{"id":"W4294797025","doi":"10.1371/journal.pwat.0000040","title":"Modelling point-of-consumption residual chlorine in humanitarian response: Can cost-sensitive learning improve probabilistic forecasts?","year":2022,"lang":"en","type":"article","venue":"PLOS Water","topic":"Water Systems and Optimization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research; York University","funders":"United Nations High Commissioner for Refugees; Natural Sciences and Engineering Research Council of Canada; Global Affairs Canada; Achmea; Enhancing Learning and Research for Humanitarian Assistance; Grand Challenges Canada; York University; Government of the United Kingdom; United States Agency for International Development","keywords":"Weighting; Statistics; Mean squared error; Residual; Probabilistic logic; Point estimation; Reliability (semiconductor); Econometrics; Computer science; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004153806,0.0001325134,0.000189639,0.0001973706,0.0001046034,0.00002336752,0.00007352816,0.0000422608,0.00006042749],"category_scores_gemma":[0.00001925766,0.0001213019,0.00002916466,0.00007695195,0.00001694366,0.0001134681,0.00006905646,0.0002749508,0.000008699013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002356118,"about_ca_system_score_gemma":0.00001195073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002219355,"about_ca_topic_score_gemma":0.0002419272,"domain_scores_codex":[0.9989058,0.0001442853,0.000319062,0.0001900239,0.0001727137,0.0002680854],"domain_scores_gemma":[0.9997039,0.00004255142,0.00003663357,0.0001365792,0.00004729455,0.00003300388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002103387,0.00002570711,0.0004489198,0.000107231,0.00002256874,0.00001877752,0.006937818,0.9828875,0.009216987,0.00003682256,0.00001703523,0.00007025967],"study_design_scores_gemma":[0.0004881861,0.0001336874,0.0002498209,0.00004561115,0.00001734291,0.000008861728,0.0002786245,0.961484,0.03681386,0.0000900126,0.000203358,0.0001866331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959701,0.000021283,0.00293585,0.0000624302,0.0002136331,0.0005333858,0.00002356139,0.0001031371,0.0001366113],"genre_scores_gemma":[0.9987476,0.000002430802,0.0002951599,0.000005596329,0.00005977275,0.0001544969,0.00009680796,0.0000452604,0.0005928639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02759687,"threshold_uncertainty_score":0.4946548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02395549242991967,"score_gpt":0.1954667394808121,"score_spread":0.1715112470508925,"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."}}