{"id":"W2786266018","doi":"10.3138/cmlr.3670","title":"First Language Test Bias? Comparing French-Speaking and Polish-Speaking Participants’ Performance on the Peabody Picture Vocabulary Test","year":2018,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cognate; Vocabulary; Psychology; Peabody Picture Vocabulary Test; Test (biology); Linguistics; Word (group theory); Meaning (existential); Contrast (vision); Logistic regression; Descriptive statistics; Vocabulary development; Statistics; Computer science; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003576433,0.0002530992,0.0004483741,0.0008441455,0.000208775,0.0007964161,0.000352512,0.0004507515,0.001841947],"category_scores_gemma":[0.01379303,0.0001232428,0.0003320603,0.0004893568,0.0007195988,0.0006139559,0.000649062,0.0002550266,0.0003743269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003342078,"about_ca_system_score_gemma":0.0004387514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006982402,"about_ca_topic_score_gemma":0.007299806,"domain_scores_codex":[0.9979718,0.0005403092,0.0002233187,0.00041849,0.000549884,0.0002961953],"domain_scores_gemma":[0.9958866,0.001642945,0.001094765,0.0003450787,0.0007847272,0.0002459669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002344256,0.00006605358,0.9762648,0.00005324685,0.0001017801,0.0001658779,0.004099845,0.00002738165,0.002581738,0.0001307549,0.0001342742,0.01613981],"study_design_scores_gemma":[0.000006738991,0.0002248355,0.9963182,0.00001578924,0.0000263921,0.0003988605,0.001717993,0.00005882471,0.0006310146,0.00008945214,0.0005058519,0.000005945098],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989896,0.0002701903,0.00008776665,0.00004768478,0.000006066089,0.000006479933,0.00002817591,0.000001922775,0.0005620347],"genre_scores_gemma":[0.9994633,0.0001055418,0.00005085293,0.00003252465,0.000005476786,0.000007224539,0.00006341121,0.000002326622,0.0002693552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006982402,"threshold_uncertainty_score":0.01891416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03728438863522641,"score_gpt":0.2738895015692373,"score_spread":0.2366051129340109,"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."}}