{"id":"W7117547354","doi":"10.1109/jsac.2025.3649622","title":"On-Device Machine Learning Model Adaptation for 6G Communications: From Standardization to Over-the-Air Prototyping Experiments Based on Beam Prediction","year":2025,"lang":"","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Qualcomm (Canada)","funders":"","keywords":"Standardization; Adaptation (eye); Benchmark (surveying); Inference; Wireless; Process (computing); Rapid prototyping; Data modeling","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","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001280254,0.0005877966,0.0005347329,0.001071567,0.004429579,0.0005278452,0.00532396,0.0002627633,0.000008857941],"category_scores_gemma":[0.001440042,0.000581779,0.0002078377,0.004377419,0.0002032637,0.0007282512,0.0005038165,0.002710562,0.00001629876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001799499,"about_ca_system_score_gemma":0.00105435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005901628,"about_ca_topic_score_gemma":0.000309002,"domain_scores_codex":[0.9944263,0.00160547,0.001688225,0.0008472964,0.0007922727,0.0006404351],"domain_scores_gemma":[0.9865374,0.005370546,0.001114721,0.005195105,0.001535941,0.0002462841],"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":[0.0005586484,0.001172233,0.0001658547,0.00001325495,0.00009050392,3.589147e-7,0.001249915,0.9606842,0.001161229,0.01019178,0.0006703926,0.02404163],"study_design_scores_gemma":[0.00205299,0.0006966279,0.001361329,0.001773956,0.00008129,0.000002933198,0.0001184577,0.9723828,0.001233854,0.009902257,0.00998275,0.0004107346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004577913,0.0009900874,0.969403,0.01805746,0.0004230671,0.005367285,0.0003044798,0.0002255855,0.0006511139],"genre_scores_gemma":[0.8765998,0.001558841,0.1132837,0.004226755,0.0001164602,0.00361037,0.0004000393,0.00007772103,0.0001262914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8720219,"threshold_uncertainty_score":0.9996634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05841679081063163,"score_gpt":0.3521063930030678,"score_spread":0.2936896021924362,"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."}}