{"id":"W3086729219","doi":"10.1364/cleo_si.2020.sth4m.1","title":"Deep Learning for Multi-Step Performance Prediction in Operational Optical Networks","year":2020,"lang":"en","type":"article","venue":"Conference on Lasers and Electro-Optics","topic":"Optical Network Technologies","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ciena (Canada)","funders":"","keywords":"Robustness (evolution); Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Mean squared prediction error; Bit error rate; Artificial neural network; Machine learning; Field (mathematics); Data modeling; Word error rate; Bit rate; Data mining; Real-time computing; Algorithm; Database; Mathematics","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":[0.00006826893,0.0001497164,0.0001669647,0.00004063931,0.00007280136,0.00006920443,0.00009355335,0.0001624892,0.00001131985],"category_scores_gemma":[0.0000714436,0.0001489136,0.00002288565,0.0001374765,0.00005876125,0.0001159634,0.00002413255,0.0004698418,0.000005877834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003519686,"about_ca_system_score_gemma":0.00001402964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.109819e-7,"about_ca_topic_score_gemma":0.000005084776,"domain_scores_codex":[0.9991849,0.000008600906,0.0001826559,0.0002005056,0.00008348958,0.0003398525],"domain_scores_gemma":[0.9997232,0.00006523794,0.00001499639,0.00006912944,0.00004151371,0.00008592501],"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":[0.00008278414,0.00002789671,0.00263014,0.00006632251,0.00002333267,0.000002850312,0.00007379225,0.9212233,0.0009049923,0.03303915,0.0001825392,0.04174287],"study_design_scores_gemma":[0.0005026818,0.0005310592,0.001028885,0.00002898826,0.000009670402,0.000001557176,0.00007341012,0.9967508,0.0006274948,0.00004437824,0.0002487669,0.0001523257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5312579,0.0001931075,0.4656667,0.0007617549,0.0001140387,0.0003546921,0.000002857128,0.0004757035,0.001173311],"genre_scores_gemma":[0.979111,0.000872622,0.0196821,0.000110526,0.00009876194,0.00004575944,0.0000274931,0.0000214983,0.00003025275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4478531,"threshold_uncertainty_score":0.6072519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02571838428369289,"score_gpt":0.2279302221559498,"score_spread":0.2022118378722569,"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."}}