{"id":"W4223635528","doi":"10.1364/jocn.455539","title":"Supervised graph convolution networks for OSNR and power estimation in optical mesh networks","year":2022,"lang":"en","type":"article","venue":"Journal of Optical Communications and Networking","topic":"Optical Network Technologies","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ciena (Canada)","funders":"","keywords":"Computer science; Convolution (computer science); Electronic engineering; Graph; Theoretical computer science; Artificial intelligence; 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":[0.001013967,0.0001697131,0.0003594894,0.0001971344,0.0003259284,0.000086354,0.0004266234,0.0001446047,0.000006991444],"category_scores_gemma":[0.00005800769,0.0001717544,0.00008319804,0.0004654644,0.0002445074,0.0001966227,0.0003988538,0.001023754,1.266563e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064422,"about_ca_system_score_gemma":0.00001517817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001191512,"about_ca_topic_score_gemma":0.000005961298,"domain_scores_codex":[0.9985869,0.00008722775,0.0006614634,0.0001362278,0.000164446,0.000363725],"domain_scores_gemma":[0.9982673,0.001052364,0.0001089052,0.0003823119,0.00007679711,0.0001123539],"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":[0.0001306058,0.0001378004,0.002599774,0.00002724027,0.0001113801,0.000009073292,0.0001383114,0.792168,0.00005081928,0.07868522,0.0005046478,0.1254372],"study_design_scores_gemma":[0.0006876148,0.0002816728,0.001827564,0.00007500601,0.00005204142,0.00008855227,0.0002295298,0.9915472,0.000001883978,0.003376803,0.001652945,0.0001791952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2337997,0.03691919,0.7237579,0.002450377,0.0008809124,0.0007718098,0.000005183912,0.0002268257,0.001188072],"genre_scores_gemma":[0.9288347,0.006489362,0.06445246,0.00005830399,0.00007678458,0.00004777023,0.000009870811,0.00002862891,0.000002130474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.695035,"threshold_uncertainty_score":0.7003942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02052917874619004,"score_gpt":0.2506116659533985,"score_spread":0.2300824872072085,"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."}}