{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04071942,0.002715764,0.001815071,0.004236252,0.0006670157,0.001988568,0.001418163,0.0007584753,0.002325297],"category_scores_gemma":[0.1662452,0.000658299,0.002386888,0.005610649,0.0005987318,0.002688258,0.001349382,0.002730869,0.00166329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007155774,"about_ca_system_score_gemma":0.001230108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006937715,"about_ca_topic_score_gemma":0.006278155,"domain_scores_codex":[0.9493062,0.04480658,0.001084514,0.002120448,0.002243699,0.0004385458],"domain_scores_gemma":[0.784122,0.1924188,0.007942911,0.007779472,0.007238776,0.000498054],"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":[0.002189266,0.001038043,0.2203121,0.001130095,0.003148456,0.0006095589,0.005384243,0.1060365,0.01232934,0.01720651,0.005826845,0.624789],"study_design_scores_gemma":[0.0001726613,0.00183875,0.07227311,0.0002717504,0.0007602227,0.0005886003,0.001146354,0.8956475,0.006311596,0.01478573,0.005971241,0.0002325003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1542628,0.0002376466,0.8382488,0.0001739249,0.000108935,0.0008729113,0.0007374007,0.002783603,0.002574039],"genre_scores_gemma":[0.5544535,0.0002437967,0.4403354,0.00009071834,0.00005335671,0.001299517,0.001198814,0.001056834,0.001268069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04071942,"threshold_uncertainty_score":0.2153475,"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."}}