{"id":"W3202624729","doi":"10.1364/jocn.437414","title":"Learning EPON delay models from data: a machine learning approach","year":2021,"lang":"en","type":"article","venue":"Journal of Optical Communications and Networking","topic":"Advanced Photonic Communication Systems","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Concordia University","funders":"Horizon 2020 Framework Programme; Ministerio de Ciencia, Innovación y Universidades","keywords":"Computer science; Dimensioning; Polling; Algorithm; Upstream (networking); Artificial intelligence; Machine learning; Real-time computing; Computer network; 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":[],"consensus_categories":[],"category_scores_codex":[0.0007172557,0.0001344157,0.0003292896,0.00006097787,0.0002912024,0.0001173583,0.0009676507,0.00008229899,0.000008180368],"category_scores_gemma":[0.00006873937,0.0001328194,0.00005881215,0.0002558694,0.00007127565,0.0004204303,0.0008997376,0.001399536,0.000001351367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005595222,"about_ca_system_score_gemma":0.00003854172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001089193,"about_ca_topic_score_gemma":0.00001818143,"domain_scores_codex":[0.9985875,0.0002892006,0.0006177629,0.0001351396,0.0001874786,0.0001829279],"domain_scores_gemma":[0.9973692,0.0008097976,0.0002014098,0.001344783,0.0001569506,0.0001178548],"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":[0.00002685587,0.0001372016,0.001564354,0.00004284869,0.0004147985,0.00002398641,0.001632484,0.8396595,0.002002554,0.002809947,0.00008553987,0.1516],"study_design_scores_gemma":[0.0002797861,0.00002171876,0.00003924321,0.00013367,0.00005159483,0.0002047356,0.000454552,0.9291637,0.00002319795,0.0005632949,0.068937,0.0001274904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03605345,0.2276637,0.7088088,0.0004658066,0.0003207137,0.0001528162,0.00001274329,0.0001744269,0.02634751],"genre_scores_gemma":[0.8483087,0.02922739,0.1221548,0.00001684321,0.0001264638,0.000003403506,0.0001000156,0.00002970585,0.00003264884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8122553,"threshold_uncertainty_score":0.6080364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08076557816815343,"score_gpt":0.2853205483218527,"score_spread":0.2045549701536993,"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."}}