{"id":"W4226305247","doi":"10.1364/ofc.2022.w4i.2","title":"Machine Learning Based EDFA Channel In-band Gain Ripple Modeling","year":2022,"lang":"en","type":"article","venue":"Optical Fiber Communication Conference (OFC) 2022","topic":"Optical Network Technologies","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Ripple; Optical amplifier; Computer science; Channel (broadcasting); Automatic gain control; Optics; Physics; Amplifier; Telecommunications; Engineering; Voltage; Bandwidth (computing); Laser; Electrical engineering","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006293029,0.0002469321,0.0003177985,0.0002100377,0.0003615714,0.00008755876,0.001048892,0.0001290977,0.001737025],"category_scores_gemma":[0.0002026395,0.0002874446,0.00007423401,0.0006236478,0.0001141356,0.0001432293,0.0006283026,0.001899812,0.00007347381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002337881,"about_ca_system_score_gemma":0.00005270946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000610614,"about_ca_topic_score_gemma":0.00006515774,"domain_scores_codex":[0.998183,0.0002247681,0.0004465959,0.0003071125,0.0003554244,0.0004830707],"domain_scores_gemma":[0.9984032,0.000434825,0.000045689,0.0009533582,0.00006705798,0.00009589515],"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":[0.00002002713,0.0000735216,0.0001815128,0.00002550845,0.0000158403,0.00000482971,0.0001246014,0.9824976,0.0002800958,0.01103186,0.0001125756,0.005631991],"study_design_scores_gemma":[0.0004329363,0.00006543226,0.00003596277,0.00003810236,0.0000125351,0.000003816678,0.0003655082,0.9910673,0.0001933894,0.002990983,0.004472053,0.0003219821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5225171,0.01834559,0.2083877,0.02385086,0.0009763934,0.003215393,0.000212892,0.008495948,0.2139981],"genre_scores_gemma":[0.9898527,0.00032779,0.008863027,0.00009911092,0.00001620451,0.0003101936,0.0001899103,0.00005445666,0.0002866447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4673356,"threshold_uncertainty_score":0.9999578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02706989280020346,"score_gpt":0.2280378518368164,"score_spread":0.2009679590366129,"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."}}