{"id":"W4416235960","doi":"10.48550/arxiv.2511.09038","title":"Test Plan Generation for Live Testing of Cloud Services","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test (biology); Plan (archaeology); Software deployment; Test plan; Test Management Approach; Production (economics); Cloud computing; Task (project management)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001539284,0.0006035484,0.0009507792,0.0002047207,0.0005241538,0.0001785692,0.002033981,0.0006406161,0.00001794633],"category_scores_gemma":[0.0008714392,0.0005635404,0.0003507805,0.0006530876,0.0001418731,0.0004574095,0.001658366,0.0005460184,0.00008525766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001663904,"about_ca_system_score_gemma":0.0009516231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007973816,"about_ca_topic_score_gemma":0.0001132454,"domain_scores_codex":[0.9955683,0.0001590004,0.001612421,0.00159467,0.0004539575,0.000611602],"domain_scores_gemma":[0.9931754,0.001946745,0.001266005,0.001980197,0.001487698,0.0001439376],"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":[0.00001862055,0.0002222796,0.9756789,0.004643194,0.00009164137,0.00000176356,0.0034532,0.004223882,0.001663839,0.00007498104,0.0001697535,0.009757936],"study_design_scores_gemma":[0.001011044,0.0009520157,0.3430557,0.004644508,0.0002219302,0.00001266019,0.0003921021,0.6282495,0.01840808,0.0003874225,0.001588861,0.001076132],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9485022,0.0005399276,0.04091163,0.0002626576,0.007270128,0.001826747,0.000174094,0.0001939005,0.0003187482],"genre_scores_gemma":[0.981275,0.0001151536,0.01544726,0.0002342627,0.001925235,0.0002643476,0.0000962732,0.00002199135,0.0006204791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6326232,"threshold_uncertainty_score":0.9996816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07671994857185874,"score_gpt":0.2854198562953189,"score_spread":0.2086999077234601,"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."}}