{"id":"W4387390093","doi":"10.48550/arxiv.2310.02779","title":"Expected flow networks in stochastic environments and two-player zero-sum games","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Computer science; Set (abstract data type); Zero (linguistics); Flow (mathematics); Adversarial system; Generative grammar; Sampling (signal processing); Object (grammar); Theoretical computer science; Mathematical optimization; Artificial intelligence; Mathematics; Computer vision","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":[0.0003152553,0.0004140142,0.0004373112,0.0004248762,0.0001499644,0.0001269382,0.001439514,0.0003216252,0.00001830666],"category_scores_gemma":[0.00009198642,0.0005110868,0.0001043558,0.0006261006,0.0001433001,0.0003696081,0.004152248,0.001241336,0.00005971006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002662679,"about_ca_system_score_gemma":0.00006753799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002137883,"about_ca_topic_score_gemma":0.00007239521,"domain_scores_codex":[0.9973117,0.0002731665,0.0002563718,0.001481931,0.0001421365,0.0005347377],"domain_scores_gemma":[0.9982451,0.000298514,0.0002396492,0.001022946,0.00002216263,0.0001716169],"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":[0.00002233776,0.00003267378,0.005567653,0.00001423704,0.00004786894,0.0004202517,0.0003158478,0.9872068,0.000006274939,0.005746361,0.00005106697,0.0005686882],"study_design_scores_gemma":[0.0008171744,0.00002320775,0.007529856,0.0001304619,0.00003420364,0.00000373997,0.00005837466,0.9798726,0.000002120504,0.01103744,0.00002668865,0.0004640764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08885267,0.00007363157,0.9094904,0.0000618875,0.0008430136,0.0002896754,0.000003743516,0.000257607,0.000127396],"genre_scores_gemma":[0.9944863,0.00008999779,0.004106314,0.00004290444,0.0000943796,0.000002801545,0.00001967497,0.00004149897,0.001116164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9056336,"threshold_uncertainty_score":0.999734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05003588794772058,"score_gpt":0.199117575685199,"score_spread":0.1490816877374785,"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."}}