{"id":"W4416677557","doi":"10.1109/models67397.2025.00018","title":"Accurate and Consistent Graph Model Generation from Text with Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); McGill University","funders":"","keywords":"Graph; Language model; Probabilistic logic; Constraint (computer-aided design); Consistency (knowledge bases); Graphical model; Syntax","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":[0.003249528,0.001953498,0.0009713674,0.003240014,0.0008513603,0.001952503,0.003027063,0.001911755,0.00282274],"category_scores_gemma":[0.02445703,0.0006947489,0.00280577,0.00262293,0.0008165735,0.004006482,0.002196846,0.002170433,0.002058194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001547006,"about_ca_system_score_gemma":0.002719002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110875,"about_ca_topic_score_gemma":0.02663117,"domain_scores_codex":[0.9967021,0.001296462,0.0002149426,0.0008031438,0.0008714838,0.0001117741],"domain_scores_gemma":[0.9851766,0.009970794,0.000588428,0.002563559,0.001532825,0.0001678766],"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":[0.0003683672,0.0003801317,0.007195397,0.00195993,0.0004721933,0.001468141,0.00109408,0.4574077,0.014713,0.02734433,0.06345014,0.4241466],"study_design_scores_gemma":[0.00007386018,0.00003767268,0.0004326481,0.00005997385,0.00007124584,0.0001747168,0.0001683318,0.945741,0.006879873,0.03438503,0.01194036,0.00003526104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02775217,0.0006818958,0.92883,0.001026596,0.0001423497,0.0003853453,0.006572348,0.03280847,0.001800892],"genre_scores_gemma":[0.1779472,0.0005889724,0.7684636,0.0005218763,0.00007007824,0.0005152321,0.04598001,0.003638445,0.002274719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0110875,"threshold_uncertainty_score":0.02204597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03510477081533805,"score_gpt":0.258425097175378,"score_spread":0.2233203263600399,"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."}}