{"id":"W4400484851","doi":"10.1145/3663529.3663855","title":"Leveraging Large Language Models for the Auto-remediation of Microservice Applications: An Experimental Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); York University","funders":"","keywords":"Computer science; Language model; Microservices; Natural language processing; Cloud computing; 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":[0.0005819528,0.00006650211,0.00007682816,0.00003777953,0.0001182082,0.00009617468,0.0004439983,0.00002293399,0.00000564954],"category_scores_gemma":[0.000003065631,0.00004074851,0.00004004921,0.0002094986,0.0000099586,0.0005412225,0.00009246381,0.0000408767,0.000008090137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966568,"about_ca_system_score_gemma":0.00004076824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062106,"about_ca_topic_score_gemma":0.0000164359,"domain_scores_codex":[0.9992899,0.0000265989,0.0001812506,0.0002387214,0.0001490408,0.0001144465],"domain_scores_gemma":[0.9993014,0.000120572,0.00002999096,0.0004743379,0.00005254534,0.00002109122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005664063,0.006937133,0.01072124,0.00166059,0.0003797096,0.000005158101,0.6392397,0.01074033,0.0760207,0.1002163,0.001705209,0.1523173],"study_design_scores_gemma":[0.000236386,0.000106693,0.0004605379,0.0000109184,0.000008124223,0.000001528856,0.009476074,0.9781561,0.01041068,0.0004276411,0.0006269331,0.00007834443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2084549,0.001045466,0.788985,0.0001027302,0.0001878551,0.0009529747,0.000003932818,0.0001975444,0.00006964292],"genre_scores_gemma":[0.993906,0.000002843987,0.005386367,0.00008552517,0.00007489356,0.0004600039,0.000004654008,0.000005614952,0.00007409551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9674158,"threshold_uncertainty_score":0.1661676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02218837485246432,"score_gpt":0.3130548366701679,"score_spread":0.2908664618177036,"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."}}