{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005779199,0.0001316521,0.0001338977,0.0001499521,0.0001488149,0.0004720057,0.0003808328,0.00003785227,0.00001817198],"category_scores_gemma":[0.00003074803,0.0001021339,0.00003428636,0.0005181554,0.00004987111,0.0006900005,0.0004618599,0.00005668378,0.00001396858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008270894,"about_ca_system_score_gemma":0.00009508549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005601045,"about_ca_topic_score_gemma":0.000008646642,"domain_scores_codex":[0.9987426,0.00009051654,0.000179772,0.0004121428,0.0003808844,0.0001940274],"domain_scores_gemma":[0.999423,0.00005176127,0.00004869774,0.0003066578,0.0001154927,0.00005434834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005434036,0.000288003,0.0001080128,0.00002855664,0.00007047575,0.000003901918,0.0007086541,0.0002006222,0.00002458915,0.974694,0.003690631,0.02017719],"study_design_scores_gemma":[0.000428791,0.00004328566,0.0008298722,0.00001537429,0.00002281797,0.000001910076,0.00006536107,0.9522962,0.0002441723,0.04264151,0.003277615,0.0001330724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1561632,0.0001650995,0.3082656,0.0008614186,0.0004037956,0.0007889853,9.331235e-7,0.0009566431,0.5323943],"genre_scores_gemma":[0.980947,0.000005019589,0.01534576,0.0006413842,0.00002016103,0.00002300647,0.00000445258,0.000004517776,0.003008655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9520956,"threshold_uncertainty_score":0.4551562,"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."}}