{"id":"W3011618373","doi":"10.1075/jslp.19015.tay","title":"Testing the malleability of teachers’ judgments of second language speech","year":2020,"lang":"en","type":"article","venue":"Journal of Second Language Pronunciation","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; German; Vowel; Intonation (linguistics); Linguistics; Second language; First language; Context (archaeology); Consonant","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003717144,0.0002420814,0.0001958533,0.000854339,0.0004822644,0.001150428,0.0002150985,0.0002825578,0.00145991],"category_scores_gemma":[0.03085652,0.0002152072,0.0001697476,0.0002478919,0.001036295,0.0005229224,0.0009273519,0.0003589223,0.0003380117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000685558,"about_ca_system_score_gemma":0.0004955215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063552,"about_ca_topic_score_gemma":0.01832624,"domain_scores_codex":[0.9963032,0.001268619,0.0002304966,0.0005045959,0.001503924,0.0001890673],"domain_scores_gemma":[0.9740003,0.01275928,0.005040657,0.001736898,0.005401978,0.001060821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005620991,0.0001105581,0.9214612,0.00006620459,0.00007762499,0.0001284421,0.02617773,0.0001573657,0.03130858,0.0001220488,0.0001683982,0.01965984],"study_design_scores_gemma":[0.000008664783,0.0003190169,0.9821696,0.00001527196,0.00001336855,0.0001132978,0.01140052,0.0004766247,0.004857055,0.00008842615,0.0005180437,0.0000200848],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983045,0.00001723267,0.00027742,0.00001302063,0.000003952133,0.000008330805,0.00001305916,0.000006086513,0.001356465],"genre_scores_gemma":[0.9994979,0.00001068883,0.0001675965,0.00001042782,0.000002138375,0.000007542089,0.00001757482,0.000003481932,0.0002825814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01063552,"threshold_uncertainty_score":0.02114725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05239156274944249,"score_gpt":0.3310371246838275,"score_spread":0.2786455619343849,"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."}}