{"id":"W2230887875","doi":"10.1080/10888438.2015.1107073","title":"The Random Forests statistical technique: An examination of its value for the study of reading","year":2016,"lang":"en","type":"article","venue":"Scientific Studies of Reading","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Reading (process); Computer science; Random forest; Statistical analysis; Value (mathematics); Statistics; Artificial intelligence; Machine learning; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005625145,0.0001339015,0.0003712152,0.0002112855,0.0006265735,0.00005650282,0.001191704,0.00002972005,6.90354e-7],"category_scores_gemma":[0.00262273,0.00006351219,0.00008044647,0.0007180067,0.0006618169,0.0004280414,0.000381981,0.0000518974,3.873511e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000600706,"about_ca_system_score_gemma":0.00003195294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007264964,"about_ca_topic_score_gemma":0.00006586709,"domain_scores_codex":[0.9978935,0.0002175406,0.0006036109,0.0004337087,0.0005984955,0.000253124],"domain_scores_gemma":[0.9928188,0.004800117,0.0005465073,0.0008948438,0.0009089899,0.00003072895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001126794,0.000408231,0.001530901,0.0001609145,0.0005057239,0.000001793495,0.0119029,0.0001360155,0.1937785,0.2099987,0.0008667946,0.5805969],"study_design_scores_gemma":[0.002750124,0.001959498,0.01200564,0.0007698658,0.0003801917,0.00000509582,0.01156336,0.02331621,0.8872185,0.05854448,0.0009987445,0.000488312],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06508529,0.0003818865,0.9326547,0.00009692932,0.0002664528,0.001365132,0.00001166216,0.00006101234,0.00007693116],"genre_scores_gemma":[0.9708036,0.00007808747,0.02864284,0.000001736779,0.00001642231,0.0002262699,6.675174e-7,0.000008559219,0.0002218847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9057183,"threshold_uncertainty_score":0.481916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04712200114569937,"score_gpt":0.3674317793021761,"score_spread":0.3203097781564768,"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."}}