{"id":"W4407783027","doi":"10.1109/lwc.2025.3543965","title":"Parameter-Efficient Online Fine-Tuning of ML-Based Hybrid Beamforming With LoRA","year":2025,"lang":"en","type":"article","venue":"IEEE Wireless Communications Letters","topic":"Antenna Design and Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Beamforming; Telecommunications","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":[0.00009936369,0.0001510919,0.0002015471,0.0002451123,0.0001261339,0.00002511271,0.0005547213,0.0000356761,0.000004040574],"category_scores_gemma":[0.00001356814,0.0001488923,0.00005288482,0.0004584435,0.0001655693,0.0000712031,0.00004003649,0.0002164665,0.000002540032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007251192,"about_ca_system_score_gemma":0.00003469608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002530948,"about_ca_topic_score_gemma":0.00002661179,"domain_scores_codex":[0.9992214,0.00004829616,0.0003073557,0.0001235343,0.0001171523,0.0001822364],"domain_scores_gemma":[0.9985331,0.000236914,0.00007496425,0.00104822,0.00007346674,0.00003331286],"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":[0.000012818,0.00009290524,0.0002999273,0.00006640101,0.00005141061,0.000001368087,0.0001086311,0.955902,0.03886526,0.0001898903,0.0002737509,0.00413567],"study_design_scores_gemma":[0.0003791513,0.00001475882,0.0001501256,0.0002914072,0.0000371353,0.000001542973,0.000065124,0.9861023,0.01244262,0.00000393632,0.0003599311,0.0001519132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3795046,0.0001236939,0.6189355,0.0009026991,0.00006340089,0.0001442875,0.00001726908,0.000150079,0.0001585367],"genre_scores_gemma":[0.9397792,0.00004467785,0.05956982,0.0004128825,0.000008886964,0.00003276951,0.000107751,0.00002685906,0.00001713905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5602747,"threshold_uncertainty_score":0.6071653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524419153987744,"score_gpt":0.2308517600884659,"score_spread":0.2156075685485884,"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."}}