{"id":"W7125587093","doi":"10.1109/cascon66301.2025.00082","title":"From Requirements to Models: A Case Study of Large Language Models on Epidemiological Modeling","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Wellcome Trust","keywords":"Representation (politics); Modeling language; Key (lock); Language model; Data modeling; Transmission (telecommunications)","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":[0.01075828,0.0008286487,0.0004748104,0.001003822,0.001326123,0.002726027,0.00198071,0.002102009,0.004196212],"category_scores_gemma":[0.0397827,0.0006567436,0.001398228,0.00111405,0.001841578,0.004137865,0.003383711,0.002478977,0.0006546658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002617639,"about_ca_system_score_gemma":0.002618387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007810336,"about_ca_topic_score_gemma":0.008203619,"domain_scores_codex":[0.9894843,0.007860554,0.0004490108,0.0004816192,0.001404406,0.0003201721],"domain_scores_gemma":[0.9231902,0.06818462,0.001389008,0.004055251,0.002582157,0.0005987942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006637793,0.0008706346,0.01298287,0.001447573,0.0001390211,0.01005968,0.02123937,0.477091,0.01816427,0.358347,0.009290769,0.08970398],"study_design_scores_gemma":[0.0001441662,0.0003289062,0.00204608,0.0003292191,0.0001016933,0.00188407,0.005368727,0.7967553,0.0181485,0.09301097,0.0817804,0.00010196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2937734,0.0003807365,0.6747159,0.004925111,0.00006387581,0.0007262464,0.000999508,0.002431835,0.02198333],"genre_scores_gemma":[0.6308184,0.0003432633,0.3620967,0.0004798351,0.00003007734,0.000448836,0.0008735572,0.0009132799,0.003996092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01075828,"threshold_uncertainty_score":0.05689591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1861507294007786,"score_gpt":0.395080489789336,"score_spread":0.2089297603885574,"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."}}