NOVA: Fundamental Limits of Knowledge Discovery Through AI
NOVA:通过人工智能进行知识发现的基本限制
机构 * University of Southern California(南加州大学) ; Northeastern University(东北大学) ; Massachusetts Institute of Technology(麻省理工学院)
AI总结 本文提出NOVA框架,将“生成-验证-积累-再训练”循环建模为知识空间上的自适应采样过程,识别了知识覆盖有限域的条件及失败模式,并证明了发现成本与Zipf定律相关的标度律。
Comments Added an explicit recursive retraining model showing how accepted outputs reshape future generation. New results characterize when repeated retraining suppresses undiscovered artifacts and when mixing updates with a fixed base distribution preserves exposure. Corrected the Zipf discovery-cost proof and expanded the analysis. Main results and implications remain unchanged