{"id":"W4411488587","doi":"10.1145/3744920","title":"On the Utility of Domain Modeling Assistance with Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Université de Montréal","funders":"","keywords":"Computer science; Modeling language; Domain (mathematical analysis); Usability; Software engineering; Domain analysis; Abstraction; Domain-specific language; Process (computing); Model-driven architecture; Context (archaeology); Subject-matter expert; Domain model; Software; Domain engineering; Human–computer interaction; Software development; Data science; Artificial intelligence; Domain knowledge; Programming language; Component-based software engineering; Software construction","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":[0.001257349,0.0001665249,0.0002480614,0.000239586,0.0001158074,0.00002463405,0.0005984764,0.0000974016,0.000008035432],"category_scores_gemma":[0.001334816,0.0001220742,0.0000567293,0.0005338114,0.00004168099,0.000105577,0.00003043449,0.0004439851,8.618549e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002727774,"about_ca_system_score_gemma":0.0000535537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000212528,"about_ca_topic_score_gemma":0.000006365871,"domain_scores_codex":[0.9987816,0.0001843076,0.0001831352,0.0003567987,0.0001887332,0.0003054254],"domain_scores_gemma":[0.9919388,0.006968928,0.00002461693,0.0009484467,0.00006477266,0.00005443805],"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":[0.0001134361,0.0001242256,0.0001292096,0.0001881843,0.000186164,0.00001446231,0.001880862,0.9054126,0.0004503145,0.06750542,0.0000402293,0.02395496],"study_design_scores_gemma":[0.0005905522,0.0001555842,0.0007592305,0.0001976701,0.00002208113,0.00001613147,0.0001676192,0.983182,0.003676652,0.01086326,0.0001364894,0.0002327971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07787291,0.0002514223,0.9209518,0.0002891121,0.0001630651,0.000139634,0.0000105572,0.0002975967,0.00002389244],"genre_scores_gemma":[0.5556725,0.00001460371,0.4441593,0.00005841318,0.000004220438,0.00003597685,4.445685e-7,0.000009155257,0.0000453491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4777996,"threshold_uncertainty_score":0.4978042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06253040734009754,"score_gpt":0.3178245270606738,"score_spread":0.2552941197205763,"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."}}