{"id":"W4416677538","doi":"10.1109/models67397.2025.00014","title":"MCeT: Behavioral Model Correctness Evaluation using Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Correctness; Sequence diagram; Documentation; Natural language; Automation; Sequence (biology); Hallucinating; Behavioral modeling; Data modeling","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":[0.01003692,0.001372628,0.0006280076,0.003422332,0.0006726576,0.001744718,0.001905848,0.001124009,0.004569073],"category_scores_gemma":[0.07703894,0.0005577296,0.001034433,0.00130461,0.0007973907,0.003640159,0.002350674,0.0009749528,0.000774165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001343247,"about_ca_system_score_gemma":0.002019095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006184259,"about_ca_topic_score_gemma":0.006823024,"domain_scores_codex":[0.9860169,0.005893466,0.001101399,0.001167517,0.005460307,0.0003603605],"domain_scores_gemma":[0.9281676,0.04818778,0.004185011,0.009795477,0.009043608,0.0006205775],"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":[0.002079782,0.001432878,0.0541728,0.001333995,0.0006949128,0.001307256,0.002246156,0.4046874,0.06153068,0.03477797,0.02270526,0.4130309],"study_design_scores_gemma":[0.000114475,0.0002518662,0.002735569,0.00005291869,0.00004193165,0.0001645804,0.0001437522,0.9612707,0.02615703,0.004923905,0.004100083,0.00004315951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2574638,0.0002347228,0.6909208,0.0002860825,0.00009406536,0.0004663828,0.001799189,0.04267245,0.006062509],"genre_scores_gemma":[0.6009358,0.00007022916,0.3911358,0.00008699827,0.00001676625,0.0003577838,0.003679315,0.002182739,0.001534542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01003692,"threshold_uncertainty_score":0.05308092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09302292773906319,"score_gpt":0.4021141141634302,"score_spread":0.309091186424367,"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."}}