{"id":"W7106650730","doi":"10.32913/mic-ict-research.v2025.n1.1277","title":"A Rich High-Order Mutation Testing Dataset for Software Fortification","year":2024,"lang":"","type":"article","venue":"Research and Development on Information and Communication Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Mutation; Mutation testing; Random forest; Software; Software testing; Test (biology)","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002808752,0.0002456235,0.0002203279,0.001996977,0.001549987,0.001435041,0.0008233308,0.0003355569,0.000006627849],"category_scores_gemma":[0.003319313,0.0002430812,0.00001330753,0.002238174,0.0004146841,0.001611743,0.0008438341,0.0006974664,0.00008374261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001705489,"about_ca_system_score_gemma":0.000668656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004522533,"about_ca_topic_score_gemma":0.000006812164,"domain_scores_codex":[0.997606,0.0001298905,0.0008163533,0.0004533873,0.0004947007,0.0004997155],"domain_scores_gemma":[0.9952919,0.002087018,0.0002011612,0.0009967806,0.001298506,0.00012461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002001186,0.00005532936,0.0001919283,0.0003944609,0.0000276574,9.514666e-7,0.001325174,0.000006930216,0.000009358968,0.04887215,0.01313574,0.9359603],"study_design_scores_gemma":[0.001269338,0.001846955,0.002504736,0.002394367,0.00002253463,0.000170359,0.000953348,0.2199801,0.003520433,0.3759226,0.3903851,0.001030134],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008402587,0.003726378,0.969584,0.01091127,0.0001655303,0.001775511,0.0002232675,0.005034021,0.0001774608],"genre_scores_gemma":[0.3317809,0.001142751,0.6634086,0.0002835951,0.00001877127,0.001026246,0.002242587,0.00001938996,0.00007711937],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9349301,"threshold_uncertainty_score":0.9997498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1138390251804364,"score_gpt":0.3782881379797234,"score_spread":0.264449112799287,"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."}}