{"id":"W2015457266","doi":"10.1016/j.system.2013.07.010","title":"Putting testing researchers to the test: An exploratory study on the TOEFL iBT","year":2013,"lang":"en","type":"article","venue":"System","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mount Saint Vincent University; Carleton University; Queen's University","funders":"","keywords":"Test of English as a Foreign Language; Computer science; Context (archaeology); Construct (python library); Test (biology); Exploratory research; Variance (accounting); Focus group; Psychology; Construct validity; Language assessment; Mathematics education; Psychometrics; Sociology; Developmental psychology; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02996378,0.0007863044,0.0009599343,0.001905579,0.003160374,0.00470425,0.002939583,0.001861261,0.002671294],"category_scores_gemma":[0.16813,0.0006860668,0.0004515925,0.001465832,0.002049211,0.004346656,0.004134938,0.003025481,0.001030447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002725078,"about_ca_system_score_gemma":0.003525616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006343674,"about_ca_topic_score_gemma":0.01101015,"domain_scores_codex":[0.9724743,0.02002404,0.001405388,0.001436178,0.003308768,0.001351229],"domain_scores_gemma":[0.7420928,0.2110272,0.006378436,0.01311728,0.02180824,0.005575954],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.003887369,0.02391551,0.2793767,0.001068916,0.0001841047,0.003113412,0.3535449,0.003267036,0.02675684,0.002386843,0.00501193,0.2974864],"study_design_scores_gemma":[0.001252259,0.05513493,0.3891734,0.001000677,0.0005599413,0.002687342,0.381825,0.04979213,0.06338134,0.004642093,0.04982499,0.0007258906],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924656,0.00002005628,0.004570937,0.0001496377,0.00001645339,0.0004240162,0.00008806133,0.0001978082,0.002067544],"genre_scores_gemma":[0.980653,0.00003638857,0.01508008,0.0002115626,0.00001739489,0.0005488663,0.0002406198,0.0001929706,0.003019009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9700362,"threshold_uncertainty_score":0.1584655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2468339053032725,"score_gpt":0.4152035437005829,"score_spread":0.1683696383973104,"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."}}