{"id":"W2587671992","doi":"10.1075/itl.167.2.02dan","title":"Evaluating lists of high-frequency words","year":2016,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Word list; Word (group theory); Artificial intelligence; Linguistics; Corpus linguistics; Natural language processing; Word lists by frequency; American English; Computer science; Philosophy","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":[0.00405543,0.0007474112,0.0007682304,0.01383144,0.001087163,0.002729781,0.0008130543,0.0008858767,0.005772691],"category_scores_gemma":[0.04094167,0.0003032089,0.0004325801,0.01010513,0.0005958365,0.004538229,0.001882192,0.0004395793,0.003943925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041977,"about_ca_system_score_gemma":0.001158268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006989944,"about_ca_topic_score_gemma":0.01084791,"domain_scores_codex":[0.9956951,0.001191152,0.0004638011,0.0006043012,0.001838939,0.0002067439],"domain_scores_gemma":[0.9641179,0.02359633,0.002656155,0.001595778,0.007239996,0.0007937642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002076159,0.0002943371,0.1980725,0.00325021,0.0004445612,0.0005966483,0.0102174,0.004181158,0.03297712,0.002173327,0.01656314,0.7291535],"study_design_scores_gemma":[0.000284804,0.002387437,0.7248853,0.001321522,0.0009723761,0.003435619,0.02505874,0.04720328,0.06422457,0.006969126,0.1227771,0.0004801662],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.945299,0.004667281,0.02130585,0.0002308708,0.0001686759,0.0002063164,0.006080227,0.002133054,0.01990865],"genre_scores_gemma":[0.95257,0.001420584,0.02272696,0.0001207413,0.0001186003,0.0002403145,0.01752597,0.0004878611,0.004788968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01383144,"threshold_uncertainty_score":0.02144742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03959487389603254,"score_gpt":0.3964028863748773,"score_spread":0.3568080124788447,"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."}}