{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001251656,0.0001140566,0.0001093738,0.0001376432,0.00005732802,0.0000767829,0.0003671932,0.00004798056,0.000002712611],"category_scores_gemma":[0.000001169902,0.0000919821,0.00003577305,0.0002585207,0.00001287256,0.0003411006,0.0001402101,0.00007840768,0.000002251584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003387067,"about_ca_system_score_gemma":0.00005921216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001971428,"about_ca_topic_score_gemma":0.00002369368,"domain_scores_codex":[0.999244,0.00001456583,0.0001233032,0.0002817128,0.000153661,0.0001827624],"domain_scores_gemma":[0.9993026,0.000009255781,0.00002172262,0.0005560452,0.00007169232,0.00003869196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.548052e-7,0.00002146499,0.00001252792,0.00000592785,0.00000988587,0.000003823251,0.0001845378,0.1702747,0.0005767857,0.8248444,0.001394296,0.002670853],"study_design_scores_gemma":[0.000147655,0.00001647807,0.000005117473,0.00001537301,0.000004515759,0.000003530341,0.000002477281,0.9888414,0.004939435,0.005434235,0.0004751175,0.0001146812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001874036,0.00008690309,0.9920541,0.0002414654,0.00004781242,0.0001584687,0.000002773478,0.001227884,0.004306522],"genre_scores_gemma":[0.3974053,0.000005484789,0.6010536,0.0003587181,0.000005775385,0.00003203762,0.000003348192,0.000004838467,0.001130927],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8194101,"threshold_uncertainty_score":0.3750921,"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."}}