{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000198655,0.0001058212,0.0003572861,0.0001550546,0.0000234132,0.00002823162,0.00008108089,0.00007072984,0.00000372004],"category_scores_gemma":[0.00005610751,0.00009661369,0.00005580349,0.0001050006,0.000005806728,0.0002625464,0.00001340953,0.0001017945,2.699204e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007939686,"about_ca_system_score_gemma":0.0000360057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001802352,"about_ca_topic_score_gemma":0.00001114096,"domain_scores_codex":[0.9991037,0.00002571515,0.0005618921,0.00006001848,0.000140287,0.0001083551],"domain_scores_gemma":[0.9994121,0.0001620305,0.0001871188,0.0001245647,0.00008042589,0.00003378905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007118741,0.00002650644,0.05468456,0.00394014,0.0003682226,0.00007735077,0.002518808,0.9329893,0.002510472,0.0002974783,0.0001265617,0.0024535],"study_design_scores_gemma":[0.000724872,0.00002404286,0.0283482,0.005481482,0.00008375399,0.0001349909,0.001339623,0.9629878,0.0004713531,0.00003136444,0.0001997863,0.0001726923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6845182,0.00668889,0.307951,0.000002387813,0.000643807,0.00006823909,0.00005717598,0.00004656788,0.00002375651],"genre_scores_gemma":[0.9975276,0.00007458297,0.002282681,0.000003325623,0.0000822846,0.000001735957,0.000002199075,0.00001657159,0.000009013808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3130094,"threshold_uncertainty_score":0.3939792,"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."}}