{"id":"W7082278547","doi":"10.48448/jat9-fs09","title":"WXImpactBench: A Disruptive Weather Impact Understanding Benchmark for Evaluating Large Language Models","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Benchmark (surveying); Newspaper; Climate change; Set (abstract data type); Extreme weather; Adaptation (eye); Code (set theory)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002259661,0.0005103179,0.0005130498,0.0006557963,0.000556457,0.0004501326,0.002293795,0.0002992922,0.0005785607],"category_scores_gemma":[0.0007391765,0.0004175628,0.0002235957,0.001342151,0.0003453462,0.0005351334,0.000813207,0.0003585742,0.00001776732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006088978,"about_ca_system_score_gemma":0.001673998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002067387,"about_ca_topic_score_gemma":0.00009624651,"domain_scores_codex":[0.9962732,0.00007281827,0.0003866688,0.001272611,0.0008097724,0.001184928],"domain_scores_gemma":[0.9976539,0.0003315612,0.0004079753,0.001133162,0.0002308857,0.0002424949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004333768,0.0004481794,0.0001448361,0.0005826681,0.0003879055,0.00005483999,0.008586659,0.008523596,0.003498373,0.8045896,0.1553736,0.0177664],"study_design_scores_gemma":[0.0008323902,0.0002116728,0.0000100099,0.0005097046,0.00005025311,0.00001283271,0.001673813,0.8761052,0.000226967,0.1124167,0.00722496,0.0007255183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00002045833,0.0003130034,0.5988825,0.0004892544,0.0003170767,0.0005256896,0.0001217976,0.0002493794,0.3990808],"genre_scores_gemma":[0.3658206,0.00004571522,0.1248551,0.0006518094,0.0005171853,0.000126825,0.0001565371,0.0001099772,0.5077162],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8675816,"threshold_uncertainty_score":0.9998276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05835675538037455,"score_gpt":0.3621707965193668,"score_spread":0.3038140411389922,"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."}}