{"id":"W3124232740","doi":"10.20944/preprints201801.0217.v1","title":"Evaluation of Analysis by Cross-Validation. Part I: Using Verification Metrics","year":2018,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Set (abstract data type); Error analysis; Variance (accounting); Moment (physics); Computer science; Statistics; Margin (machine learning); Algorithm; Mathematics; Applied mathematics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07091226,0.003583094,0.001513125,0.004669032,0.001054815,0.003403091,0.002487074,0.003184357,0.001750891],"category_scores_gemma":[0.2046627,0.00069254,0.002286653,0.00227661,0.002298102,0.003880101,0.00359779,0.003140917,0.0006332612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001977114,"about_ca_system_score_gemma":0.002330337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003406928,"about_ca_topic_score_gemma":0.003089002,"domain_scores_codex":[0.9424339,0.03544734,0.005064412,0.006462253,0.009607458,0.0009846347],"domain_scores_gemma":[0.7654072,0.1692641,0.01499697,0.02799011,0.0208461,0.001495454],"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":[0.002434701,0.001021253,0.1030755,0.00206594,0.005372579,0.0005664795,0.001218688,0.4966957,0.02665864,0.02598233,0.01138143,0.3235268],"study_design_scores_gemma":[0.000129493,0.0008738649,0.02103279,0.0002612325,0.0003355262,0.0003406147,0.0002645161,0.9304991,0.02439903,0.01774947,0.003987319,0.0001270177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1030252,0.002151676,0.8876597,0.0003909624,0.0003345184,0.0004818554,0.001179406,0.002452775,0.002323832],"genre_scores_gemma":[0.5416908,0.0002818412,0.4525464,0.0002480579,0.0001183565,0.00056945,0.00264987,0.001080791,0.0008144705],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07091226,"threshold_uncertainty_score":0.3750243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3687192818685479,"score_gpt":0.4427413703578471,"score_spread":0.07402208848929925,"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."}}