{"id":"W4389076451","doi":"10.1109/mnet.2023.3335255","title":"Optimizing Mobile-Edge AI-Generated Everything (AIGX) Services by Prompt Engineering: Fundamental, Framework, and Case Study","year":2023,"lang":"en","type":"article","venue":"IEEE Network","topic":"Advanced Data and IoT Technologies","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Generative grammar; Mobile edge computing; Edge device; Coding (social sciences); Mobile device; Task (project management); Artificial intelligence; Multimedia; Distributed computing; World Wide Web; Cloud computing; Systems engineering","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":[0.0009936113,0.0007705887,0.0003911871,0.0003105421,0.0004228576,0.001094385,0.0008961124,0.0008847817,0.002249529],"category_scores_gemma":[0.002899617,0.0001668915,0.0003526359,0.0004938047,0.0007770712,0.001216821,0.00133868,0.0009990394,0.000420671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006827413,"about_ca_system_score_gemma":0.0006406649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002431083,"about_ca_topic_score_gemma":0.002287702,"domain_scores_codex":[0.9994339,0.000263588,0.00002507959,0.00006917055,0.0001174796,0.00009068422],"domain_scores_gemma":[0.9990491,0.0005601945,0.00005130612,0.0001426398,0.0001076977,0.00008898877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009068747,0.0007589773,0.008154645,0.001114741,0.00007078247,0.002696436,0.001752677,0.6158456,0.03336668,0.08719037,0.008984039,0.2391582],"study_design_scores_gemma":[0.00006186461,0.0004606488,0.001240792,0.00005311157,0.00003395006,0.0004053604,0.0006311343,0.9560713,0.01359013,0.01644994,0.01096148,0.0000402533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4505781,0.002102029,0.5207298,0.00119652,0.0001347244,0.0006374705,0.0004518847,0.002987683,0.02118173],"genre_scores_gemma":[0.8749595,0.0005649388,0.1214693,0.000130816,0.00002284393,0.000136148,0.0001984933,0.0001482474,0.002369805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002431083,"threshold_uncertainty_score":0.007525444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01373670493363319,"score_gpt":0.2538851889630422,"score_spread":0.240148484029409,"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."}}