{"id":"W4405754909","doi":"10.1109/tcc.2024.3521657","title":"Understanding Serverless Inference in Mobile-Edge Networks: A Benchmark Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cloud Computing","topic":"Opportunistic and Delay-Tolerant Networks","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Inference; Benchmark (surveying); Enhanced Data Rates for GSM Evolution; Mobile edge computing; Distributed computing; Artificial intelligence","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":[0.002023966,0.001260998,0.000717658,0.0007791778,0.0006886599,0.001415095,0.002671734,0.001184218,0.001613625],"category_scores_gemma":[0.009842037,0.0003281307,0.0003731596,0.001053632,0.0009631948,0.003975016,0.001301115,0.001913005,0.0003597675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001706609,"about_ca_system_score_gemma":0.001183916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008230117,"about_ca_topic_score_gemma":0.007774394,"domain_scores_codex":[0.9987835,0.0003684834,0.00006651478,0.0002677516,0.0002536354,0.0002601342],"domain_scores_gemma":[0.9955814,0.002488921,0.0002357117,0.0008582967,0.0006018771,0.0002337454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0006127228,0.0005195689,0.007511561,0.0004317148,0.000100324,0.0002035666,0.0001437698,0.9142731,0.005539029,0.01976355,0.009576004,0.04132509],"study_design_scores_gemma":[0.00001333391,0.00006778513,0.0005345093,0.00001039151,0.000009181292,0.0000267005,0.00005873172,0.9907507,0.00249431,0.005422625,0.0006044577,0.000007197398],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7804154,0.002383739,0.1961623,0.00205097,0.000346703,0.0002777193,0.003044986,0.003034159,0.01228414],"genre_scores_gemma":[0.9515258,0.0005191026,0.04483041,0.0002033696,0.0000535223,0.0001153647,0.001715823,0.0001816203,0.000854998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008230117,"threshold_uncertainty_score":0.01636446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07639356632476259,"score_gpt":0.281413566683511,"score_spread":0.2050200003587484,"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."}}