{"id":"W4401247234","doi":"10.1109/mic.2024.3383758","title":"Revisiting Edge AI: Opportunities and Challenges","year":2024,"lang":"en","type":"article","venue":"IEEE Internet Computing","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Data science; World Wide Web; Telecommunications","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008008807,0.0002512134,0.0002643651,0.0002352303,0.0001391651,0.001051244,0.0006667225,0.00007943369,0.000002699995],"category_scores_gemma":[0.00003589911,0.0002430476,0.00009108079,0.0001837133,0.00006400588,0.0005266956,0.0006475754,0.000356206,0.00006659589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004944116,"about_ca_system_score_gemma":0.00005914914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002625872,"about_ca_topic_score_gemma":6.628084e-7,"domain_scores_codex":[0.9981476,0.00009831369,0.0003962058,0.0006502475,0.0002200683,0.0004875627],"domain_scores_gemma":[0.9989917,0.0004116762,0.00007364849,0.0003160537,0.00007716055,0.0001297259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001237751,0.000007641426,0.00007027662,0.0003691819,0.00004159459,0.0002571306,0.005184625,0.0000228747,0.00008872632,0.03057082,0.006012077,0.9573738],"study_design_scores_gemma":[0.0001073855,0.00005543056,0.0002582099,0.001546513,0.00001068137,0.0003713441,0.0001341281,0.822873,0.0006333808,0.001401189,0.1722125,0.0003961838],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.123514,0.04458695,0.7560415,0.01439165,0.03735503,0.0002218232,4.036453e-7,0.002554825,0.02133387],"genre_scores_gemma":[0.984695,0.0005792776,0.006530362,0.0006631903,0.006918154,0.000002106514,0.000001233194,0.00003378106,0.0005769354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9569776,"threshold_uncertainty_score":0.9999858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09894864539242888,"score_gpt":0.287821873082944,"score_spread":0.1888732276905151,"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."}}