{"id":"W2309564712","doi":"10.2166/aqua.2003.0020","title":"Predicting trihalomethane formation in chlorinated waters using multivariate regression and neural networks","year":2003,"lang":"en","type":"article","venue":"Journal of Water Supply Research and Technology—AQUA","topic":"Water Systems and Optimization","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"U.S. Geological Survey","keywords":"Icon; Multivariate statistics; Trihalomethane; Computer science; Art; Library science; Chemistry; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113552,0.0001289416,0.0002483554,0.001159259,0.0001057785,0.00008170003,0.0001010805,0.0002182433,0.000004289318],"category_scores_gemma":[0.00006880608,0.00008356918,0.00001972037,0.0004488223,0.00007943583,0.0005718574,0.00005451874,0.0006614758,4.312624e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007776933,"about_ca_system_score_gemma":0.000006715394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003235281,"about_ca_topic_score_gemma":0.00001681056,"domain_scores_codex":[0.9986487,0.000112143,0.0004590545,0.0001199657,0.000206403,0.0004537534],"domain_scores_gemma":[0.9995326,0.00003825529,0.00006164794,0.0001010005,0.0001784172,0.00008811993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009539577,0.0003112495,0.2903391,0.001327463,0.0003595088,0.001828106,0.008496848,0.2595769,0.4109063,0.0005194673,0.0006862913,0.02469477],"study_design_scores_gemma":[0.002424492,0.0004237624,0.0007707356,0.0004227716,0.00001104977,0.001241541,0.0008132028,0.7823503,0.2103884,0.0007201699,0.000246882,0.0001867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946688,0.0007882642,0.003889339,0.0001992406,0.0001875315,0.0001857628,0.000001261516,0.00004249557,0.00003727439],"genre_scores_gemma":[0.9984837,0.0002936538,0.001110334,0.000001705045,0.00004494131,0.000005064398,0.000003699864,0.0000194232,0.00003750262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5227734,"threshold_uncertainty_score":0.3407852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02977981541679899,"score_gpt":0.2757154240256673,"score_spread":0.2459356086088684,"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."}}