{"id":"W4391229484","doi":"10.3389/fpsyg.2024.1270433","title":"Simon Fraser University Speech Error Database (SFUSED) Cantonese: Methods, design, and usage","year":2024,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Workflow; Database; Set (abstract data type); Perspective (graphical); Component (thermodynamics); Quality (philosophy); Natural language processing; Speech recognition; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009983302,0.001356583,0.0008154172,0.003233222,0.001388031,0.00208684,0.002275885,0.0008242245,0.03170744],"category_scores_gemma":[0.02335929,0.0005671995,0.0003164429,0.002513052,0.00104532,0.001430679,0.003323851,0.0009631105,0.01323211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00129805,"about_ca_system_score_gemma":0.004044299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02067017,"about_ca_topic_score_gemma":0.02350689,"domain_scores_codex":[0.9918324,0.002634267,0.001352115,0.001718201,0.002092883,0.0003700553],"domain_scores_gemma":[0.9789408,0.004779113,0.001212569,0.005298084,0.007937999,0.001831451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00422456,0.001248473,0.0331688,0.003252886,0.0001622987,0.001709969,0.01101497,0.004005183,0.04136509,0.007411194,0.280633,0.6118037],"study_design_scores_gemma":[0.002058323,0.002177644,0.1768653,0.001440556,0.000257896,0.001734873,0.008368324,0.01663833,0.04145923,0.007694538,0.7405404,0.0007645381],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.2880681,0.001445018,0.2189458,0.002017516,0.0007969543,0.04297809,0.3709688,0.02411566,0.05066414],"genre_scores_gemma":[0.2900297,0.001167121,0.2600199,0.0008296867,0.0003823242,0.09104866,0.3249145,0.004850226,0.02675787],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03170744,"threshold_uncertainty_score":0.1060719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02895829171747926,"score_gpt":0.3557433628741066,"score_spread":0.3267850711566273,"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."}}