{"id":"W4211261325","doi":"10.1177/00238309211071045","title":"Cross-Linguistic Trends in Speech Errors: An Analysis of Sub-Lexical Errors in Cantonese","year":2022,"lang":"en","type":"article","venue":"Language and Speech","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Syllable; Linguistics; Mandarin Chinese; Speech error; Phonology; Encoding (memory); Set (abstract data type); Psychology; Lexical diversity; Speech production; Computer science; Artificial intelligence; Vocabulary","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007674856,0.0001330112,0.0004235437,0.001324438,0.00006224921,0.00001639564,0.0002868511,0.000117583,0.008216829],"category_scores_gemma":[0.00006494883,0.0001340012,0.0000818482,0.002025491,0.0001466275,0.00002652968,0.000151566,0.0005078409,0.000006837527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005354074,"about_ca_system_score_gemma":0.0000302146,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03164697,"about_ca_topic_score_gemma":0.04265553,"domain_scores_codex":[0.9982539,0.0003136503,0.0003557651,0.0004213936,0.0002385149,0.0004167645],"domain_scores_gemma":[0.9992702,0.00009913137,0.00006523072,0.0004390878,0.00002773679,0.00009861235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005979714,0.001034669,0.8602905,0.00001920378,0.0002818774,0.005127873,0.08881333,0.000213121,0.006803147,0.0004817864,0.00007902728,0.03625754],"study_design_scores_gemma":[0.001024307,0.0002785449,0.9899384,0.000003661446,0.0000694365,0.00004874971,0.005765188,0.001659669,0.0005994617,0.0002159308,0.0002122186,0.000184391],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994738,0.0007516445,0.000001609479,0.00007167272,0.000146273,0.0000822017,0.0001327956,0.00001433671,0.004061436],"genre_scores_gemma":[0.997335,0.00001351886,0.00005812994,0.0000818091,0.00004186315,0.00002694147,0.0001580676,0.00001546565,0.002269195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.129648,"threshold_uncertainty_score":0.9926898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02967238255619012,"score_gpt":0.3946747583670924,"score_spread":0.3650023758109023,"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."}}