{"id":"W4386100187","doi":"10.1175/bams-d-22-0253.1","title":"Verif: A Weather-Prediction Verification Tool for Effective Product Development","year":2023,"lang":"en","type":"article","venue":"Bulletin of the American Meteorological Society","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; BC Hydro","keywords":"Computer science; Initialization; Numerical weather prediction; New product development; Range (aeronautics); Set (abstract data type); Product (mathematics); Data mining; Fidelity; Weather prediction; Probabilistic logic; Weather forecasting; Machine learning; Industrial engineering; Data science; Artificial intelligence; Meteorology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01271335,0.003060946,0.001293347,0.004593748,0.0009925691,0.003495298,0.004362701,0.001955789,0.08165746],"category_scores_gemma":[0.06064943,0.002491703,0.002527621,0.001789815,0.0009524358,0.007277625,0.003832057,0.002772775,0.0330908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001375153,"about_ca_system_score_gemma":0.003074374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006486251,"about_ca_topic_score_gemma":0.004182453,"domain_scores_codex":[0.9942096,0.001213002,0.0007614081,0.0008900298,0.002537613,0.0003883516],"domain_scores_gemma":[0.9671268,0.01861387,0.001849852,0.004644624,0.007254,0.0005108158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00126596,0.0003158591,0.005491665,0.002290605,0.0002307737,0.001168824,0.0008522651,0.04121815,0.01183277,0.01595099,0.5548782,0.3645039],"study_design_scores_gemma":[0.001146147,0.0004234886,0.005737065,0.001895793,0.0001742354,0.00146976,0.0003394364,0.3122985,0.0582418,0.03896933,0.5785686,0.0007358262],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004221168,0.0003133436,0.4496263,0.0004035597,0.0003477655,0.0004385417,0.02086762,0.5172945,0.006487228],"genre_scores_gemma":[0.07497965,0.0005901453,0.6443757,0.0005760662,0.0001763451,0.001629365,0.08860541,0.1767491,0.01231835],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.08165746,"threshold_uncertainty_score":0.2731714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956740594176879,"score_gpt":0.2341202572377008,"score_spread":0.214552851295932,"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."}}