{"id":"W4415974165","doi":"10.1016/j.procs.2025.09.440","title":"Towards automatic extraction of UML class diagrams: Creation of an annotated dataset for training deep models","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Unified Modeling Language; Class diagram; Automation; Applications of UML; Schema (genetic algorithms); Software; Structuring","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":[0.001096129,0.0001381061,0.0002504232,0.0003829497,0.0001425986,0.0001477219,0.001507094,0.00005401632,8.726273e-7],"category_scores_gemma":[0.0001281338,0.0001334312,0.00004310456,0.001228089,0.0001879771,0.002499926,0.0002734837,0.00008102154,4.328272e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006155189,"about_ca_system_score_gemma":0.0006058104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003243624,"about_ca_topic_score_gemma":0.00001233784,"domain_scores_codex":[0.9980884,0.00003421074,0.0004997503,0.0006124582,0.0004554305,0.0003097217],"domain_scores_gemma":[0.9984453,0.0001268835,0.0002621305,0.0006431214,0.000434779,0.00008773429],"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":[0.000007014276,0.0001164096,0.00004000478,0.0002151395,0.00001020127,7.989426e-7,0.003355688,0.06281187,0.003655913,0.04671262,0.00003867886,0.8830357],"study_design_scores_gemma":[0.0002765125,0.0001143617,0.0008195778,0.00008335588,0.00000964831,0.00000585633,0.00003707683,0.9747723,0.00572752,0.01799885,0.00003803097,0.0001168516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05734121,0.00002939273,0.9413199,0.000222491,0.0004542088,0.0003858165,0.00002843151,0.00009913735,0.000119423],"genre_scores_gemma":[0.5666856,0.000001887071,0.433156,0.00007775145,0.00002775719,0.00002559726,0.00002042903,0.000002895132,0.000002081282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9119605,"threshold_uncertainty_score":0.5441166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04597214538598426,"score_gpt":0.3260006784343023,"score_spread":0.280028533048318,"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."}}