{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001450575,0.0003096148,0.0002882292,0.0001072206,0.0001817769,0.0001479726,0.0002118034,0.0001930879,0.000005095019],"category_scores_gemma":[0.000009395677,0.0003189547,0.00003084323,0.0007805175,0.00002901936,0.0003846659,0.0001419562,0.0004944011,0.00002576107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005366589,"about_ca_system_score_gemma":0.000005293548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002732419,"about_ca_topic_score_gemma":0.00001705574,"domain_scores_codex":[0.998634,0.00001658959,0.000276058,0.0003688795,0.0001415495,0.0005628658],"domain_scores_gemma":[0.9993553,0.000109142,0.00003554723,0.0003864615,0.00002163359,0.00009195927],"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":[0.000006842599,0.00003250746,0.0009850205,0.0001258755,0.0001144037,0.0007711067,0.001173021,0.9780449,0.002395636,0.000007764493,0.01392441,0.002418541],"study_design_scores_gemma":[0.001088537,0.0004688448,0.0002573227,0.000505819,0.0001199142,0.0005582664,0.01072933,0.9392828,0.004023685,0.0003182348,0.04105893,0.001588372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846407,0.002697355,0.006306622,0.0000172259,0.002093247,0.0005761569,0.00003413716,0.003613687,0.00002083521],"genre_scores_gemma":[0.9948832,0.0003967903,0.003676451,0.0000559865,0.0005970056,0.0002116601,0.00004980566,0.00009267079,0.00003637387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03876211,"threshold_uncertainty_score":0.9999263,"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."}}