{"id":"W2131222006","doi":"10.1177/0265532210364380","title":"Use of tree-based regression in the analyses of L2 reading test items","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Cognition; Psychology; Interpretation (philosophy); Cognitive psychology; Test (biology); Tree (set theory); Regression; Regression analysis; Natural language processing; Artificial intelligence; Computer science; Machine learning; Linguistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003532011,0.00005269352,0.00008678131,0.000113463,0.00003535407,0.0000175126,0.0004178238,0.00003928541,0.000003445648],"category_scores_gemma":[0.001931721,0.00003362502,0.00002020452,0.0005838154,0.00004787209,0.0001184292,0.00004634073,0.0001721514,6.056441e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005460204,"about_ca_system_score_gemma":0.00005182611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003274851,"about_ca_topic_score_gemma":0.00007328141,"domain_scores_codex":[0.9994681,0.00003758151,0.0001667527,0.0001149816,0.0001235235,0.00008900646],"domain_scores_gemma":[0.9972418,0.002189643,0.0001543395,0.0003570463,0.00004635795,0.00001084406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[6.703237e-7,0.0001308049,0.2848825,0.00001644372,0.000002413642,0.00001200938,0.001244647,0.00006304986,0.6914383,0.0028929,0.00003269767,0.01928355],"study_design_scores_gemma":[0.0002231377,0.0001033221,0.4095229,0.0003797789,0.00001237367,0.00001663616,0.00125326,0.06037855,0.5269459,0.0009841033,0.00003135062,0.0001486324],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961209,0.00003536544,0.002765309,0.0004215768,0.00004787805,0.00005265056,0.000001155401,0.00004014962,0.0005150454],"genre_scores_gemma":[0.8886801,2.169788e-7,0.1112188,0.00005749081,0.00001686807,0.000004652825,0.000001529832,0.000002087322,0.00001823502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1644924,"threshold_uncertainty_score":0.231259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1065583235754579,"score_gpt":0.3862878005927542,"score_spread":0.2797294770172963,"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."}}