{"id":"W4310673963","doi":"10.1016/j.infsof.2022.107129","title":"A probabilistic framework for mutation testing in deep neural networks","year":2022,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Testability; Context (archaeology); Machine learning; Probabilistic logic; Mutation; Set (abstract data type); Artificial intelligence; Test suite; Artificial neural network; Suite; Data mining; Model-based testing; Reliability engineering; Test case; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003657813,0.0001000224,0.0001263332,0.0004697019,0.000282302,0.00008370673,0.0003888081,0.0001059499,0.000002090669],"category_scores_gemma":[0.003599765,0.0001078685,0.00001857762,0.001030118,0.00004873831,0.0004725719,0.0003203576,0.0003141381,7.925006e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007196362,"about_ca_system_score_gemma":0.00002946545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001753548,"about_ca_topic_score_gemma":0.000003514306,"domain_scores_codex":[0.9991542,0.0000269125,0.0003123955,0.0001618032,0.0001128498,0.0002319161],"domain_scores_gemma":[0.998724,0.0007410957,0.0001583331,0.0002531454,0.00009678962,0.00002665978],"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":[0.000007343212,0.00001958128,0.01217021,0.00003008156,0.000002392349,0.000004584233,0.0006136359,0.01988298,2.315497e-7,0.05992569,0.0001393631,0.9072039],"study_design_scores_gemma":[0.0001514272,0.0001493727,0.000982531,0.000009996304,0.000001404324,0.00009935231,0.00003262001,0.660566,0.000001900735,0.3377032,0.0002075582,0.00009469733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01179871,0.00008639728,0.978835,0.0006695538,0.0001382927,0.0003878777,0.000002167748,0.00806535,0.00001661561],"genre_scores_gemma":[0.54786,6.654372e-7,0.451323,0.0004125089,0.000006378547,0.0003844477,0.000008422591,0.000003812002,8.13243e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9071092,"threshold_uncertainty_score":0.4398751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01667141722285493,"score_gpt":0.2536663021430027,"score_spread":0.2369948849201478,"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."}}