{"id":"W3155215713","doi":"10.5539/elt.v14n5p23","title":"Identifying Guessing in English Language Tests via Rasch Fit Statistics: An Exploratory Study","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rasch model; Psychology; Polytomous Rasch model; Test (biology); Statistics; Item response theory; Social psychology; Psychometrics; Mathematics education; 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":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02009318,0.0003796311,0.0007581266,0.001019047,0.0004435214,0.001415649,0.001232492,0.0001525241,0.0005353043],"category_scores_gemma":[0.2733515,0.0003442618,0.0001140131,0.002216327,0.0000623345,0.001598399,0.0006299305,0.001419628,0.00003683302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001490279,"about_ca_system_score_gemma":0.0001222777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000345603,"about_ca_topic_score_gemma":0.00179279,"domain_scores_codex":[0.9897892,0.005081757,0.001306547,0.001332686,0.001716999,0.0007728252],"domain_scores_gemma":[0.9804567,0.01686237,0.0004731687,0.00154538,0.0003995997,0.0002627971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001282202,0.000471315,0.08763903,0.00001813968,0.00002474056,0.001882857,0.6946984,0.0001450303,0.003158958,0.00007821398,0.0003513024,0.2115192],"study_design_scores_gemma":[0.001124068,0.0001044989,0.02321932,0.0001040327,0.00002591532,0.00001443509,0.9719262,0.001186776,0.0005978714,0.0008962365,0.0002957706,0.0005048504],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9621365,0.001707592,0.02882889,0.00001085188,0.002479044,0.0002824802,0.00003475901,0.0004593783,0.004060471],"genre_scores_gemma":[0.9310068,0.000004551356,0.06716595,0.0001283943,0.001116352,0.00002605513,0.00003343775,0.00005782471,0.0004606259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2772278,"threshold_uncertainty_score":0.9999009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2478259227889233,"score_gpt":0.467829404316962,"score_spread":0.2200034815280387,"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."}}