{"id":"W4376851317","doi":"10.1109/jlt.2023.3276373","title":"Joint PMD Tracking and Nonlinearity Compensation With Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"Journal of Lightwave Technology","topic":"Optical Network Technologies","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Polarization mode dispersion; Computer science; Artificial neural network; Nonlinear system; Compensation (psychology); Backpropagation; Artificial intelligence; Optical fiber; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002122846,0.000155786,0.0003435935,0.0005624445,0.0000568078,0.00003454254,0.0001874298,0.0003041711,0.000005665233],"category_scores_gemma":[0.00008481142,0.0001207733,0.00004245957,0.0008575472,0.0001870107,0.00015345,0.00007962164,0.0008158743,0.000004831036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004799633,"about_ca_system_score_gemma":0.000006024815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.560457e-7,"about_ca_topic_score_gemma":0.00001389201,"domain_scores_codex":[0.9990152,0.00001250707,0.0003941914,0.0001156874,0.0001451983,0.000317175],"domain_scores_gemma":[0.9994512,0.00008136987,0.0001279819,0.0001771548,0.0001117088,0.00005057221],"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":[0.0001185439,0.0001061198,0.02913835,0.0001667493,0.000511214,0.001641885,0.0002467477,0.5843114,0.01022836,0.02581538,0.001334758,0.3463805],"study_design_scores_gemma":[0.0005239415,0.0004288489,0.009264905,0.00007095152,0.00004385002,0.0009049344,0.0002206518,0.9818323,0.002602962,0.003298131,0.0005990082,0.0002095123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9721823,0.0006856085,0.02323865,0.002229904,0.0002605043,0.00009483496,6.983891e-7,0.001169578,0.0001379064],"genre_scores_gemma":[0.9845408,0.000311141,0.01497415,0.00002017395,0.0001171422,0.000002485081,0.000001251876,0.00002927664,0.000003638275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.397521,"threshold_uncertainty_score":0.4924991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01451219808574663,"score_gpt":0.2153754831028445,"score_spread":0.2008632850170978,"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."}}