{"id":"W4200186911","doi":"10.21083/ajote.v10i2.6762","title":"Analysis of Item Writing Flaws in a Communications Skills Test in a Ghanaian University","year":2021,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Multiple choice; Multitude; Quality (philosophy); First language; Mathematics education; Descriptive statistics; Item analysis; Social psychology; Statistics; Linguistics; Psychometrics; Developmental psychology; Mathematics","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":[0.001005265,0.0000416401,0.0001873238,0.0005291498,0.00007537656,0.00002312579,0.0003344492,0.00003511,0.0001004915],"category_scores_gemma":[0.0004932235,0.00004753165,0.0000920325,0.002550933,0.00008430732,0.0002028901,0.00003815641,0.0001674282,7.963361e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003385111,"about_ca_system_score_gemma":0.000847358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001516466,"about_ca_topic_score_gemma":0.01440577,"domain_scores_codex":[0.9989279,0.000403413,0.0002961451,0.00006809891,0.0002020726,0.0001023768],"domain_scores_gemma":[0.9988256,0.0003998515,0.000320003,0.0001567583,0.0002461069,0.00005167843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002256686,0.0008699153,0.953757,0.000001744533,0.0000505587,0.000002133482,0.04070917,0.000005569251,0.0001258042,0.001057457,0.000081258,0.003337168],"study_design_scores_gemma":[0.0001189066,0.00001020482,0.7421145,0.00003894826,0.0001131519,4.020507e-7,0.255466,0.00002692907,0.0000054687,0.00005550029,0.002012968,0.00003699846],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.972823,0.0002320448,0.00001268713,0.003706182,0.00005363308,0.00004496265,0.000001368119,0.000002237154,0.02312393],"genre_scores_gemma":[0.9978925,0.0001871505,0.001093176,0.00002078416,0.00004269833,5.060157e-7,0.000004014338,0.000002387068,0.0007567627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2147569,"threshold_uncertainty_score":0.8038757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02527638234198573,"score_gpt":0.3559029099377932,"score_spread":0.3306265275958075,"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."}}