{"id":"W2102131480","doi":"10.5539/ies.v4n1p166","title":"Optimal Number of Gaps in C-Test Passages","year":2011,"lang":"en","type":"article","venue":"International Education Studies","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alexander von Humboldt-Stiftung","keywords":"Test (biology); Reliability (semiconductor); Statistics; Psychology; Factorial; Mathematics; Computer science; Mathematics education","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":[0.0001493583,0.00006940048,0.00009704359,0.0001484556,0.00002812318,0.000009293298,0.0004833274,0.00003083521,0.00008915856],"category_scores_gemma":[0.0002627023,0.00006569173,0.00002713666,0.0001989694,0.00008483067,0.0002691679,0.0001386085,0.00007499599,0.00005701302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006858324,"about_ca_system_score_gemma":0.0001925802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004392828,"about_ca_topic_score_gemma":0.000009257123,"domain_scores_codex":[0.9993439,0.00001633388,0.0002300288,0.0001712304,0.0001557197,0.00008283482],"domain_scores_gemma":[0.9989865,0.0001180661,0.0001122829,0.0001666692,0.0006000082,0.00001649055],"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":[0.00000284462,0.0009695723,0.3808583,0.0000101963,0.00006727994,0.000001206408,0.003193259,0.000004692253,0.0001038889,0.6039022,0.004619086,0.006267473],"study_design_scores_gemma":[0.0003671435,0.00006558111,0.7831651,0.0001848783,0.00001064885,0.00004500336,0.009202671,0.0002472335,0.009603422,0.1863661,0.01044212,0.0003001276],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9123439,0.001102988,0.005830525,0.01197647,0.005820397,0.0001450888,0.000005370269,0.00009591763,0.0626793],"genre_scores_gemma":[0.9228876,0.0001908064,0.07524589,0.0001412562,0.00004309203,0.00005723478,0.000002509732,0.000002665417,0.001428992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4175362,"threshold_uncertainty_score":0.2678831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06296830432380317,"score_gpt":0.4108746882031374,"score_spread":0.3479063838793342,"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."}}