{"id":"W3112629186","doi":"10.14705/rpnet.2020.48.1191","title":"Beyond frequency: evaluating the lexical demands of reading materials with open-access corpus tools","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Computer science; Reading (process); Noun; Set (abstract data type); Natural language processing; Lexical access; Lexical density; Word lists by frequency; Word (group theory); Artificial intelligence; Lexical item; Linguistics; Psychology","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":[0.005801446,0.0008151407,0.0007920231,0.003809867,0.0009104442,0.004369927,0.0013744,0.00111153,0.006805352],"category_scores_gemma":[0.06140942,0.0005169203,0.0003548769,0.00291252,0.0008330164,0.005099992,0.00229527,0.0007952406,0.002163478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006815432,"about_ca_system_score_gemma":0.0006619428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00145211,"about_ca_topic_score_gemma":0.003327312,"domain_scores_codex":[0.991327,0.003446662,0.0009653885,0.001102608,0.002910487,0.0002478205],"domain_scores_gemma":[0.8779984,0.1054574,0.004083375,0.003289819,0.007943014,0.001228079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007091815,0.005293862,0.1412046,0.004306967,0.0002232296,0.002980068,0.04548123,0.002944397,0.1992802,0.003428717,0.004578508,0.5831864],"study_design_scores_gemma":[0.0006568867,0.009758193,0.7470452,0.000783605,0.0004705463,0.005818653,0.03958,0.02412385,0.128251,0.005307523,0.03770567,0.0004989255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9780273,0.0004625642,0.007806843,0.00009582336,0.00004218108,0.0004438495,0.0006415267,0.0002803507,0.01219955],"genre_scores_gemma":[0.9577586,0.0004359995,0.03226567,0.0001191055,0.00008598992,0.001152896,0.002252925,0.0004124694,0.005516405],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006805352,"threshold_uncertainty_score":0.03068131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1427326636412118,"score_gpt":0.4206874571691568,"score_spread":0.277954793527945,"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."}}