{"id":"W7112209861","doi":"","title":"ROBUST MACHINE LEARNING USING SUPERQUANTILES","year":2021,"lang":"","type":"dissertation","venue":"Calhoun: The Naval Postgraduate School Institutional Archive (Naval Postgraduate School)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Adversarial system; Artificial neural network; Computation; Support vector machine; Online machine learning; Deep learning; Robotics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.005772816,0.005626554,0.004491755,0.002429305,0.01452517,0.005673051,0.01037187,0.001953966,0.0009989389],"category_scores_gemma":[0.01527723,0.005022899,0.003832776,0.005731697,0.003840018,0.005359997,0.005308358,0.0214849,0.003229086],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00298011,"about_ca_system_score_gemma":0.0140386,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01136032,"about_ca_topic_score_gemma":0.001732732,"domain_scores_codex":[0.9659045,0.00788196,0.005860951,0.007325685,0.007579564,0.005447295],"domain_scores_gemma":[0.980498,0.002781559,0.003947058,0.004609102,0.004436275,0.003728079],"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":[0.002934722,0.001177511,0.008098175,0.001196862,0.003179415,0.003376759,0.003897811,0.9066453,0.01716446,0.04210899,0.001433396,0.008786584],"study_design_scores_gemma":[0.00609261,0.001075575,0.01543003,0.005314236,0.002356837,0.004269451,0.002855113,0.9291824,0.001802285,0.01268781,0.01155613,0.00737758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5726978,0.02046688,0.341706,0.01069091,0.03209813,0.007923653,0.002671958,0.002348418,0.009396229],"genre_scores_gemma":[0.8910543,0.006609232,0.05833807,0.00226604,0.009080046,0.0003611774,0.01877251,0.001214855,0.01230377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3183565,"threshold_uncertainty_score":0.9999143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05439984103169884,"score_gpt":0.2823500705063668,"score_spread":0.2279502294746679,"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."}}