{"id":"W4402400605","doi":"10.1007/978-3-031-70245-7_19","title":"Goal Model Extraction from User Stories Using Large Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Extraction (chemistry); Natural language processing; Information retrieval; Information extraction; Artificial intelligence; Chromatography; Chemistry","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":[0.0007943198,0.0002018804,0.0001897287,0.0009573301,0.00031455,0.001017706,0.002622906,0.0001372202,0.000004609092],"category_scores_gemma":[0.00005002633,0.0002091247,0.00004265104,0.0004186034,0.0002800654,0.01031076,0.002949096,0.0006387445,0.0000500434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003107166,"about_ca_system_score_gemma":0.0003324541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000057444,"about_ca_topic_score_gemma":0.00001505596,"domain_scores_codex":[0.9983709,0.00001400162,0.0004446981,0.0003127455,0.0005947857,0.0002628066],"domain_scores_gemma":[0.9972354,0.0003367252,0.0001221701,0.001952972,0.0002562386,0.00009646293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001500994,0.00001311957,0.00001856147,0.00003446131,0.00001007395,0.000001561681,0.008521796,0.0655686,0.00002531151,0.899255,0.000156054,0.02639396],"study_design_scores_gemma":[0.00009825768,0.000008779532,0.00006892993,0.0001592085,0.000004236229,0.000008644254,0.00002981676,0.9720424,0.00001128587,0.0174934,0.009865553,0.0002094208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005428346,0.000998135,0.9804975,0.000169257,0.0003917601,0.000207949,0.00005068859,0.0002275272,0.01691433],"genre_scores_gemma":[0.2297706,0.001551726,0.7636869,0.0003644668,0.000121047,0.00003600252,0.0001193345,0.00003482365,0.004315091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9064739,"threshold_uncertainty_score":0.9813759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06199237035249826,"score_gpt":0.343000401956136,"score_spread":0.2810080316036377,"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."}}