{"id":"W2995625743","doi":"10.48550/arxiv.1912.08368","title":"Real-Time Prediction of Delay Distribution in Service Systems using Mixture Density Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Queuing Theory Analysis","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Queueing theory; Variance (accounting); Service (business); Percentile; Stability (learning theory); Statistics; Machine learning; Mathematics; Computer 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001833385,0.000712163,0.0006953782,0.0009819667,0.0003549055,0.001028339,0.001053358,0.0008110119,0.0007720363],"category_scores_gemma":[0.00889782,0.0006549322,0.0005681054,0.0008598943,0.0006873406,0.001743867,0.0007018399,0.001481762,0.0002171335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001737411,"about_ca_system_score_gemma":0.000781511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02188061,"about_ca_topic_score_gemma":0.01160757,"domain_scores_codex":[0.9994438,0.0001948337,0.00002197334,0.0001116494,0.0001536256,0.00007417133],"domain_scores_gemma":[0.9956245,0.003377474,0.0003082602,0.0001511402,0.0004269199,0.0001117885],"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":[0.00005233413,0.00002224274,0.001659373,0.00001086329,0.00001657328,0.00001406446,0.00002389434,0.9893197,0.0004005712,0.00268099,0.0001459865,0.005653525],"study_design_scores_gemma":[6.442409e-7,0.000002176039,0.0001146509,5.446607e-7,8.661788e-7,0.000001301334,0.000001212421,0.9992132,0.00005890063,0.0005866605,0.00001811376,0.000001753889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2037065,0.0004266512,0.7937795,0.0003802293,0.00004760494,0.00004039871,0.0001546145,0.0005315187,0.0009329582],"genre_scores_gemma":[0.9715455,0.0002291677,0.02711494,0.00003436823,0.00002745475,0.0000295429,0.0002027491,0.00003316473,0.0007831487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02188061,"threshold_uncertainty_score":0.04350656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03077856169877187,"score_gpt":0.172086336382359,"score_spread":0.1413077746835871,"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."}}