{"id":"W2901827878","doi":"10.48550/arxiv.1811.05381","title":"Sorting out Lipschitz function approximation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Lipschitz continuity; Affine transformation; Robustness (evolution); Norm (philosophy); Mathematics; Mathematical optimization; Applied mathematics; Computer science; Pure mathematics","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":[0.003432493,0.001461013,0.0012985,0.0007121378,0.0008333343,0.001780754,0.001804502,0.002240063,0.00427444],"category_scores_gemma":[0.01959596,0.000751576,0.00109874,0.0005521704,0.002904119,0.004770013,0.00421242,0.003711288,0.001040291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001753605,"about_ca_system_score_gemma":0.001363312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001284406,"about_ca_topic_score_gemma":0.001427023,"domain_scores_codex":[0.9975892,0.0007391025,0.000150708,0.0005629151,0.0007369484,0.0002211282],"domain_scores_gemma":[0.994329,0.002976641,0.0003964421,0.001666677,0.0004692706,0.0001619101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003262101,0.00007334782,0.001769312,0.0002187122,0.0001012438,0.0002877833,0.0002258321,0.5402732,0.01213032,0.3578428,0.0058117,0.08093964],"study_design_scores_gemma":[0.00001360614,0.00005365963,0.0001575097,0.00002867713,0.0000125354,0.00007875977,0.00002103906,0.8005556,0.005722126,0.191294,0.00204833,0.00001404281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02938886,0.0002152283,0.9642023,0.0008699437,0.00005248499,0.00004202905,0.0001165419,0.0009237763,0.004188761],"genre_scores_gemma":[0.7719547,0.0004886246,0.2141361,0.0009832667,0.0001433356,0.0002839701,0.0005516653,0.0007299092,0.01072848],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00427444,"threshold_uncertainty_score":0.01815301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0708494643085336,"score_gpt":0.2053713486700701,"score_spread":0.1345218843615364,"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."}}