{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004447543,0.0002020371,0.0005135493,0.0006180635,0.0002211206,0.0001616113,0.0005069947,0.0002981754,0.0001079418],"category_scores_gemma":[0.0001254913,0.0001884246,0.0001868834,0.0003905403,0.0002827871,0.0001111022,0.001047026,0.001016218,0.000009939665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004975905,"about_ca_system_score_gemma":0.0005719876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001490214,"about_ca_topic_score_gemma":0.005418952,"domain_scores_codex":[0.9970919,0.0006355977,0.0004634505,0.0006255602,0.0004784879,0.0007049464],"domain_scores_gemma":[0.9985507,0.0005736778,0.0001851299,0.0003903678,0.0001617965,0.0001383562],"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":[0.0001336579,0.0003943478,0.007917454,0.001217939,0.0006638558,0.0001875459,0.09266254,0.06469949,0.00005880447,0.0740632,0.00003929849,0.7579619],"study_design_scores_gemma":[0.0005303505,0.00007842632,0.004160226,0.001117491,0.00007250252,0.000002395948,0.02047945,0.9175768,0.00005494151,0.05170919,0.003539937,0.0006783082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7408123,0.0006539733,0.00005281374,0.0006676654,0.0002999152,0.0008747042,0.0002159175,0.0002836318,0.2561391],"genre_scores_gemma":[0.9910005,0.005625194,0.002209878,0.00003076627,0.0002537587,0.0001287993,0.0000640039,0.00004077415,0.0006463247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8528773,"threshold_uncertainty_score":0.7683731,"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."}}