{"id":"W4413349786","doi":"10.1109/cloud67622.2025.00053","title":"Automated LLM Deployment and Evaluation: A Cloud-Native Approach Using LLM-as-a-Judge","year":2025,"lang":"en","type":"article","venue":"","topic":"Digital Rights Management and Security","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"","keywords":"Software deployment; Cloud computing; Computer science; Software engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01328145,0.002648405,0.001578815,0.003395715,0.001412712,0.004476561,0.003916092,0.002259607,0.00628591],"category_scores_gemma":[0.05171325,0.0009237996,0.001216933,0.001693867,0.001350034,0.004871861,0.004982066,0.002895423,0.003485973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002616049,"about_ca_system_score_gemma":0.00361595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008354574,"about_ca_topic_score_gemma":0.01273517,"domain_scores_codex":[0.9889089,0.004287733,0.0009983316,0.00194181,0.003043366,0.000819754],"domain_scores_gemma":[0.97623,0.008940862,0.001593108,0.006044975,0.005617807,0.001573223],"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":[0.003323318,0.003125625,0.04083097,0.001402049,0.0008033887,0.001436479,0.001172461,0.2972767,0.03025986,0.02120674,0.1599818,0.4391806],"study_design_scores_gemma":[0.0001730471,0.0002900966,0.002718276,0.00006600722,0.00003256544,0.00009010785,0.0001756125,0.97576,0.007715886,0.004429551,0.00848188,0.00006695864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1822837,0.001581879,0.5670826,0.002424821,0.001075949,0.002554487,0.004985964,0.2169215,0.02108912],"genre_scores_gemma":[0.5593796,0.0002810421,0.4173621,0.001258735,0.0001488528,0.0009246223,0.01021018,0.006859219,0.003575677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01328145,"threshold_uncertainty_score":0.07023984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03676756761446493,"score_gpt":0.3112119642635197,"score_spread":0.2744443966490548,"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."}}