{"id":"W2170240781","doi":"10.1016/j.watres.2010.05.019","title":"Novel application of a statistical technique, Random Forests, in a bacterial source tracking study","year":2010,"lang":"en","type":"article","venue":"Water Research","topic":"Fecal contamination and water quality","field":"Environmental Science","cited_by":82,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Texas Department of State Health Services; Texas General Land Office; National Oceanic and Atmospheric Administration; Canadian Centre for Applied Research in Cancer Control","keywords":"Random forest; Linear discriminant analysis; Sampling (signal processing); Environmental science; Veterinary medicine; Mathematics; Statistics; Biology; Physics; Artificial intelligence; Medicine; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003670472,0.00006546331,0.0001251354,0.00008492333,0.00006411949,0.00003387384,0.0002377673,0.00005965172,0.0007937393],"category_scores_gemma":[0.0001304808,0.00004590644,0.00001713541,0.0001659613,0.000220933,0.0001059313,0.0002224917,0.0003564961,0.0001092538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004939006,"about_ca_system_score_gemma":0.000006747242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004017675,"about_ca_topic_score_gemma":0.005567239,"domain_scores_codex":[0.9984384,0.0002492347,0.0002567559,0.0002503706,0.0005241441,0.0002810682],"domain_scores_gemma":[0.9995832,0.00007195701,0.0000204625,0.0002343309,0.00002609738,0.00006393116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001771284,0.0005028784,0.1156464,0.000009243781,0.000001733374,0.000001881595,0.001532219,0.000007629634,0.8731439,0.00008343044,0.00002374012,0.008869835],"study_design_scores_gemma":[0.003076386,0.000255478,0.6668155,0.000006488553,0.000003184401,0.00000397851,0.0002383764,0.001925862,0.3226725,0.001419334,0.003436903,0.0001460273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9358758,2.081786e-7,0.06245105,0.00009197131,0.00002045333,0.001047523,0.000005635938,0.00001327941,0.0004940988],"genre_scores_gemma":[0.9985617,1.092573e-7,0.0009614943,0.000005848292,0.00002076059,0.0002586093,0.00001425692,0.000008721298,0.0001684471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.551169,"threshold_uncertainty_score":0.8690888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059769811739862,"score_gpt":0.3717241681816979,"score_spread":0.3211264700642993,"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."}}