{"id":"W4403222415","doi":"10.2139/ssrn.4980325","title":"Automatic Instantiation of Assurance Cases from Patterns Using Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; York University","funders":"","keywords":"Computer science; Programming language; Software engineering; Linguistics; Natural language processing; Philosophy","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007163903,0.0003784573,0.0005464012,0.0003036635,0.00003877619,0.000078735,0.000361033,0.0002843952,0.0000265242],"category_scores_gemma":[0.00003199447,0.0004008077,0.0002352962,0.0001487649,0.000009868498,0.0001681052,0.0001646675,0.003202476,0.00001168285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002087076,"about_ca_system_score_gemma":0.001155558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004562477,"about_ca_topic_score_gemma":0.0005721028,"domain_scores_codex":[0.9972883,0.00005729216,0.0007412818,0.000258468,0.0003346185,0.001320002],"domain_scores_gemma":[0.9991684,0.00009404446,0.000223553,0.0003995674,0.00005596492,0.00005846704],"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":[0.000003444674,0.0000192164,0.0002194308,0.001200669,0.0008811801,0.00003973601,0.001309589,0.9876803,0.00138572,0.004125486,0.00001296508,0.003122317],"study_design_scores_gemma":[0.0002509735,0.00001883944,0.0002100312,0.001948946,0.0001834037,0.0002852322,0.0007505347,0.9751934,0.0005168314,0.02023454,0.00002020602,0.0003870925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7197663,0.02272738,0.255129,0.00001186399,0.001453946,0.0001843192,0.0002507371,0.0003460185,0.0001303894],"genre_scores_gemma":[0.9965001,0.001815184,0.0009545091,0.000003310078,0.0004864539,0.00001273524,0.00004955651,0.0001534091,0.00002469574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2767338,"threshold_uncertainty_score":0.9998444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01105182713125467,"score_gpt":0.2358639729466211,"score_spread":0.2248121458153665,"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."}}