{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006003031,0.0001192106,0.000170907,0.00005066017,0.001660519,0.0009484289,0.0007443408,0.0000447011,0.00005329943],"category_scores_gemma":[0.0004712705,0.0001115039,0.00002946535,0.00006313102,0.00006284466,0.0006385546,0.00004768205,0.0001572808,2.194599e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002713967,"about_ca_system_score_gemma":0.002682062,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05898476,"about_ca_topic_score_gemma":0.1688569,"domain_scores_codex":[0.9988531,0.00006682172,0.0002919619,0.0002470174,0.0002707491,0.000270309],"domain_scores_gemma":[0.9985614,0.000141252,0.0003444473,0.000475229,0.0002703991,0.0002072256],"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":[0.0003672183,0.0002995598,0.04551859,0.0004199415,0.0002534152,0.0009158557,0.004060277,0.0004463046,0.02471691,0.1802927,0.0157137,0.7269955],"study_design_scores_gemma":[0.007186564,0.0007784122,0.5883985,0.0005235057,0.00008575169,0.001316277,0.0003580708,0.2519757,0.009717119,0.06432715,0.07325159,0.002081374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3294747,0.001362831,0.6599392,0.007512571,0.0008572904,0.0004209092,0.00004049544,0.00007702913,0.0003150033],"genre_scores_gemma":[0.8298388,0.000007271115,0.1642135,0.005580562,0.0002847856,0.0000116938,0.00001172481,0.00001355494,0.00003818679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7249141,"threshold_uncertainty_score":0.9996392,"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."}}