{"id":"W2610650708","doi":"10.18806/tesl.v34i1.1257","title":"Steps for Creating a Specialized Corpus and Developing an Annotated Frequency-Based Vocabulary List","year":2017,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vocabulary; Corpus linguistics; Linguistics; Computer science; Humanities; Library science; Psychology; Artificial intelligence; Art; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00996212,0.001453704,0.0009526458,0.008682296,0.003506038,0.004716988,0.001912354,0.001428433,0.03706852],"category_scores_gemma":[0.03065498,0.001758318,0.001112213,0.004684483,0.001968598,0.008360063,0.006430512,0.004068681,0.01542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001948896,"about_ca_system_score_gemma":0.00498616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003833547,"about_ca_topic_score_gemma":0.007009711,"domain_scores_codex":[0.9935554,0.002480609,0.001284328,0.0009553104,0.001496072,0.0002282318],"domain_scores_gemma":[0.9740114,0.01265802,0.001026023,0.003262899,0.008279415,0.0007621657],"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":[0.0003115445,0.0003766232,0.004926695,0.004178519,0.00006358827,0.002297061,0.05513449,0.003133746,0.06803167,0.1025344,0.1305934,0.6284182],"study_design_scores_gemma":[0.00007663053,0.0001826491,0.004717027,0.00139316,0.00004974935,0.001295324,0.01243271,0.007640374,0.01675984,0.02611102,0.9291294,0.0002121948],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02137844,0.0006755606,0.9054035,0.002445177,0.001039776,0.01120437,0.0102472,0.008075496,0.03953042],"genre_scores_gemma":[0.01303472,0.0002720048,0.9562147,0.0003104529,0.0001150345,0.008546524,0.009269899,0.002263068,0.009973611],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03706852,"threshold_uncertainty_score":0.1240066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03666660018396091,"score_gpt":0.2821312117248886,"score_spread":0.2454646115409277,"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."}}