{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009261686,0.0001399722,0.0004625107,0.00006894534,0.00002723796,0.000003261531,0.0002297312,0.00008175728,0.03205331],"category_scores_gemma":[0.003335015,0.0001001141,0.00009765667,0.0001870524,0.00009249051,0.000005302445,0.00003818497,0.0001174424,0.0002642908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002255295,"about_ca_system_score_gemma":0.00005061747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002796307,"about_ca_topic_score_gemma":6.315237e-7,"domain_scores_codex":[0.9985083,0.00009022852,0.0006987753,0.0002421462,0.0002584491,0.0002020398],"domain_scores_gemma":[0.9981168,0.0004322864,0.0005476683,0.0005472028,0.0002949231,0.00006114546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005820326,0.0001367434,0.00009370046,0.004125249,0.0001246105,0.00002040088,0.001221639,0.000001782981,0.005523234,0.6713129,0.003751908,0.3136296],"study_design_scores_gemma":[0.01316004,0.001810069,0.01173167,0.08917032,0.002394236,0.00007708544,0.002645977,0.0000342881,0.01952238,0.06966674,0.7863715,0.003415717],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03402958,0.161184,0.001616925,0.0002232194,0.002435939,0.0009043692,0.00008180193,0.0001296784,0.7993945],"genre_scores_gemma":[0.9842713,0.001667252,0.01009985,0.002580048,0.0007468414,0.00003348162,0.0000199906,0.00003372152,0.0005475393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9502417,"threshold_uncertainty_score":0.9688315,"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."}}