{"id":"W3028726210","doi":"10.5539/ies.v13n6p96","title":"Analyzing the Content of Reading Texts Questions in Flying High for Saudi Arabia","year":2020,"lang":"en","type":"article","venue":"International Education Studies","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Reading (process); Checklist; Cognition; Content analysis; Categorization; Mathematics education; Pedagogy; Social science; Sociology; Linguistics","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":[0.0004310225,0.00005941214,0.0001143471,0.00008348034,0.0002830849,0.0000335783,0.0001979904,0.00002196393,0.00005671901],"category_scores_gemma":[0.0019314,0.00004920115,0.00004816689,0.0002109793,0.000120266,0.0001623774,0.00002772143,0.00006362922,0.000005274071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571266,"about_ca_system_score_gemma":0.0004381561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001755512,"about_ca_topic_score_gemma":0.0009970902,"domain_scores_codex":[0.9992388,0.00007155311,0.0002639864,0.0001328055,0.0001917636,0.0001010493],"domain_scores_gemma":[0.9979236,0.0007146021,0.0001603922,0.00004994748,0.001118999,0.00003246744],"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":[0.00003545883,0.0002173799,0.3067595,0.00004133547,0.000240669,1.28959e-7,0.08283272,0.0001320591,0.0005727112,0.5731163,0.01091752,0.02513421],"study_design_scores_gemma":[0.0005210151,0.00006253013,0.3973808,0.0003039018,0.00007752008,6.339455e-7,0.3056543,0.0002530538,0.000208189,0.05451474,0.2407391,0.0002843077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7322397,0.002337905,0.002498888,0.2521965,0.004399253,0.0005095983,0.00002395945,0.00003026855,0.005763883],"genre_scores_gemma":[0.9949924,0.0004861985,0.001254163,0.000639273,0.0007086066,0.0001693541,0.00001797375,0.000004412482,0.001727632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5186015,"threshold_uncertainty_score":0.2653821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2670350450032555,"score_gpt":0.5059886895439419,"score_spread":0.2389536445406864,"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."}}