{"id":"W4400447774","doi":"10.1109/tmc.2024.3415661","title":"Large Language Models (LLMs) Inference Offloading and Resource Allocation in Cloud-Edge Computing: An Active Inference Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Cloud Data Security Solutions","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Inference; Cloud computing; Resource allocation; Enhanced Data Rates for GSM Evolution; Distributed computing; Artificial intelligence; Computer network","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":[0.0008026164,0.0003498989,0.0003336344,0.000598254,0.0005020878,0.0005755826,0.0008459395,0.0001794851,0.000005907051],"category_scores_gemma":[0.0000258131,0.0003910242,0.00008698919,0.001492048,0.00009947527,0.001298138,0.00006319991,0.00096526,0.0000193979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002445888,"about_ca_system_score_gemma":0.0001596676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001685424,"about_ca_topic_score_gemma":0.000168971,"domain_scores_codex":[0.9970364,0.0002869255,0.0005177187,0.001143069,0.000380361,0.0006355492],"domain_scores_gemma":[0.9980529,0.0007405056,0.0000992418,0.0008209965,0.00008310599,0.0002032671],"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":[0.00001686322,0.0006679016,0.00002870923,0.0001601194,0.00004754072,0.00002955432,0.05327829,0.7479234,0.001414659,0.0208437,0.0000404152,0.1755488],"study_design_scores_gemma":[0.0003618356,0.0001210037,0.0001298148,0.0002794228,0.00001704774,0.00003372967,0.001758475,0.9947116,0.001430773,0.0005829815,0.0001797397,0.0003935676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2417116,0.0002188363,0.7562356,0.00007166824,0.0003759599,0.0004391364,0.00004963873,0.0005854545,0.0003121154],"genre_scores_gemma":[0.9838015,0.00002550236,0.01582016,0.0001166394,0.0001079061,0.0000398207,0.00003419103,0.00003346036,0.00002079754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7420899,"threshold_uncertainty_score":0.9998541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02912644320797005,"score_gpt":0.2995773100000774,"score_spread":0.2704508667921074,"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."}}