{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04103191,0.0002321468,0.0004427644,0.001486156,0.0006750094,0.0002372183,0.0003500176,0.0002215105,0.001231808],"category_scores_gemma":[0.02863617,0.0001749562,0.000223947,0.004851569,0.0003367042,0.0002137295,0.0001795555,0.0008588145,0.00002160452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002096671,"about_ca_system_score_gemma":0.0002570988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008313025,"about_ca_topic_score_gemma":0.00002231643,"domain_scores_codex":[0.977493,0.01982413,0.0004846569,0.0009221794,0.0005905509,0.0006855259],"domain_scores_gemma":[0.9518619,0.04457624,0.0001492155,0.0007398776,0.002425712,0.0002471072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003064159,0.001212601,0.0621883,0.00004080212,0.001593781,0.0001933676,0.3249421,5.181274e-7,0.004185782,0.0005788308,0.003727933,0.5982718],"study_design_scores_gemma":[0.001180762,0.0006572417,0.8890801,0.00004431789,0.0007487654,0.00001638387,0.07272237,0.0001444321,0.01114862,0.002168266,0.02173014,0.0003585944],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9742398,0.0004304345,0.02008604,0.0006046186,0.000360655,0.001469116,0.0003579936,0.00005628858,0.002395089],"genre_scores_gemma":[0.756636,0.00005958248,0.1905019,0.0003454223,0.0003564656,0.004057063,0.0002470374,0.000105437,0.0476911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8268918,"threshold_uncertainty_score":0.9996812,"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."}}