{"id":"W4406788559","doi":"10.1016/j.jss.2025.112353","title":"Automatic instantiation of assurance cases from patterns using large language models","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; École de Technologie Supérieure; York University","funders":"Mitacs; York University","keywords":"Computer science; Programming language; Software engineering; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003690455,0.001145344,0.0004994746,0.001242261,0.0005267037,0.002001838,0.001502806,0.001078534,0.003240775],"category_scores_gemma":[0.01944613,0.0008763023,0.002241514,0.0006350172,0.001022517,0.002555564,0.00335812,0.001678887,0.001058085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008419417,"about_ca_system_score_gemma":0.001542615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001735193,"about_ca_topic_score_gemma":0.003196511,"domain_scores_codex":[0.9960156,0.001543878,0.0003926861,0.000638185,0.001221585,0.0001880855],"domain_scores_gemma":[0.9886124,0.007288321,0.0008902084,0.002306039,0.0007227425,0.0001802184],"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":[0.0007046677,0.001029001,0.0253431,0.001851671,0.0003343472,0.005177141,0.006496166,0.2229548,0.1102063,0.08620968,0.01441865,0.5252745],"study_design_scores_gemma":[0.0001308164,0.0001931887,0.001326142,0.000186966,0.0001209796,0.001018406,0.0004636937,0.8849203,0.046204,0.03334669,0.03201433,0.0000744409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07765557,0.0001448149,0.9018059,0.0004268014,0.00004789509,0.0006057478,0.0008423308,0.01512257,0.003348425],"genre_scores_gemma":[0.2276631,0.0001370911,0.7651871,0.0001866202,0.00001459447,0.0003671322,0.003024116,0.001838405,0.001581758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003690455,"threshold_uncertainty_score":0.01951718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01140233925048323,"score_gpt":0.2290072410788513,"score_spread":0.217604901828368,"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."}}