{"id":"W2949344517","doi":"10.1016/j.mex.2019.06.005","title":"Improving long-term air pollution estimates with incomplete data: A method-fusion approach","year":2019,"lang":"en","type":"article","venue":"MethodsX","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Outlier; Air pollution; Pollution; Environmental science; Series (stratigraphy); Sensor fusion; Computer science; Time series; Statistics; Econometrics; Mathematics; Machine learning; Geology","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":[0.003438603,0.0002013976,0.0003045654,0.0000475898,0.0002242786,0.0000357637,0.0005024747,0.0001056173,0.0003915193],"category_scores_gemma":[0.0001775288,0.0001516833,0.00003093958,0.0002998584,0.0001393663,0.0006712142,0.0006837898,0.0002483563,0.0002891535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001705052,"about_ca_system_score_gemma":0.00004604833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001989805,"about_ca_topic_score_gemma":0.00006341773,"domain_scores_codex":[0.9976646,0.0005523688,0.0002770681,0.0006445095,0.0003803024,0.0004811678],"domain_scores_gemma":[0.9984041,0.0002541551,0.0001927218,0.0009331336,0.000008065011,0.0002078502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003975951,0.0003484529,0.1832177,0.0007557701,0.00004622262,0.00001451518,0.002577132,0.01525377,0.02376875,0.0004675625,0.001373174,0.7717794],"study_design_scores_gemma":[0.000949824,0.0003830822,0.7467331,0.00007078927,0.00006645744,0.00007563752,0.0001404617,0.2442749,0.002179148,0.0007051945,0.003902457,0.000518947],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1165195,0.00004717219,0.8792069,0.0007843238,0.0001051894,0.0005439852,0.0000203066,0.00009651067,0.002676161],"genre_scores_gemma":[0.07361338,0.000005512867,0.9237199,0.002139001,0.00005465,0.00001236833,0.00006637828,0.00002473503,0.0003640903],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7712604,"threshold_uncertainty_score":0.6185465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09930749654113749,"score_gpt":0.3849800446979307,"score_spread":0.2856725481567932,"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."}}