{"id":"W4402218589","doi":"10.1109/icdcsw63686.2024.00011","title":"Towards LLM-Assisted System Testing for Microservices","year":2024,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Microservices; Computer science; Software engineering; Operating system; Cloud computing","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":[0.0005434256,0.0001205414,0.0001546222,0.00007239463,0.0001412695,0.0004429948,0.0005647914,0.00006889568,0.000003474227],"category_scores_gemma":[0.00003748539,0.00008198633,0.00009004643,0.0005438965,0.00001544448,0.0004432296,0.0001358947,0.00006190705,0.0001187849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009020135,"about_ca_system_score_gemma":0.0001459717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001439062,"about_ca_topic_score_gemma":0.000009247785,"domain_scores_codex":[0.9988949,0.00002168905,0.0002657722,0.0004080038,0.0001595901,0.0002500632],"domain_scores_gemma":[0.9991009,0.0002403018,0.00003299161,0.0004165234,0.0001496523,0.00005968997],"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":[0.00001189005,0.0001268709,0.006717995,0.01588796,0.0001362607,0.00004276412,0.001919759,0.00008294425,0.007616906,0.09399777,0.007947704,0.8655112],"study_design_scores_gemma":[0.0004365619,0.0003783278,0.01393322,0.001361419,0.00003146474,0.0002769438,0.0003704187,0.9351172,0.009404617,0.001025609,0.0370662,0.0005980346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06269352,0.001068517,0.9138552,0.0008973912,0.003760001,0.0006390922,0.000008984598,0.004162224,0.01291505],"genre_scores_gemma":[0.8827982,8.07544e-7,0.1163535,0.0000982015,0.0001743616,0.00007665996,0.000001799587,0.000009720626,0.0004867722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9350342,"threshold_uncertainty_score":0.4271809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02939684908194526,"score_gpt":0.2746690199451169,"score_spread":0.2452721708631716,"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."}}