{"id":"W2571426659","doi":"10.5539/elt.v10n2p23","title":"Cross-Mode Comparability of Computer-Based Testing (CBT) Versus Paper-Pencil Based Testing (PPT): An Investigation of Testing Administration Mode among Iranian Intermediate EFL Learners","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Gender and Technology in Education","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Assessment Systems Corporation","keywords":"Comparability; Psychology; Test (biology); Contrast (vision); Pencil (optics); Vocabulary; Mode (computer interface); Repeated measures design; Mathematics education; Statistics; Computer science; Artificial intelligence; Mathematics; Engineering; 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":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002528367,0.0002235012,0.000329238,0.0001508679,0.001336778,0.0002596861,0.0007479792,0.0002226123,0.00001434719],"category_scores_gemma":[0.02283968,0.0002514833,0.00006962025,0.0002383263,0.001018103,0.001015905,0.00007321319,0.0006258831,0.000001060551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002147626,"about_ca_system_score_gemma":0.0006775914,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02339569,"about_ca_topic_score_gemma":0.008293735,"domain_scores_codex":[0.9974618,0.0005917803,0.0006080444,0.000481496,0.0004589049,0.0003979617],"domain_scores_gemma":[0.9960443,0.001715413,0.0009748466,0.000710324,0.0003956188,0.000159516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003277567,0.0001249212,0.8809684,0.00009591112,0.00001158729,0.000004137058,0.085714,0.00461363,0.007972198,0.0001139088,0.0000025291,0.02034601],"study_design_scores_gemma":[0.002119693,0.000791719,0.6988348,0.0005680976,0.00009377808,9.5864e-7,0.09135766,0.1941469,0.01102393,0.0004516843,0.000004699576,0.0006060813],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928941,0.000009712147,0.001122295,0.00006706461,0.0006152623,0.0003303841,0.00001688925,0.000345552,0.004598807],"genre_scores_gemma":[0.9623622,1.170786e-7,0.03710844,0.00002662677,0.0003985182,0.00001752708,0.00005542479,0.00002386331,0.000007262061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1895333,"threshold_uncertainty_score":0.9999937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07368861285141097,"score_gpt":0.3748048478557762,"score_spread":0.3011162350043652,"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."}}