{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005452977,0.003626729,0.001026562,0.003891311,0.001294932,0.002528829,0.00396827,0.002892681,0.0112301],"category_scores_gemma":[0.02419538,0.0006816825,0.001609933,0.003481126,0.001064959,0.005254787,0.003319424,0.00264796,0.00746231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002197232,"about_ca_system_score_gemma":0.003140029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02424705,"about_ca_topic_score_gemma":0.03675343,"domain_scores_codex":[0.9939313,0.002526588,0.0007068756,0.001292177,0.001172076,0.0003710371],"domain_scores_gemma":[0.9887328,0.006988111,0.0003978555,0.00174668,0.001642343,0.0004922719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001201736,0.001913117,0.01242066,0.005089279,0.0007026638,0.0007334343,0.0009538108,0.08056412,0.01155529,0.008656965,0.54324,0.332969],"study_design_scores_gemma":[0.001049449,0.001437399,0.01444185,0.0004840312,0.0002573116,0.0007248634,0.001891552,0.7226714,0.03289398,0.03140664,0.192438,0.0003036596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.2539644,0.009207135,0.1601218,0.004897111,0.002625742,0.003407654,0.3472786,0.1633406,0.055157],"genre_scores_gemma":[0.2226554,0.001207622,0.1885146,0.001103349,0.0002510647,0.002555898,0.5715794,0.004121396,0.008011298],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02424705,"threshold_uncertainty_score":0.04821181,"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."}}