{"id":"W3176638068","doi":"10.1364/jocn.423667","title":"Forecasting loss of signal in optical networks with machine learning","year":2021,"lang":"en","type":"article","venue":"Journal of Optical Communications and Networking","topic":"Optical Network Technologies","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ciena (Canada); Concordia University","funders":"","keywords":"USable; Computer science; SIGNAL (programming language); Artificial intelligence; Machine learning; Learning network","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":[0.000503587,0.000136927,0.000389219,0.0001054231,0.0000825077,0.00004590878,0.000332151,0.0001271123,0.000007252922],"category_scores_gemma":[0.00007058517,0.0001162608,0.00006077853,0.0005382191,0.000268047,0.0001257598,0.0002629745,0.00124137,1.798979e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004067667,"about_ca_system_score_gemma":0.00002581663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001142719,"about_ca_topic_score_gemma":0.00002513494,"domain_scores_codex":[0.9987823,0.00006759122,0.0006142247,0.00009200397,0.0001630965,0.0002807681],"domain_scores_gemma":[0.9983363,0.0009897344,0.0001275746,0.0003091687,0.0001505204,0.00008674664],"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":[0.00008679288,0.000165955,0.05666817,0.00007284305,0.0001812485,0.0002386936,0.0001391173,0.7499589,0.0002491858,0.01089831,0.00002032291,0.1813205],"study_design_scores_gemma":[0.0004418995,0.0001876846,0.001021128,0.0005480815,0.00004575237,0.0004425375,0.0001641183,0.9955806,0.0001013362,0.0003778701,0.0009513798,0.000137612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8037691,0.05367043,0.1323151,0.001126538,0.0001952011,0.0001714249,0.000001339407,0.0001330168,0.008617936],"genre_scores_gemma":[0.8837049,0.006545241,0.1096285,0.00001036245,0.00008148309,0.000001980772,0.000002335519,0.00002173313,0.000003453502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2456217,"threshold_uncertainty_score":0.5393202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02791422566479422,"score_gpt":0.2344838378777125,"score_spread":0.2065696122129183,"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."}}