{"id":"W4407570960","doi":"10.48550/arxiv.2502.08758","title":"Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding","year":2025,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Antenna Design and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Precoding; MIMO; Computer science; Artificial neural network; Compression (physics); Artificial intelligence; Telecommunications; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002973685,0.0005706611,0.0007603107,0.0005287702,0.0001412511,0.0001351741,0.0005929796,0.000913235,0.00002885853],"category_scores_gemma":[0.00006278356,0.0006217732,0.0003877092,0.0003070779,0.00006269241,0.0001296702,0.0004044987,0.0008663995,0.000001213119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003917032,"about_ca_system_score_gemma":0.00005797836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00028768,"about_ca_topic_score_gemma":0.000254541,"domain_scores_codex":[0.9977069,0.00008819452,0.0008011557,0.0005366671,0.0002245512,0.0006425402],"domain_scores_gemma":[0.9981952,0.0002526989,0.0003185424,0.0008327527,0.0002298908,0.0001709682],"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":[0.0001142981,0.00005095149,0.0009453411,0.0004837805,0.00007575251,0.000005565675,0.0001715931,0.978262,0.002414891,0.001239612,0.003566547,0.01266967],"study_design_scores_gemma":[0.0004158783,0.00004525765,0.0006649788,0.000456482,0.00007799903,0.000003985932,0.00003746988,0.9929091,0.003749868,0.0005547824,0.0005777961,0.0005064369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003808981,0.00782826,0.9836271,0.000193662,0.0008536828,0.001915921,0.0002392548,0.001062878,0.0004702928],"genre_scores_gemma":[0.8013846,0.002494662,0.1930646,0.0002019929,0.0003448932,0.001259933,0.0006413811,0.0001559445,0.0004519734],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7975757,"threshold_uncertainty_score":0.9996234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01328631232681271,"score_gpt":0.2218030222538888,"score_spread":0.2085167099270761,"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."}}