{"id":"W2784636304","doi":"10.3390/atmos9030086","title":"Evaluation of Analysis by Cross-Validation. Part I: Using Verification Metrics","year":2018,"lang":"en","type":"article","venue":"Atmosphere","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Statistics; Correlation; Variance (accounting); Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001752381,0.00006429123,0.00009651673,0.000004641968,0.0001428772,0.0000261964,0.0001020392,0.00005146137,0.002214596],"category_scores_gemma":[0.0002899843,0.00006433018,0.00005048651,0.001137954,0.0001421519,0.0001836235,0.00003814498,0.00003554134,0.00008021167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001983513,"about_ca_system_score_gemma":0.0000134497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006377154,"about_ca_topic_score_gemma":0.00001466261,"domain_scores_codex":[0.9986333,0.0001241923,0.0002274016,0.0001948594,0.0007061777,0.0001140473],"domain_scores_gemma":[0.9993934,0.00003536732,0.0001863874,0.0002305537,0.0001185335,0.00003577425],"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":[0.000005714424,0.00005822557,0.8693993,0.000003863955,0.000118287,5.563088e-8,0.0004081496,0.07052028,0.006138977,0.00001441819,0.0007668374,0.05256586],"study_design_scores_gemma":[0.0002456266,0.00005530964,0.1668153,0.000008515195,0.0009078376,3.998016e-7,0.0001851783,0.7877106,0.04145918,0.0002083545,0.002236969,0.0001667454],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9853863,0.00005185536,0.0115466,0.00001016666,0.0001224838,0.00007442806,0.000005714967,0.0000173241,0.002785167],"genre_scores_gemma":[0.9938333,0.000002690531,0.005842643,0.000006946747,0.00007340334,0.000003780762,0.00001683211,0.000006114032,0.0002142919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7171903,"threshold_uncertainty_score":0.9986975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08331941688392652,"score_gpt":0.3547576143085165,"score_spread":0.27143819742459,"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."}}