Comments48 pages, 27 tables, 4 figures. v3 is a correction release: a full source-verification pass over all 83 references corrects 30 defective entries and withdraws two ancillary evaluations run on synthetic stand-in data; no measured numbers changed. Changelog: 10.5281/zenodo.21858218. Earlier versions: Zenodo concept DOI 10.5281/zenodo.19353663, TDCommons dpubs_series/9683
机构
*
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机学院多媒体信息处理国家重点实验室)
;
EvoPhys AI(EvoPhys人工智能公司)
;
Joy Future Academy, JD(京东探索研究院)
;
The University of Sydney(悉尼大学)
;
The Hong Kong University of Science and Technology(香港科技大学)
;
Beijing Institute of Technology(北京理工大学)
机构
*
Shandong University(山东大学)
;
Boston University(波士顿大学)
;
North China Electric Power University(华北电力大学)
;
National University of Singapore(新加坡国立大学)
;
Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University(山东大学-南洋理工大学人工智能联合研究中心(C-FAIR))
;
Rizhao Steel Holding Group Co., Ltd.(日照钢铁控股集团有限公司)
Comments16 pages, 3 figures, 7 tables. Substantially revised: reframed around an identifiability result for the counterbalanced concentration index, with access configuration presented as one generator of the failure rather than a separate confound. Code and data are included as ancillary files
PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management
PortBench: 一种相关性感知的、全流水线的LLM驱动投资组合管理基准
Yuxuan Zhao, Sijia Chen, Ningxin Su
机构
*
Yantai Research Institute of Harbin Engineering University(哈尔滨工程大学烟台研究院)
;
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
机构
*
Department of Computer and Information Science, University of Pennsylvania(宾夕法尼亚大学计算机与信息科学系)
;
Department of Mathematics, University of Pennsylvania(宾夕法尼亚大学数学系)