{"id":"W4389606799","doi":"10.1109/models58315.2023.00037","title":"Automated Domain Modeling with Large Language Models: A Comparative Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universidad de Murcia","keywords":"Domain (mathematical analysis); Computer science; Set (abstract data type); Modeling language; Domain-specific language; Subject-matter expert; Domain model; Class (philosophy); Domain analysis; Software; Domain knowledge; Natural language processing; Software engineering; Data science; Artificial intelligence; Programming language; Software development; Expert system","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":[0.0005073022,0.0001249983,0.0001622377,0.000231009,0.00009462488,0.0001351266,0.0006390332,0.00002511695,0.000007727161],"category_scores_gemma":[0.00002464983,0.0000938155,0.00002047256,0.001419689,0.000009805835,0.0003754085,0.0003480565,0.0001407783,0.0001904621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003987458,"about_ca_system_score_gemma":0.00005051626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007973948,"about_ca_topic_score_gemma":0.00005939099,"domain_scores_codex":[0.9985493,0.00006275035,0.0001251982,0.0003548863,0.0004856245,0.0004221795],"domain_scores_gemma":[0.9990907,0.0002068978,0.0000138598,0.000522231,0.00007565774,0.00009066951],"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":[0.00001041584,0.0002038291,0.0009144818,0.00001102559,0.00006911602,0.0002761322,0.04093379,0.9435676,0.00009281489,0.01288385,0.0009179722,0.0001189431],"study_design_scores_gemma":[0.0005626947,0.0001205775,0.0005304524,0.000009612448,0.000001485494,0.000004406457,0.004572167,0.9937187,0.00003636132,0.000302751,0.000006618054,0.0001341255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4703362,0.00001041239,0.5248312,0.00003841723,0.00002248634,0.0002035502,0.000001122593,0.004135458,0.0004211306],"genre_scores_gemma":[0.9690825,4.937483e-7,0.03051697,0.00001774214,0.00001245068,0.00006226806,0.000003147358,0.00001318011,0.0002912109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4987463,"threshold_uncertainty_score":0.3825685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05186317309112483,"score_gpt":0.3344085128492332,"score_spread":0.2825453397581084,"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."}}