{"id":"W4385641099","doi":"10.2749/istanbul.2023.0285","title":"New challenges in the IABSE TG3.1 benchmark on super long span bridge aerodynamics","year":2023,"lang":"en","type":"article","venue":"Report","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Rowan Williams Davies & Irwin (Canada)","funders":"","keywords":"Aerodynamics; Benchmark (surveying); Bridge (graph theory); Thunderstorm; Computer science; Wind tunnel; Span (engineering); Wind speed; Computation; Aeroelasticity; Meteorology; Structural engineering; Simulation; Aerospace engineering; Engineering; Geology; Geography; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0004892363,0.0001050136,0.0001123203,0.00002611782,0.00008905072,0.00001660138,0.0001684853,0.00003702239,0.0001955467],"category_scores_gemma":[0.00005495972,0.00007039318,0.00004982499,0.000233235,0.00004798897,0.00006927492,0.0001293622,0.0001162172,0.0005932853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005306469,"about_ca_system_score_gemma":0.0000097824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005414828,"about_ca_topic_score_gemma":0.001813551,"domain_scores_codex":[0.9989327,0.00002645674,0.000173453,0.0002849105,0.0003336869,0.0002488416],"domain_scores_gemma":[0.9995286,0.00005543524,0.00003761331,0.0003336977,0.000002195956,0.00004244848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001070429,0.0001136566,0.8726321,0.00001597753,0.00002047263,0.003823898,0.003646425,0.001645976,0.0001710089,0.0002619464,0.05066912,0.0669887],"study_design_scores_gemma":[0.00007271634,0.00003294586,0.9751554,0.00001412991,0.000003742262,0.00007334507,0.0002230098,0.00009848335,0.00001719846,0.0002447623,0.02396879,0.00009554245],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.932062,0.00008720504,0.000009274323,0.00542966,0.0001769404,0.0001244592,0.000001308137,0.00004615318,0.06206303],"genre_scores_gemma":[0.9959233,0.0004477178,0.00002918357,0.0001598228,0.000128763,0.00001032812,0.00001037784,0.000009441529,0.003281108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1025232,"threshold_uncertainty_score":0.7625679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04506573247890022,"score_gpt":0.2653204124326345,"score_spread":0.2202546799537343,"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."}}