{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1156854,0.001468492,0.002162835,0.005674127,0.001503112,0.002490606,0.001703435,0.00182829,0.00243917],"category_scores_gemma":[0.2444715,0.0005647267,0.001884998,0.006434824,0.002702569,0.003723353,0.001796629,0.003559293,0.0006430743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000891483,"about_ca_system_score_gemma":0.002811923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00564093,"about_ca_topic_score_gemma":0.007270517,"domain_scores_codex":[0.9546769,0.03651902,0.001113534,0.00206305,0.005269033,0.0003585364],"domain_scores_gemma":[0.5790308,0.3993357,0.005000676,0.008267893,0.007350882,0.001014205],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008311365,0.0002468865,0.08258685,0.001687871,0.002353222,0.0006815543,0.003680529,0.06175264,0.00262362,0.09100565,0.01331787,0.7392322],"study_design_scores_gemma":[0.0002710486,0.001260592,0.06560376,0.002714894,0.0009141791,0.002457146,0.002110597,0.5126429,0.003654337,0.366918,0.04095934,0.0004932142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03267493,0.006465254,0.9527307,0.002163862,0.0003381699,0.0003618429,0.0004608508,0.0008896645,0.003914651],"genre_scores_gemma":[0.299451,0.003518767,0.6933197,0.00061108,0.0004284533,0.0007129695,0.0003683944,0.000603381,0.000986213],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8843147,"threshold_uncertainty_score":0.61181,"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."}}