{"id":"W2808023677","doi":"10.1145/3183519.3183551","title":"Evaluating specification-level MC/DC criterion in model-based testing of safety critical systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Microsoft (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Code coverage; Certification; Reliability engineering; Model-based testing; Process (computing); White-box testing; Software; Software engineering; Software system; Test case; Programming language; Software construction; Engineering","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":[0.001669275,0.0001238218,0.0001952931,0.0001867327,0.0001122718,0.00009467175,0.0005644762,0.00006820349,0.000005510055],"category_scores_gemma":[0.00498873,0.0001163955,0.00002963767,0.0005908395,0.0001202704,0.0002289092,0.0001276292,0.0001076209,0.000009991122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007508229,"about_ca_system_score_gemma":0.0001730396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002698577,"about_ca_topic_score_gemma":0.000005393244,"domain_scores_codex":[0.9983255,0.0001283026,0.000528324,0.0003900998,0.0003715923,0.0002562219],"domain_scores_gemma":[0.9968695,0.001677383,0.0001084049,0.0006577954,0.000626425,0.00006047798],"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":[0.0001575981,0.00154603,0.1131512,0.001482802,0.00002919369,0.000040482,0.005079174,0.07775831,0.07224695,0.3205243,0.0107479,0.3972361],"study_design_scores_gemma":[0.000140622,0.0001527156,0.003044443,0.0003219654,0.000002684145,0.000007185749,0.000005454068,0.9810396,0.003612095,0.01152847,0.000007568623,0.0001372081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01513614,0.00003029197,0.979403,0.0002506076,0.000162532,0.0001473427,0.000002825475,0.002482155,0.00238506],"genre_scores_gemma":[0.5174516,1.339358e-7,0.4824126,0.00006300886,0.00003797179,0.00001042707,6.902415e-7,0.000005774442,0.00001773239],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9032813,"threshold_uncertainty_score":0.5972336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2588067781531558,"score_gpt":0.4076255821686803,"score_spread":0.1488188040155246,"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."}}