{"id":"W2582501968","doi":"10.1093/trstmh/trx043","title":"Use of Bayesian networks in predicting contamination of drinking water with E. coli in rural Vietnam","year":2017,"lang":"en","type":"article","venue":"Transactions of the Royal Society of Tropical Medicine and Hygiene","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Contamination; Water contamination; Environmental science; Bayesian network; Environmental health; Geography; Water resource management; Biology; Ecology; Mathematics; Statistics; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0001714615,0.00007825786,0.0002846303,0.00003370009,0.0000859211,0.000008792794,0.0003183844,0.00006916837,0.000004022756],"category_scores_gemma":[0.0000186014,0.00004597867,0.00006450797,0.00008562978,0.0003874475,0.0001567747,0.00003021448,0.0001773094,1.397372e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000136719,"about_ca_system_score_gemma":0.00002056978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001043468,"about_ca_topic_score_gemma":0.0002166013,"domain_scores_codex":[0.9991766,0.00003971286,0.000347986,0.000115661,0.0001891595,0.000130895],"domain_scores_gemma":[0.9993441,0.0000811603,0.0001743954,0.0002858146,0.00008457449,0.00003001053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002440951,0.0005537462,0.7640591,0.0005636647,0.0001722485,0.000001893826,0.01664944,0.125217,0.008345357,0.002644464,0.00002684259,0.08152217],"study_design_scores_gemma":[0.0008526396,0.0002981401,0.3596235,0.0008023608,0.00002755029,0.000001085093,0.0002705692,0.6346897,0.003163109,0.0002159204,0.0000025297,0.00005290223],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5077863,0.00003265396,0.491171,0.0008848835,0.00003628764,0.0000677878,5.452281e-7,0.000003263439,0.00001733067],"genre_scores_gemma":[0.9942888,0.00005224405,0.005598018,0.00002158734,0.00001311924,0.000003474086,3.47662e-7,0.000003264538,0.00001915162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5094727,"threshold_uncertainty_score":0.1874956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02321314134233458,"score_gpt":0.2482474513843707,"score_spread":0.2250343100420361,"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."}}