{"id":"W7138876242","doi":"10.1109/globecom59602.2025.11431821","title":"Hierarchical Deep Reinforcement Learning for Robust Access in Cognitive IoT Networks under Smart Jamming Attacks","year":2025,"lang":"","type":"article","venue":"","topic":"Cognitive Radio Networks and Spectrum Sensing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Cognitive radio; Channel (broadcasting); Jamming; Interference (communication); Process (computing); Control channel; Power control; Mode (computer interface)","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00155168,0.0007791801,0.0009851708,0.0008171586,0.001181015,0.00195785,0.001111531,0.0004835696,0.0001918851],"category_scores_gemma":[0.0003968097,0.0008304269,0.0004170486,0.002658257,0.0003353115,0.0007459983,0.001497097,0.001886697,0.000008600205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005619068,"about_ca_system_score_gemma":0.0004965331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002361122,"about_ca_topic_score_gemma":0.001713,"domain_scores_codex":[0.9936672,0.0004766618,0.001422598,0.001826298,0.0005316014,0.002075674],"domain_scores_gemma":[0.9949006,0.003412785,0.0003432222,0.0004906456,0.0005208753,0.0003318172],"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":[0.0002687467,0.0001069099,0.002330213,0.00005594028,0.0001779062,0.00003731459,0.0004712757,0.6810445,0.000003139351,0.01428148,0.0001644419,0.3010581],"study_design_scores_gemma":[0.003539754,0.0004244201,0.006506713,0.001810555,0.0001335695,0.00001485783,0.0006905412,0.9836196,0.00008584986,0.00167346,0.000611528,0.0008891165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006745229,0.001052653,0.9629804,0.003082328,0.001513329,0.001828131,5.273135e-7,0.0001465284,0.02265081],"genre_scores_gemma":[0.9850477,0.0004330318,0.00563142,0.004274297,0.0005455813,0.00008482029,0.00002921535,0.00005009706,0.003903869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9783024,"threshold_uncertainty_score":0.9994147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03643292094030831,"score_gpt":0.3089616069700988,"score_spread":0.2725286860297905,"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."}}