{"id":"W2979327180","doi":"10.1002/stvr.1713","title":"An end‐user‐centric test generation methodology for performance evaluation of mobile networked applications","year":2019,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Computer network; Test suite; Wireless network; End user; Wireless; Test case; Machine learning; Operating system","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":[0.005779985,0.0001813975,0.000306524,0.0001036773,0.0002597064,0.00005502846,0.0004541818,0.000175505,0.00001501628],"category_scores_gemma":[0.001924395,0.0001601831,0.00006016159,0.0006897963,0.0001169935,0.0005740107,0.00006038291,0.0001273153,0.00001176744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263453,"about_ca_system_score_gemma":0.0003007767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003393951,"about_ca_topic_score_gemma":0.000002124606,"domain_scores_codex":[0.9975204,0.0003930608,0.0006559382,0.0007765924,0.0003968841,0.0002570626],"domain_scores_gemma":[0.9951156,0.001466109,0.0004234387,0.001294108,0.001605269,0.00009541725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001605227,0.0003323393,0.4847988,0.0004300596,0.000009851371,1.930671e-8,0.0004701174,0.03208456,0.006148008,0.0003803486,0.00005834352,0.4752715],"study_design_scores_gemma":[0.0006921017,0.0004894845,0.2111628,0.00003284337,0.00004570402,0.000005731747,0.00004196344,0.782271,0.003074805,0.0008424615,0.001095546,0.0002456335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5904573,0.0001687715,0.4066138,0.00003184286,0.0003097449,0.002127274,0.000009762835,0.0002462066,0.00003529469],"genre_scores_gemma":[0.7562675,0.00002419404,0.2426087,0.00002820738,0.00009814756,0.0008767645,0.0000614942,0.00001067637,0.00002433449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7501864,"threshold_uncertainty_score":0.6532076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06774374964768788,"score_gpt":0.3249485911742777,"score_spread":0.2572048415265898,"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."}}