{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002356057,0.001959534,0.0007168599,0.00556691,0.0009431901,0.001439278,0.001681692,0.00201662,0.005779827],"category_scores_gemma":[0.01015137,0.0006505756,0.001140464,0.002862975,0.0007390537,0.002818763,0.002014392,0.002464291,0.005557678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001444549,"about_ca_system_score_gemma":0.002366563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008403698,"about_ca_topic_score_gemma":0.01597756,"domain_scores_codex":[0.9981703,0.0005560771,0.0001992066,0.0006690723,0.0002916748,0.0001136969],"domain_scores_gemma":[0.9931764,0.003863606,0.0003503286,0.0009869756,0.001405477,0.0002172263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005919612,0.001258049,0.01656497,0.003979321,0.0002096563,0.002389447,0.002533833,0.02850537,0.05183275,0.01189313,0.2749335,0.6053081],"study_design_scores_gemma":[0.0003583166,0.0004165911,0.02921018,0.001114418,0.0002973366,0.001633612,0.003320823,0.4200005,0.0790154,0.0176795,0.446705,0.0002483627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2344138,0.003775963,0.4371344,0.002043207,0.0010266,0.001679886,0.2571525,0.04255415,0.02021969],"genre_scores_gemma":[0.1506724,0.0008123267,0.339808,0.0003652045,0.00009290253,0.002941581,0.4977593,0.001802149,0.005746122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008403698,"threshold_uncertainty_score":0.01933545,"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."}}