{"id":"W4411552861","doi":"10.1109/icse55347.2025.00140","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","year":2025,"lang":"en","type":"article","venue":"","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Programming language; Code generation; Process (computing); Code (set theory); Software engineering; Operating 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003098548,0.0002999275,0.0003254445,0.0003635703,0.0005960161,0.0005471435,0.0002543919,0.0001367629,0.00008516714],"category_scores_gemma":[0.00009059232,0.0002814798,0.0001152845,0.0009792075,0.00002174336,0.002115573,0.0001772932,0.0001588012,0.00001656621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004745623,"about_ca_system_score_gemma":0.00006550248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005044474,"about_ca_topic_score_gemma":0.0001101571,"domain_scores_codex":[0.9981689,0.000008420757,0.0004519118,0.0005516873,0.0003621282,0.0004569117],"domain_scores_gemma":[0.9990067,0.00001172909,0.0002193764,0.0002963591,0.0004489825,0.00001684534],"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":[0.000009006502,0.0001181576,0.001371484,0.0003653509,0.0000559911,0.00000249722,0.0001343331,0.9892687,0.002299397,0.002138877,0.002354636,0.001881557],"study_design_scores_gemma":[0.0004780538,7.947694e-7,0.000007416048,0.00009659943,0.0001790077,3.120639e-7,0.0003758536,0.9936356,0.000286906,0.004521455,0.0001002547,0.0003177579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3357395,0.0002154444,0.6613262,0.0002076328,0.00008010394,0.0001222212,0.00001271172,0.0003002642,0.001995931],"genre_scores_gemma":[0.9888507,0.000007554464,0.004810869,0.003413078,0.0003412844,0.00002394983,0.0002752407,0.00004776853,0.00222961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6565154,"threshold_uncertainty_score":0.9999638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04480364990843271,"score_gpt":0.30023183536439,"score_spread":0.2554281854559572,"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."}}