{"id":"W4413267718","doi":"10.1109/mcom.001.2500052","title":"Mobile Network Data Synthesis with Generative AI: Challenges and Solutions","year":2025,"lang":"en","type":"article","venue":"IEEE Communications Magazine","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Mobile computing; Computer network; Cellular 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":[0.0004631511,0.0001379317,0.0001801941,0.0001001454,0.0007414776,0.0001443548,0.003124465,0.0000477047,8.75481e-7],"category_scores_gemma":[0.00004933399,0.000123663,0.00001865661,0.0004672484,0.0001990889,0.000444726,0.002696197,0.0002168975,0.00002805364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002887467,"about_ca_system_score_gemma":0.0001169419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001027204,"about_ca_topic_score_gemma":0.0001183466,"domain_scores_codex":[0.9988537,0.0002006715,0.0002011032,0.0003722387,0.00009676302,0.0002755353],"domain_scores_gemma":[0.994584,0.0005325105,0.00006958134,0.004625946,0.0001349426,0.00005297018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001051358,0.0003595352,0.0002537326,0.00005586526,0.0002448273,0.000004247207,0.002132191,0.001066555,0.0002281915,0.1346309,0.2524871,0.6085263],"study_design_scores_gemma":[0.0002532651,0.00007288564,0.002009906,0.0002152136,0.0000596827,0.00001857157,0.00005456091,0.398667,0.00007548679,0.006590012,0.5916808,0.0003026161],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004464935,0.0582641,0.8572249,0.02960706,0.002324725,0.0005386388,0.000005930678,0.0004620829,0.05112601],"genre_scores_gemma":[0.2399514,0.02730268,0.7265192,0.001994615,0.001460652,0.0004649826,0.00007516663,0.00003897311,0.002192317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6082237,"threshold_uncertainty_score":0.5806085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08370938156416743,"score_gpt":0.3062978875450519,"score_spread":0.2225885059808845,"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."}}