{"id":"W4414871503","doi":"10.1109/access.2025.3618587","title":"Pre-Connect Handover Management for 5G Networks Using Multi-Agent Deep Q-Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Telecommunications and Broadcasting Technologies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Carleton University","funders":"Mitacs","keywords":"Handover; Quality of service; Reliability (semiconductor); Network packet; Wireless network; Wireless; Soft handover; Low latency (capital markets); Mobility management","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001206041,0.0001586596,0.0001668907,0.0001378311,0.0001697612,0.0001598054,0.0007657488,0.000125488,0.000007063422],"category_scores_gemma":[0.00001692805,0.0001583733,0.00006881679,0.0003523578,0.00003167944,0.0001514474,0.0001332709,0.0001687291,0.00000119894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009238827,"about_ca_system_score_gemma":0.000004428477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002725408,"about_ca_topic_score_gemma":0.00006670717,"domain_scores_codex":[0.9992108,0.00001301038,0.0002312965,0.0001841345,0.00005002849,0.0003106996],"domain_scores_gemma":[0.9992173,0.000112175,0.00004018047,0.0005733633,0.00003507025,0.00002195042],"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":[0.000008078007,0.00002557634,0.000874372,0.00008175598,0.0001158056,0.000001217973,0.00001389277,0.9332998,0.00003988155,0.0002109567,0.001589153,0.06373954],"study_design_scores_gemma":[0.0004935929,0.000007134036,0.002484045,0.0001104975,0.0000533335,8.84777e-7,0.00001930947,0.9915924,0.0009870217,0.0002101747,0.003861134,0.0001804636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05368188,0.002065268,0.9413439,0.00003227163,0.0008641637,0.0005326211,0.000002278808,0.0007932279,0.0006843911],"genre_scores_gemma":[0.9736772,0.0004602451,0.02537592,0.00006434588,0.00005838089,0.000189657,0.000008205419,0.00002808314,0.0001379987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9199953,"threshold_uncertainty_score":0.6458277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03852399396801755,"score_gpt":0.3143019338170496,"score_spread":0.275777939849032,"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."}}