{"id":"W2123754104","doi":"10.1017/s1366728914000832","title":"Flawed self-assessment: Investigating self- and other-perception of second language speech","year":2014,"lang":"en","type":"article","venue":"Bilingualism Language and Cognition","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Fluency; Psychology; Self-assessment; Perception; Stress (linguistics); Cognition; Cognitive psychology; Linguistics; Computer science; Social psychology; Speech recognition","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0006393018,0.0001385779,0.0002053595,0.0001274563,0.00009338983,0.00003411127,0.00006448734,0.0001694425,0.0007058296],"category_scores_gemma":[0.00004687054,0.0001313958,0.00003199942,0.0001249568,0.0001074119,0.00005099448,0.00004774503,0.0002134013,0.00002237779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001191734,"about_ca_system_score_gemma":0.00002760637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004040116,"about_ca_topic_score_gemma":0.0001574566,"domain_scores_codex":[0.9987879,0.0002877215,0.0002427274,0.0003124059,0.0001366908,0.0002325104],"domain_scores_gemma":[0.9993237,0.0002000183,0.0001133765,0.0002051716,0.00006342043,0.00009436597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005543158,0.0003177873,0.01028741,0.0003479413,0.0002016215,0.00005965543,0.2874734,1.468763e-7,0.6005986,0.00207748,0.0001850008,0.09839551],"study_design_scores_gemma":[0.01674611,0.00313996,0.598074,0.000593839,0.0008791912,0.001425202,0.2317416,0.004787567,0.1155241,0.02141055,0.003306397,0.00237151],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881999,0.0004571286,0.00004317658,0.00004808695,0.00008846512,0.0002165529,0.00003620956,0.00009644587,0.01081403],"genre_scores_gemma":[0.9963903,0.00002329537,0.002544559,0.0005812644,0.0001898969,0.00002104018,0.00005554616,0.0000229632,0.0001710751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5877866,"threshold_uncertainty_score":0.772834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01891757290345875,"score_gpt":0.3412955555550399,"score_spread":0.3223779826515811,"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."}}