{"id":"W6979280317","doi":"","title":"Simulink Mutation Testing using CodeBERT","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutation; Mutation testing; Process (computing); Mutant; Frameshift mutation","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":[0.001190146,0.001184723,0.000442323,0.001076011,0.0003417668,0.0007221985,0.001635475,0.0008601066,0.002964979],"category_scores_gemma":[0.007724332,0.0004488843,0.0005870087,0.0003902817,0.001019482,0.001162937,0.001006194,0.0008626152,0.0006703116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007895371,"about_ca_system_score_gemma":0.001228048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003381692,"about_ca_topic_score_gemma":0.004559547,"domain_scores_codex":[0.9984896,0.0003726916,0.00008081034,0.000217483,0.0007300407,0.0001093597],"domain_scores_gemma":[0.9950813,0.002692386,0.0005403119,0.0009700127,0.0006181791,0.00009782207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008872078,0.0003792598,0.01060355,0.0006357002,0.0002084875,0.001466145,0.0006389507,0.5734665,0.09957733,0.05970432,0.01076977,0.2416628],"study_design_scores_gemma":[0.00004879344,0.0001896254,0.0005616753,0.00006261726,0.0000393629,0.0004214387,0.00003935956,0.8958585,0.08254115,0.008041873,0.01215656,0.00003903353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07619535,0.0002205076,0.865149,0.0002259022,0.00008951793,0.0001253186,0.000403533,0.05052448,0.00706633],"genre_scores_gemma":[0.5822926,0.0001730697,0.4084799,0.0001721387,0.00001965384,0.0001282944,0.0008319287,0.004021105,0.003881369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003381692,"threshold_uncertainty_score":0.009918809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1159398562788714,"score_gpt":0.2193839124784322,"score_spread":0.1034440561995607,"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."}}