{"id":"W4382934973","doi":"10.21203/rs.3.rs-2998318/v1","title":"Test Plan Generation for Live Testing of Cloud Services","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ericsson (Canada); Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test plan; Test (biology); Plan (archaeology); Software deployment; Test Management Approach; Computer science; Schedule; Production (economics); Test case; Task (project management); Reliability engineering; Cloud computing; Service (business); Engineering; Systems engineering; Software engineering; Operating system; Software; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003590247,0.0001766795,0.0003248505,0.0003025928,0.0002840238,0.0002374573,0.001486432,0.0002904577,0.000003808867],"category_scores_gemma":[0.001531435,0.0001498228,0.0001220487,0.0006163237,0.00007166193,0.0001750588,0.001912064,0.0005681517,0.0000889155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320194,"about_ca_system_score_gemma":0.0005658689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000876425,"about_ca_topic_score_gemma":0.0001422177,"domain_scores_codex":[0.997158,0.0002111447,0.0004649833,0.0007459574,0.000931828,0.0004880717],"domain_scores_gemma":[0.9940374,0.002708704,0.0001968185,0.001221101,0.001734063,0.0001018759],"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":[0.0000683593,0.0007991957,0.7853234,0.06815844,0.0002337057,0.00004468883,0.02252636,0.02707404,0.007217216,0.003168393,0.01944601,0.06594015],"study_design_scores_gemma":[0.0004100276,0.001050986,0.03427169,0.003686417,0.00001070027,0.000004774522,0.0006247874,0.9470528,0.004885959,0.006535064,0.00101721,0.0004495222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9280187,0.0006627467,0.06030775,0.00109552,0.003439603,0.004787601,0.0004648958,0.0009154692,0.0003076537],"genre_scores_gemma":[0.9808852,0.00006596252,0.01660778,0.00001266765,0.001336837,0.0005780744,0.0001580515,0.00002994257,0.0003254759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9199788,"threshold_uncertainty_score":0.6109596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1930620486014544,"score_gpt":0.399791728425844,"score_spread":0.2067296798243896,"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."}}