{"id":"W4399838215","doi":"10.48550/arxiv.2406.12843","title":"Can Go AIs be adversarially robust?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données","keywords":"Econometrics; 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","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005394979,0.0006720939,0.0006098232,0.0005806893,0.0002922132,0.0004320114,0.004253037,0.0006411507,0.0001204253],"category_scores_gemma":[0.0001638879,0.0007962617,0.0004751037,0.001211379,0.0001940053,0.0003804844,0.01115962,0.002562542,0.0003420398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006842021,"about_ca_system_score_gemma":0.0008888721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007879687,"about_ca_topic_score_gemma":0.0002503013,"domain_scores_codex":[0.9960071,0.0003185958,0.0003620585,0.002312277,0.0002669443,0.0007330489],"domain_scores_gemma":[0.9966878,0.0002177898,0.0003425211,0.002216326,0.0002056955,0.0003299004],"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":[0.00001645926,0.00003140354,0.0002412788,0.0001167584,0.0001505044,0.00113586,0.0004593962,0.6981034,0.000008025584,0.2974424,0.001704142,0.0005903576],"study_design_scores_gemma":[0.0004794948,0.00004932082,0.0001513627,0.0002142447,0.0002002124,0.00001367468,0.00008949694,0.8643519,0.00002819253,0.1301657,0.003359884,0.0008964729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02019108,0.0001789122,0.948507,0.00321744,0.005853604,0.0005142275,0.00004862003,0.001612554,0.01987656],"genre_scores_gemma":[0.9783271,0.00009946963,0.01220362,0.0003583206,0.0004652423,0.000001940783,0.0000366977,0.00007479915,0.008432818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.958136,"threshold_uncertainty_score":0.9997386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06371097362501402,"score_gpt":0.2000806973805253,"score_spread":0.1363697237555112,"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."}}