{"id":"W4385357917","doi":"10.3390/fi15080251","title":"Intelligent Caching with Graph Neural Network-Based Deep Reinforcement Learning on SDN-Based ICN","year":2023,"lang":"en","type":"article","venue":"Future Internet","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Ottawa","funders":"","keywords":"Computer science; Cache; Reinforcement learning; Benchmark (surveying); Computer network; Information-centric networking; Software-defined networking; Robustness (evolution); Context (archaeology); False sharing; Distributed computing; CPU cache; Cache algorithms; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0003690798,0.0002839779,0.0002195453,0.0002536292,0.0001733097,0.0002683989,0.0007990607,0.00007932306,0.00003408084],"category_scores_gemma":[0.00002187246,0.0002231278,0.0001613502,0.0006065373,0.00003263676,0.000144832,0.000142793,0.0006117342,0.0001622634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008367962,"about_ca_system_score_gemma":0.00004763396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001818549,"about_ca_topic_score_gemma":0.0001327294,"domain_scores_codex":[0.9980248,0.0001419649,0.0002794332,0.0005261843,0.0004881989,0.0005394797],"domain_scores_gemma":[0.9989837,0.0001648461,0.0001377355,0.0005081062,0.00006761256,0.0001379753],"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":[0.0001161103,0.00002288036,0.001802252,0.00001498299,0.00003461035,0.0001262938,0.0003435443,0.9798992,0.00004803822,0.001915825,0.004075908,0.01160033],"study_design_scores_gemma":[0.0004678628,0.0007130045,0.0005630029,0.0001724382,0.0000121863,0.000006819925,0.00007304316,0.9866842,0.0003705849,0.00003686564,0.0106016,0.0002984116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1625443,0.0001455177,0.8291361,0.002589081,0.002755317,0.000315783,0.000001072887,0.001311221,0.00120158],"genre_scores_gemma":[0.995167,0.000005373982,0.0005670994,0.002647535,0.0005733681,0.00003052681,0.00005741251,0.00002693825,0.0009247194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8326227,"threshold_uncertainty_score":0.9098889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01413858790375801,"score_gpt":0.2209575774238036,"score_spread":0.2068189895200456,"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."}}