{"id":"W4394130195","doi":"10.6084/m9.figshare.20402389","title":"From Black Box to Shining Spotlight: Using Random Forest Prediction Intervals to Illuminate the Impact of Assumptions in Linear Regression","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of British Columbia","funders":"","keywords":"Random forest; Black box; Linear regression; Statistics; Regression; Econometrics; Mathematics; Environmental science; Computer science; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006165461,0.001028543,0.0006903345,0.002277752,0.0005211838,0.002732929,0.002037084,0.001543613,0.01082922],"category_scores_gemma":[0.03628066,0.0005026818,0.001011417,0.002473573,0.0005746347,0.002792427,0.002350223,0.002649156,0.007038502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006095722,"about_ca_system_score_gemma":0.0007342118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004739346,"about_ca_topic_score_gemma":0.01366302,"domain_scores_codex":[0.9974272,0.001397002,0.0001862318,0.0004552827,0.0004389627,0.00009529049],"domain_scores_gemma":[0.9734657,0.02180148,0.0007570032,0.002672722,0.001125077,0.0001780326],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008743318,0.0002097054,0.01566357,0.001466409,0.0001638195,0.000421836,0.000880865,0.03896426,0.001386098,0.03019366,0.7319505,0.1778251],"study_design_scores_gemma":[0.0008008151,0.0002276243,0.008459036,0.001074786,0.0000929767,0.0008511655,0.000581146,0.2764983,0.007575702,0.1548905,0.5487306,0.0002172779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.06862155,0.00791733,0.5075715,0.01229287,0.0018201,0.0004867936,0.2826504,0.09080655,0.02783298],"genre_scores_gemma":[0.1943116,0.002535725,0.5748844,0.003798681,0.0004865456,0.00157108,0.2042901,0.01034136,0.007780429],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.9938346,"threshold_uncertainty_score":0.03622735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2140695316718665,"score_gpt":0.47739924547586,"score_spread":0.2633297138039936,"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."}}