{"id":"W4293147763","doi":"10.1075/ijcl.20024.nai","title":"Handle it in-house?","year":2022,"lang":"en","type":"article","venue":"International Journal of Corpus Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Sophistication; Vocabulary; Natural language processing; Context (archaeology); Corpus linguistics; Selection (genetic algorithm); Artificial intelligence; Resource (disambiguation); Key (lock); Lexical density; Lexical item; Word lists by frequency; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.002095877,0.0003417258,0.0005060676,0.001034185,0.002784233,0.005165935,0.0009416394,0.001518512,0.2859845],"category_scores_gemma":[0.01135888,0.0002433966,0.0002730404,0.0007922193,0.001265823,0.006426644,0.003966117,0.001606365,0.1294746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102979,"about_ca_system_score_gemma":0.001079704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003508825,"about_ca_topic_score_gemma":0.004971804,"domain_scores_codex":[0.9985384,0.000436451,0.00007668305,0.0002414699,0.0004635526,0.0002435233],"domain_scores_gemma":[0.9951775,0.001133076,0.0004937528,0.0009077518,0.001370398,0.0009175381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001303035,0.0001450524,0.01158358,0.0002282186,0.00001441714,0.001659721,0.01441737,0.00008672548,0.001666657,0.03966767,0.7036217,0.2267786],"study_design_scores_gemma":[0.000005951273,0.00002716893,0.002157562,0.0001361337,0.000005198833,0.0005349405,0.007996854,0.0001799706,0.0006964841,0.004181406,0.984057,0.00002136931],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06352405,0.001531699,0.01549427,0.05573797,0.006356393,0.0003137176,0.00393213,0.004718528,0.8483913],"genre_scores_gemma":[0.2780348,0.001518738,0.008341121,0.01577958,0.001896538,0.0001948594,0.002377941,0.002866012,0.6889903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2859845,"threshold_uncertainty_score":0.9567133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02167538962131468,"score_gpt":0.3440635685827646,"score_spread":0.3223881789614499,"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."}}