{"id":"W4291910357","doi":"10.1109/lcomm.2022.3198908","title":"Self-Supervised Learning for CSI Compression in FDD Massive MIMO Systems","year":2022,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Mitacs","keywords":"Computer science; Channel state information; MIMO; Data compression; Base station; Bandwidth (computing); Overhead (engineering); Algorithm; Computer engineering; Channel (broadcasting); Real-time computing; Telecommunications; Wireless","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008734447,0.0005169464,0.0006617851,0.000272724,0.000285601,0.0003978832,0.0006837591,0.0005438384,0.0006164535],"category_scores_gemma":[0.003146054,0.0003075597,0.0002565501,0.0003668033,0.0005493815,0.0009249565,0.0007102766,0.001069112,0.0001522024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004345994,"about_ca_system_score_gemma":0.0006593607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002048789,"about_ca_topic_score_gemma":0.002246117,"domain_scores_codex":[0.999663,0.0001077488,0.00001863308,0.00006145144,0.0001076182,0.00004163719],"domain_scores_gemma":[0.9985859,0.000858305,0.0001465842,0.0001463226,0.0002258358,0.00003715009],"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":[0.0001005041,0.00008188269,0.0005410936,0.00004787576,0.00002908057,0.00004589971,0.00005340341,0.8768845,0.003182702,0.002960373,0.0009274685,0.1151453],"study_design_scores_gemma":[0.00000126421,0.00000556155,0.00004227719,7.827667e-7,8.521132e-7,0.000002750432,0.000001174813,0.9990863,0.0003410776,0.0004806946,0.00003604545,0.000001231286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05458162,0.000275784,0.9432685,0.0002217426,0.00003843722,0.00002402825,0.00004099143,0.0004867753,0.001062133],"genre_scores_gemma":[0.9257371,0.0001637877,0.07227783,0.0001196975,0.00006090668,0.00004507333,0.0001029024,0.000045479,0.001447379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002048789,"threshold_uncertainty_score":0.0046193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0202387108419215,"score_gpt":0.2466741036157282,"score_spread":0.2264353927738067,"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."}}