores_codex":[0.9991059,0.0001960788,0.0002203416,0.0001096754,0.0002159482,0.0001520502],"domain_scores_gemma":[0.9986057,0.0001756438,0.0008120825,0.0001438369,0.0001935863,0.000069146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00008151335,0.0005069037,0.04845214,0.0006046917,0.0003156752,0.0003093245,0.8675434,8.906869e-7,0.00009421806,0.04153421,0.008842639,0.03171437],"study_design_scores_gemma":[0.0006757955,0.0001225915,0.03040191,0.002383323,0.00009332785,0.00004119667,0.8562127,0.00001647479,0.00002297599,0.0979192,0.01185311,0.000257439],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.966271,0.006441034,0.0002135509,0.02185133,0.000250628,0.0001244615,0.000003175912,0.00002951604,0.004815317],"genre_scores_gemma":[0.9812853,0.0118013,0.006194653,0.00006351353,0.00009260429,1.682803e-7,9.085031e-7,0.000003592745,0.0005579335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.056385,"threshold_uncertainty_score":0.7851757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1572865781028226,"score_gpt":0.3946645338389376,"score_spread":0.237377955736115,"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."}}