{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009932929,0.001796056,0.0006655714,0.002430261,0.0007258035,0.002204871,0.001342159,0.001111497,0.006528834],"category_scores_gemma":[0.007442696,0.0008700039,0.001655579,0.0018027,0.0004609567,0.004262817,0.001680421,0.001868958,0.004234809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00090062,"about_ca_system_score_gemma":0.001161912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004626818,"about_ca_topic_score_gemma":0.007719589,"domain_scores_codex":[0.9988195,0.0004444575,0.0001020668,0.0002330989,0.0003380941,0.00006276435],"domain_scores_gemma":[0.9936957,0.004978153,0.0002163875,0.0003995464,0.00062977,0.00008053255],"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":[0.0006955823,0.0005385192,0.006851197,0.002878923,0.0003330582,0.003539944,0.006465464,0.04055451,0.04080633,0.02812134,0.09051475,0.7787004],"study_design_scores_gemma":[0.00009423971,0.0002087138,0.004065868,0.0007032244,0.0004048735,0.002511267,0.003672086,0.7134215,0.06343422,0.04718088,0.1641278,0.0001753866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04159257,0.00113572,0.9135197,0.001144573,0.0001432379,0.0004991181,0.01301527,0.01716491,0.01178501],"genre_scores_gemma":[0.2969874,0.001342212,0.6458663,0.0003599457,0.0000893918,0.0008226159,0.04198428,0.002610767,0.009937136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006528834,"threshold_uncertainty_score":0.02184111,"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."}}