{"id":"W1829912168","doi":"10.3968/j.hess.1927024020120201.452","title":"The Effects of Test Facets on the Construct Validity of the Tests in Iranian EFL Students","year":2012,"lang":"en","type":"article","venue":"Higher education of social science","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Construct (python library); Construct validity; Psychology; Affect (linguistics); Test validity; Mathematics education; Cloze test; Computer science; Developmental psychology; Psychometrics; Linguistics; Reading comprehension; Communication; Reading (process)","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":[0.001061848,0.00005231757,0.00007913225,0.00002820656,0.0006983114,0.00004628238,0.0004531907,0.00001635504,0.00007537151],"category_scores_gemma":[0.0004173359,0.0000258704,0.00003386794,0.0001247798,0.001295416,0.0000958861,0.00004701903,0.000132125,0.000003926395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004387184,"about_ca_system_score_gemma":0.0001393206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000245265,"about_ca_topic_score_gemma":0.0000197731,"domain_scores_codex":[0.9990896,0.0001667422,0.0001424054,0.0000704628,0.0003921925,0.0001386135],"domain_scores_gemma":[0.9987939,0.0007707413,0.0002007747,0.0001312276,0.00008410217,0.00001926693],"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":[0.0000025343,0.0002885002,0.2862434,0.00003306038,0.00000382308,8.555279e-9,0.10864,6.202613e-7,0.0024538,0.6003014,0.0008896302,0.001143219],"study_design_scores_gemma":[0.00007142122,0.0000301423,0.9791973,0.00006857205,0.00000605279,7.086346e-8,0.004586991,4.158175e-7,0.001239994,0.000480893,0.01428289,0.00003530511],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573596,0.00005235931,7.96333e-8,0.0006046362,0.001267089,0.0001457571,0.000001501542,0.000004330136,0.04056468],"genre_scores_gemma":[0.9968948,0.000002160298,0.000003099977,0.000116198,0.0001982033,0.000007489369,1.509777e-7,0.000002971487,0.002774886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6929538,"threshold_uncertainty_score":0.5370917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04058171410618787,"score_gpt":0.3344179722173117,"score_spread":0.2938362581111238,"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."}}