{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001810786,0.001098043,0.001510601,0.0007316762,0.0007280337,0.00139719,0.002541181,0.001075719,0.001814194],"category_scores_gemma":[0.0052073,0.0008405064,0.001026933,0.0007824734,0.000860016,0.002693014,0.001608908,0.002747355,0.0004200027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215603,"about_ca_system_score_gemma":0.002803295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01943474,"about_ca_topic_score_gemma":0.02684699,"domain_scores_codex":[0.9988585,0.0003903309,0.00005848668,0.0003032885,0.0001914404,0.0001980112],"domain_scores_gemma":[0.9970204,0.00211807,0.0001698054,0.0002252363,0.0003259478,0.0001405427],"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":[0.0004246898,0.0003264286,0.001984208,0.000163429,0.0001308372,0.0002752728,0.0002834879,0.766133,0.006054382,0.01238676,0.00572704,0.2061106],"study_design_scores_gemma":[0.000006875492,0.000005499508,0.0000359214,0.000001800348,0.000004799913,0.000004907286,0.000006549238,0.9972831,0.0003594612,0.002151045,0.0001370899,0.000002926649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02232178,0.0003892259,0.9733369,0.0006462662,0.00006365099,0.0000684715,0.0001273061,0.002002519,0.001043837],"genre_scores_gemma":[0.7638154,0.0003089157,0.2307453,0.0008849464,0.0001568717,0.0001888886,0.000448516,0.0003501294,0.00310109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01943474,"threshold_uncertainty_score":0.03864324,"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."}}