{"id":"W4293229571","doi":"10.1175/bams-d-21-0126.1","title":"The 2020 International Verification Methods Workshop Online: Major Outcomes and Way Forward","year":2022,"lang":"en","type":"article","venue":"Bulletin of the American Meteorological Society","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Environment and Climate Change Canada; Universität Wien","keywords":"Computer science; Representativeness heuristic; Software verification; Data assimilation; Data verification; Verification; Software; Data science; Data mining; Meteorology; Geography; Software system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001461592,0.0001324708,0.0002657583,0.00000970279,0.0008889063,0.0000376453,0.0007956967,0.00003464414,0.003344108],"category_scores_gemma":[0.0007241343,0.00006445407,0.000285803,0.0002661059,0.0008035429,0.00001571732,0.0002385987,0.0003596378,0.000009113392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001139327,"about_ca_system_score_gemma":0.00001309411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002749044,"about_ca_topic_score_gemma":0.00002025148,"domain_scores_codex":[0.9979029,0.000868427,0.0003268978,0.0002845527,0.0003732189,0.0002439626],"domain_scores_gemma":[0.9965665,0.002685139,0.0003421176,0.0002914008,0.00003869177,0.00007616073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004797197,0.0002118111,0.5496617,0.000007223749,0.0004673903,0.000001684125,0.0004056318,0.01666582,0.0004188782,0.001644203,0.04100484,0.3890311],"study_design_scores_gemma":[0.0001867825,0.0001645371,0.7526814,5.959116e-7,0.00003181485,0.000003037301,0.0009731043,0.005286836,0.000005891349,0.00316602,0.2374028,0.00009723485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9334299,0.0007969813,0.0008384596,0.06251878,0.0004409856,0.0003070995,0.0001567872,0.00004242104,0.001468576],"genre_scores_gemma":[0.9610808,0.0002407644,0.03174446,0.005741907,0.00006850322,0.00001447932,0.00003880581,0.00000378487,0.001066452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3889339,"threshold_uncertainty_score":0.997567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02111506724293009,"score_gpt":0.2871741818396746,"score_spread":0.2660591145967445,"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."}}