{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003499907,0.0003109873,0.0006501009,0.0002123197,0.000115786,0.00003429537,0.0004571366,0.0001826021,0.09724317],"category_scores_gemma":[0.01145926,0.000207569,0.0002092911,0.0002981297,0.00001242302,0.00009680955,0.0005613556,0.000592017,0.00005976323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428804,"about_ca_system_score_gemma":0.00008400373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003222459,"about_ca_topic_score_gemma":0.0001602484,"domain_scores_codex":[0.9979335,0.0003555726,0.0006543864,0.0004102303,0.0003589643,0.0002873631],"domain_scores_gemma":[0.9963607,0.002329715,0.0003908047,0.0006706318,0.0001078328,0.0001402874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001646572,0.00006478243,0.000001779115,0.0002024714,0.00004319076,0.00001918695,0.0007419682,0.01454868,0.00002775289,0.000002877402,0.9837222,0.000460419],"study_design_scores_gemma":[0.003494146,0.001120609,0.0006332307,0.04757578,0.0004798384,0.00001814314,0.001409884,0.1011208,0.000229939,0.03376916,0.8085805,0.001568021],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007060964,0.00003360729,0.01366863,0.00002851868,0.0001332831,0.0009849339,0.984408,0.00002571642,0.00001123163],"genre_scores_gemma":[0.0002585269,0.000005498177,0.02840703,0.00003674912,0.0001857282,0.0002672458,0.970759,0.00004765863,0.00003260915],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1751418,"threshold_uncertainty_score":0.9968677,"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."}}