{"id":"W4415958513","doi":"10.48550/arxiv.2510.19886","title":"An Expert-grounded benchmark of General Purpose LLMs in LCA","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Environmental Impact and Sustainability","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; St Mary's Hospital Centre","funders":"","keywords":"Benchmark (surveying); Quality (philosophy); Field (mathematics); Hallucinating; Usability; Sophistication; Risk assessment","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2129252,0.001321829,0.001437236,0.01024615,0.001961713,0.005728223,0.003213518,0.002713145,0.002840896],"category_scores_gemma":[0.5338602,0.0007323386,0.001791454,0.005889184,0.00262012,0.005933822,0.007053047,0.001850701,0.0009229335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005020183,"about_ca_system_score_gemma":0.006403854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00309078,"about_ca_topic_score_gemma":0.005832579,"domain_scores_codex":[0.7618257,0.1729327,0.02364756,0.009243576,0.03079261,0.001557898],"domain_scores_gemma":[0.2683629,0.5230226,0.03406263,0.06747644,0.1039229,0.003152494],"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":[0.004997512,0.003170473,0.08032335,0.0269533,0.002107896,0.0008965316,0.06915278,0.0272992,0.02057468,0.01619617,0.02977287,0.7185553],"study_design_scores_gemma":[0.004807202,0.022704,0.2516036,0.04133536,0.00401623,0.002681666,0.05665982,0.1974235,0.07399022,0.079028,0.2636233,0.00212713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7802085,0.01087049,0.1529355,0.003740961,0.0004835195,0.01243363,0.005832472,0.003996461,0.02949848],"genre_scores_gemma":[0.7732266,0.001223583,0.2096603,0.001023144,0.0001659185,0.007375252,0.005456695,0.0006016851,0.001266744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2129252,"threshold_uncertainty_score":0.9706033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119877764453126,"score_gpt":0.2958000058968369,"score_spread":0.2746012282523056,"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."}}