AI 中文总结
研究从公司披露文本构建公司网络，提出基于大语言模型的流程，应用于纳斯达克100指数成份股公司文件，生成含149条边的网络，经审计确认部分边有效，恢复跨行业关系，消融研究表明相关方法对网络质量有贡献。
AI 中文摘要
标准行业分类系统（如全球行业分类标准GICS）将每个公司归入单一行业，但冲击传播的经济关系（如供应商协议、客户集中度、知识产权许可、云服务依赖和电力购买合同）常跨越行业界限，且常仅在非结构化文本中披露。我们将公司层面邻接矩阵的构建表述为一个测量问题，并提出基于大语言模型的流程，从公开披露中提取加权、有向、实时的公司网络。应用于42家纳斯达克100指数成份股公司最新的10-K文件，该流程生成一个包含149条有向边的网络。对抗性审计确认了88%权重至少为0.1的抽样边，若纳入经济上合理但记录薄弱的关系，这一比例增至100%。被反驳的边完全集中在网络权重最低的部分。所得网络与GICS一致，在行业分类信息丰富时，行业内连通性提高了1.9倍，同时还恢复了标准分类无法代表的具有经济意义的跨行业关系。消融研究进一步表明，多智能体融合、逆文档频率过滤和相对阈值化对网络质量都有可衡量的贡献。
英文摘要
Standard industry classification systems such as GICS assign each firm to a single sector, but the economic relationships through which shocks propagate, such as supplier agreements, customer concentration, intellectual property licensing, cloud service dependencies, and power purchase contracts frequently cross sector boundaries and are often disclosed only in unstructured text. We formulate the construction of a firm-level adjacency matrix as a measurement problem and propose an LLM based pipeline that extracts a weighted, directed, point in time corporate network from public disclosures. Applied to the most recent 10 K and 10 K filings of 42 Nasdaq 100 constituents, the proposed pipeline produces a network containing 149 directed edges. An adversarial audit confirms 88% of sampled edges with weights of at least 0.1, increasing to 100% when economically plausible but weakly documented relationships are included. Refuted edges are concentrated entirely in the lowest-weight portion of the network. The resulting network is consistent with GICS where sector classifications are informative, exhibiting a 1.9-fold increase in within-sector connectivity, while also recovering economically meaningful cross-sector relationships that standard classifications cannot represent. Examples include nuclear power-purchase agreements connecting utilities with hyper scale technology firms and GPU-cloud dependencies within the emerging AI infrastructure ecosystem. Ablation studies further demonstrate that multi-agent fusion, inverse-document-frequency filtering, and relative thresholding each make measurable contributions to network quality.
Comments9 pages, 4 figures and 4 tables
