{"id":"W3140486864","doi":"10.3758/s13428-021-01556-y","title":"Is the author recognition test a useful metric for native and non-native English speakers? An item response theory analysis","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Hebrew University of Jerusalem","keywords":"Test (biology); Psychology; Reading (process); Item response theory; Neuroscience of multilingualism; First language; Foreign language; Language assessment; Linguistics; Cognitive psychology; Mathematics education; Psychometrics; Developmental psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01056106,0.0004653818,0.001135586,0.003616307,0.0003765749,0.001693161,0.001008147,0.001129496,0.001535253],"category_scores_gemma":[0.03683615,0.0002342859,0.0006812604,0.001652081,0.0009875261,0.001835732,0.0008260428,0.001050718,0.0006998456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005867248,"about_ca_system_score_gemma":0.0007679087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002818018,"about_ca_topic_score_gemma":0.003988681,"domain_scores_codex":[0.9931144,0.002405343,0.001145954,0.0008110886,0.002272911,0.000250189],"domain_scores_gemma":[0.9762725,0.01120221,0.004259149,0.001406965,0.005703813,0.001155326],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003956529,0.0001903207,0.9262638,0.0001056393,0.0002266002,0.0002259019,0.001430135,0.0002123262,0.001798947,0.0006025169,0.001698144,0.06685],"study_design_scores_gemma":[0.00003576989,0.0007404127,0.9883668,0.0001193857,0.000110312,0.0006013869,0.002408649,0.002424373,0.001505167,0.001233067,0.002408613,0.00004600287],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9798029,0.001115978,0.007425527,0.001850274,0.0001389773,0.0001428607,0.001196231,0.0001672608,0.008159994],"genre_scores_gemma":[0.9912686,0.0002623129,0.006352639,0.0003035972,0.00006119201,0.0001326819,0.0006342448,0.00002359841,0.000961031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.989439,"threshold_uncertainty_score":0.05585289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3218624457308632,"score_gpt":0.5860858601608735,"score_spread":0.2642234144300103,"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."}}