{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1080788,0.002182823,0.0009928524,0.002058302,0.002275952,0.0101023,0.004288713,0.004719729,0.03913201],"category_scores_gemma":[0.05920987,0.0009042102,0.002627943,0.001091222,0.002038084,0.007846232,0.01170488,0.007424686,0.01745311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004307549,"about_ca_system_score_gemma":0.009796639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005201153,"about_ca_topic_score_gemma":0.003563432,"domain_scores_codex":[0.9666604,0.01458092,0.001182801,0.002030809,0.01212184,0.003423278],"domain_scores_gemma":[0.9187545,0.01406856,0.001497433,0.00761778,0.04637926,0.01168252],"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":[0.0007429495,0.0006544603,0.001301331,0.0003770792,0.00006792277,0.0002886648,0.0006052656,0.004607053,0.004253228,0.035983,0.7231005,0.2280184],"study_design_scores_gemma":[0.0002496922,0.0006871629,0.003106505,0.001192536,0.00005114727,0.0002468964,0.00123535,0.02032601,0.01055289,0.04551665,0.9166569,0.0001782456],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02290508,0.01290832,0.5609926,0.1745752,0.08869313,0.003147198,0.00772735,0.008378768,0.1206723],"genre_scores_gemma":[0.2213857,0.006577745,0.4061767,0.02757275,0.01700534,0.004065146,0.02868943,0.01033073,0.2781963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1080788,"threshold_uncertainty_score":0.5715823,"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."}}