{"id":"W3198238708","doi":"10.48550/arxiv.2102.05196","title":"Once is Never Enough: Foundations for Sound Statistical Inference in Tor\\n Network Experimentation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Sound (geography); Computer science; Statistical inference; Artificial intelligence; Mathematics; Statistics; Acoustics; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002008377,0.0002003607,0.0003996052,0.0001616843,0.000135441,0.0001555875,0.0002629218,0.000194142,0.0008342686],"category_scores_gemma":[0.00005646646,0.0002896975,0.0001270135,0.000303047,0.00006570278,0.000360798,0.0002071449,0.0002622872,0.00004912102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003106924,"about_ca_system_score_gemma":0.0001136879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007861498,"about_ca_topic_score_gemma":0.000345511,"domain_scores_codex":[0.9985042,0.00001202363,0.0004179333,0.0007365184,0.00002046221,0.0003088371],"domain_scores_gemma":[0.9989372,0.0001505863,0.0003372463,0.0004166016,0.00007922408,0.00007909742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002333308,0.00007650482,0.103501,0.00005383197,0.00005979456,0.00002619095,0.0004729468,0.2972227,3.438761e-7,0.5980667,0.0004237967,0.00007284026],"study_design_scores_gemma":[0.0007551894,0.0000510257,0.03013537,0.00008678323,0.00003769942,7.12291e-7,0.0003951043,0.7707407,0.000007744689,0.1883048,0.008856677,0.0006282087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4014262,0.0003210258,0.5949508,0.00009743538,0.0006795958,0.0003086368,0.000213306,0.00001971008,0.001983321],"genre_scores_gemma":[0.9957236,0.00061101,0.001317941,0.0002646453,0.0001424952,0.000007086038,0.0003053978,0.0000206037,0.001607187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5942975,"threshold_uncertainty_score":0.9999555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1885894387928196,"score_gpt":0.2435710650988728,"score_spread":0.05498162630605324,"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."}}