{"id":"W4391136370","doi":"10.1145/3641541","title":"Learning Failure-Inducing Models for Testing Software-Defined Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; Science Foundation Ireland","keywords":"Computer science; Software testing; Software engineering; Software; Programming language","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":[0.003825496,0.001880901,0.001116023,0.001804311,0.0004435777,0.00101648,0.00251037,0.001559465,0.0008975818],"category_scores_gemma":[0.03003431,0.0005891796,0.001075978,0.0006307512,0.001367713,0.002039821,0.001436784,0.002549827,0.0002332644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002330793,"about_ca_system_score_gemma":0.001537779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007185823,"about_ca_topic_score_gemma":0.01001785,"domain_scores_codex":[0.9970394,0.001084734,0.0002386751,0.0007934445,0.0006487109,0.0001950777],"domain_scores_gemma":[0.9652856,0.02835188,0.00213244,0.001749935,0.00195698,0.0005230164],"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":[0.0001430393,0.0001318825,0.007495467,0.0001132502,0.00006289232,0.00006763939,0.00007583456,0.9506246,0.001283637,0.002854424,0.0007259841,0.03642137],"study_design_scores_gemma":[0.00000632751,0.00001959677,0.0001876689,0.000006321973,0.000004424676,0.000009035984,0.00000548413,0.9957028,0.0005654817,0.003421442,0.00006821835,0.000003209551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1425781,0.0007630056,0.8510259,0.0006269271,0.0000556594,0.0001488171,0.0006350931,0.003237984,0.0009284603],"genre_scores_gemma":[0.8848155,0.0001917467,0.1122764,0.0002321757,0.00004302444,0.0001943545,0.001484833,0.0001147675,0.0006471327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007185823,"threshold_uncertainty_score":0.02023143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08763148271628124,"score_gpt":0.29222353392917,"score_spread":0.2045920512128888,"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."}}