{"id":"W4411272401","doi":"10.1109/icse-companion66252.2025.00067","title":"Consistent Graph Model Generation with Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Language model; Graph; Natural language processing; Programming language; Theoretical computer science","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":[0.002823347,0.001052051,0.0006686969,0.001639617,0.0007383125,0.001398644,0.002281646,0.001198902,0.003243366],"category_scores_gemma":[0.01726134,0.0007134656,0.002036157,0.00127708,0.0009284216,0.002946421,0.003280118,0.001911222,0.001038211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001081085,"about_ca_system_score_gemma":0.002207967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003189454,"about_ca_topic_score_gemma":0.008333587,"domain_scores_codex":[0.9962397,0.001549371,0.0001848467,0.0006212101,0.001269425,0.0001355773],"domain_scores_gemma":[0.9890673,0.006271725,0.0004528536,0.002663432,0.001378264,0.0001663864],"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":[0.0001789325,0.0002730251,0.003307172,0.0007684237,0.0001789646,0.001100231,0.001318676,0.4909902,0.01713077,0.1332997,0.01758829,0.3338657],"study_design_scores_gemma":[0.00004148224,0.00003687013,0.000131629,0.00003440652,0.00003839591,0.0001352711,0.000115046,0.891381,0.005967902,0.09411781,0.007980546,0.00001968927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008171462,0.00005958123,0.9884595,0.0001941699,0.00002141321,0.0001235757,0.0002507968,0.001933067,0.0007864903],"genre_scores_gemma":[0.1589513,0.0001502434,0.8342832,0.000229312,0.00002382364,0.0004043847,0.002867232,0.001250578,0.001839833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003243366,"threshold_uncertainty_score":0.0149315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01479721996021756,"score_gpt":0.2373932888620447,"score_spread":0.2225960689018271,"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."}}