{"id":"W4293057165","doi":"10.1109/lcomm.2022.3201625","title":"Data-Driven Soft Demapping for Residual Impairments Channels","year":2022,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Microwave Engineering and Waveguides","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies","keywords":"Computer science; Codebook; Artificial neural network; Channel (broadcasting); Wireless; Pruning; Reliability (semiconductor); Residual; Deep learning; Artificial intelligence; Machine learning; Computer network; Algorithm; Power (physics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004482566,0.0006373856,0.0003131575,0.0002110245,0.0001929306,0.0004888228,0.0006699009,0.0004393566,0.001688873],"category_scores_gemma":[0.001688374,0.0002397056,0.0002338855,0.0002257134,0.0004999831,0.0009876296,0.0009213963,0.001113512,0.0003716339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004232867,"about_ca_system_score_gemma":0.0006846599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001713895,"about_ca_topic_score_gemma":0.004063573,"domain_scores_codex":[0.9997641,0.00004681306,0.00001225674,0.00004506976,0.00009582003,0.00003588501],"domain_scores_gemma":[0.9995104,0.0001993327,0.00005874753,0.0001133824,0.000095928,0.00002225424],"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":[0.0002737778,0.00007733982,0.0009237559,0.0001335158,0.00004972368,0.0002184613,0.0001340818,0.6816682,0.06849721,0.01355409,0.00197057,0.2324992],"study_design_scores_gemma":[0.000007013194,0.00002768244,0.0001115643,0.0000095082,0.000006825444,0.00005160739,0.00001290607,0.9724131,0.02269043,0.003801286,0.0008596032,0.000008427767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03036744,0.0001641803,0.9670292,0.0001397959,0.00003442561,0.00001435946,0.00005660893,0.0007030521,0.001490959],"genre_scores_gemma":[0.7756491,0.0002339476,0.2188231,0.0002316902,0.00003419715,0.00004336137,0.0001791124,0.0001572977,0.004648166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001713895,"threshold_uncertainty_score":0.005649805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05855426435487303,"score_gpt":0.2765865752464314,"score_spread":0.2180323108915584,"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."}}