{"id":"W4391212444","doi":"10.48550/arxiv.2401.12566","title":"Automated Fact-Checking of Climate Change Claims with Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; University of Oxford; Strong; Fetzer Institute; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Viewpoints; Skepticism; Perspective (graphical); Computer science; Scientific consensus; Climate science; Process (computing); Climate change; Denial; Data science; Interpretation (philosophy); Scientific evidence; Subject (documents); Management science; Engineering ethics; Epistemology; Global warming; Psychology; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02906994,0.001315342,0.001371971,0.006161109,0.002114906,0.007632275,0.00376231,0.002382524,0.008672443],"category_scores_gemma":[0.1572915,0.001153875,0.003312123,0.002450982,0.002546705,0.009910656,0.007355753,0.004093251,0.002308589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002970552,"about_ca_system_score_gemma":0.006861042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009510791,"about_ca_topic_score_gemma":0.01789323,"domain_scores_codex":[0.9710731,0.01733192,0.00209446,0.003081399,0.005862771,0.0005563487],"domain_scores_gemma":[0.765963,0.2031521,0.009254245,0.01360501,0.006697031,0.001328593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001324429,0.0007473634,0.02572844,0.002319548,0.00111265,0.001992151,0.0088217,0.2878425,0.01194287,0.2532714,0.04346762,0.3614293],"study_design_scores_gemma":[0.0000933562,0.00004557305,0.0008567865,0.0001579983,0.00008214422,0.0001228481,0.000577184,0.852817,0.004573947,0.12479,0.01582205,0.00006110177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04152285,0.0004179722,0.92101,0.003812755,0.0001835149,0.000909926,0.004247967,0.0210629,0.006832123],"genre_scores_gemma":[0.3131456,0.0001919968,0.6753748,0.0006622773,0.0001382278,0.0006317861,0.007103089,0.0009968439,0.001755432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02906994,"threshold_uncertainty_score":0.1537384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08533069768617459,"score_gpt":0.4266853824551451,"score_spread":0.3413546847689706,"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."}}