{"id":"W4205188521","doi":"10.1109/jiot.2021.3133110","title":"Learning-Based Computation Offloading for IoRT Through Ka/Q-Band Satellite–Terrestrial Integrated Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Satellite Communication Systems","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Memorial University of Newfoundland","funders":"Beijing Municipal Science and Technology Commission; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Markov decision process; Robustness (evolution); Reinforcement learning; Satellite; Computation; Markov process; Distributed computing; Real-time computing; Communications satellite; Q-learning; Computer network; 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":[0.0006891125,0.0002149136,0.0003956016,0.0001244547,0.00007897356,0.0002349213,0.0003674298,0.0001713401,0.00003962773],"category_scores_gemma":[0.0001892157,0.0002162451,0.0002362164,0.0002362418,0.00004786841,0.0003629211,0.0000192989,0.0007582483,0.000007828113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000181362,"about_ca_system_score_gemma":0.00007776479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002741373,"about_ca_topic_score_gemma":0.000006743212,"domain_scores_codex":[0.9982097,0.0001968203,0.0008912988,0.0001707665,0.0002553919,0.0002760459],"domain_scores_gemma":[0.9985217,0.0004685106,0.0003656753,0.000206255,0.0003530974,0.0000847373],"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":[0.0002832293,0.00008071212,0.001988635,0.0001880154,0.0004953595,0.00003840123,0.005516592,0.9184707,0.03362169,0.00003375918,0.003561504,0.0357214],"study_design_scores_gemma":[0.001480455,0.000145469,0.00009539183,0.000852844,0.00005230592,0.0001897943,0.000409506,0.862966,0.1033402,0.0001942449,0.03000328,0.0002705168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1377217,0.003804768,0.8532949,0.00008361132,0.003720904,0.0001932882,0.000002468844,0.0001779989,0.001000326],"genre_scores_gemma":[0.9908425,0.0004278824,0.007973247,0.00007740658,0.0003970792,0.000008853678,0.00004965513,0.00006122689,0.0001621866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8531207,"threshold_uncertainty_score":0.8818218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03389458669781596,"score_gpt":0.2770996097776834,"score_spread":0.2432050230798675,"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."}}