{"id":"W4416529367","doi":"10.1016/j.atmosenv.2025.121696","title":"Classifying ultrafine particle formation using machine learning on total number concentrations","year":2025,"lang":"en","type":"article","venue":"Atmospheric Environment","topic":"Coagulation and Flocculation Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ultrafine particle; Particle number; Particle (ecology); Particle size; Aerosol","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001010461,0.0001280517,0.0001122636,0.000001895538,0.0003859844,0.00002839459,0.00005332296,0.00003744646,0.00459505],"category_scores_gemma":[0.00002040199,0.0001225258,0.00004894741,0.0001773202,0.00009043083,0.0001894452,0.00008837209,0.0001046464,0.0006711542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003448914,"about_ca_system_score_gemma":0.000004007024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008627596,"about_ca_topic_score_gemma":0.00001380539,"domain_scores_codex":[0.9990391,0.00005625496,0.0002462944,0.0002213638,0.000237896,0.0001990809],"domain_scores_gemma":[0.9996676,0.00005178511,0.00007908019,0.0001492238,0.000002627894,0.00004967278],"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":[0.00001497559,0.00009033358,0.5075562,0.000003445491,0.00001739343,0.000001223599,0.0003390977,0.4794377,0.006675737,0.000575535,0.0002079849,0.005080338],"study_design_scores_gemma":[0.0005341309,0.00002890987,0.333788,0.0000133588,0.00002906397,0.000003296585,0.0002107864,0.6308271,0.001482056,0.00006863396,0.03284191,0.0001727584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554442,0.00004973075,0.03332631,0.0005960417,0.00008579461,0.0002118735,0.000001591476,0.00006089171,0.01022362],"genre_scores_gemma":[0.992844,0.00004274696,0.003592585,0.0003283676,0.00001611956,0.0000189097,0.00001017511,0.000008240439,0.003138793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1737682,"threshold_uncertainty_score":0.9963149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732901941714147,"score_gpt":0.2494830344804404,"score_spread":0.2321540150632989,"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."}}