{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007822602,0.0003397046,0.0006794716,0.00008962082,0.0001497176,0.0005256296,0.001258714,0.000300781,0.3442622],"category_scores_gemma":[0.00009634953,0.0002132031,0.00008936092,0.00006174966,0.0001554842,0.0002682691,0.0004254449,0.0004660508,0.0003635972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003182941,"about_ca_system_score_gemma":0.0001254821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002647261,"about_ca_topic_score_gemma":0.00002162107,"domain_scores_codex":[0.9980245,0.0001907792,0.0006404927,0.0005604624,0.0003353245,0.0002484864],"domain_scores_gemma":[0.9981006,0.0004129997,0.00064976,0.000617836,0.0001248897,0.00009386674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000427661,0.00001821796,0.00002655953,0.00006040853,0.0004498452,0.0001988726,0.001943701,0.00000405247,0.004389159,0.9737668,0.004922114,0.01379259],"study_design_scores_gemma":[0.03396826,0.02562141,0.01293408,0.008260541,0.007748811,0.005345941,0.02107372,0.0002526677,0.03148358,0.4301721,0.4079742,0.01516466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.003860371,0.001077698,0.0002794375,0.0005607032,0.000471448,0.0007143419,0.00007570728,0.0000749341,0.9928854],"genre_scores_gemma":[0.1841582,0.00002436515,0.002046638,0.03145757,0.001189294,0.0001497459,0.0005019087,0.0002579245,0.7802143],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5435947,"threshold_uncertainty_score":0.8694172,"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."}}