{"id":"W3217141978","doi":"10.2478/popets-2022-0005","title":"MLEFlow: Learning from History to Improve Load Balancing in Tor","year":2021,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Waterloo; National Science Foundation","keywords":"Computer science; Network packet; Python (programming language); Relay; Discretization; Mathematical optimization; Real-time computing; Computer network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005721421,0.0003146808,0.0004624501,0.0003727443,0.0001095462,0.000229542,0.001594094,0.0002361959,0.00002218118],"category_scores_gemma":[0.003905988,0.0003131406,0.0001228684,0.0007965702,0.00004077446,0.0004915609,0.001405308,0.0008675795,0.0000968313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001305521,"about_ca_system_score_gemma":0.0001977763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005515805,"about_ca_topic_score_gemma":0.00007227981,"domain_scores_codex":[0.9971517,0.00001681168,0.0005399441,0.001141372,0.0005172068,0.0006329112],"domain_scores_gemma":[0.9988975,0.0001486303,0.0002147591,0.0003386131,0.0003338729,0.00006664424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000586416,0.0003654126,0.004745971,0.0001776758,0.0001675897,0.0002763042,0.02799135,0.002036051,0.534979,0.2136154,0.006107174,0.2094794],"study_design_scores_gemma":[0.0007208313,0.000409305,0.0006610384,0.001075779,0.00002851593,0.00001713574,0.006282137,0.2986321,0.6586703,0.0015854,0.03065628,0.001261135],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8813881,0.0008293896,0.1102692,0.002428931,0.0006133741,0.0001821823,5.389885e-7,0.002578454,0.001709744],"genre_scores_gemma":[0.958311,0.00003817539,0.04071861,0.000361212,0.00006974825,0.00004665657,0.000001317926,0.00002448338,0.0004287453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2965961,"threshold_uncertainty_score":0.9999321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233115322260336,"score_gpt":0.2219208070950579,"score_spread":0.2095896538724545,"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."}}