A1: Knowledge Network Development Infrastructure with Application to COVID-19 Science and Economics

NSF Convergence Accelerator支持以使用为灵感的、基于团队的、多学科的努力，以应对国家重要性的挑战，并在不久的将来产生对社会有价值的成果。该项目的目标是建立基础设施，以有效构建知识网络和应用，并通过描述COVID-19科学和经济的具体知识网络来展示该系统。在短期内，这项工作将产生高准确性的数据资源，这将有助于科学家和政策制定者应对病毒及其经济影响。样本目标包括使医学研究人员能够快速识别相关的候选药物，以及使政策制定者能够快速评估新法律的可能影响。该项目将创建编程工具，使知识网络及其应用程序的构建成本大大降低。这种编程工具的基础设施将有助于创建一套庞大而新颖的信息工具，并将大大扩大能够参与创建知识网络资源的人员。由于知识网络将联合收割机独特的数据分析质量与整个万维网的主题广度相结合，因此知识工具的潜在增长非常大，并具有潜在的变革性。 该项目包括与一系列强大的非学术和学术合作伙伴的伙伴关系。这个融合研究团队将整合他们在数据管理、人工智能、编程语言、与COVID-19相关的生物医学主题和经济学方面的多学科专业知识，以及A轨道第二阶段队列资助项目中的其他领域。创建这种知识规划基础设施和具体的知识网络需要解决几个技术挑战。第一个是智能的“知识编译层”，它使有用但快速变化的知识网络看起来足够稳定，以便程序员在编写可靠的代码时使用它们。第二是建立一种机制，在组织内部和组织之间透明地分享知识资源和调试信息。第三种方法是通过用户软件的自动检测来收集知识起源元数据--关于每个数据元素是如何创建的细节。最后一个挑战是创建从文档中获取知识的系统，该系统可以在很少明确的人为监督的情况下生成高准确度的知识网络。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。

The NSF Convergence Accelerator supports use-inspired, team-based, multidisciplinary efforts that address challenges of national importance and will produce deliverables of value to society in the near future.The goal of this project is to build infrastructure for efficient construction of knowledge networks and applications, as well as to demonstrate the system with concrete knowledge networks that describe COVID-19 science and economics. In the short term, this work will lead to high accuracy data resources that will be useful to scientists and policy makers in addressing the virus and its economic impact. Sample goals include enabling a medical researcher to quickly identify relevant candidate drugs, and a policy maker to quickly evaluate the likely impacts of a novel law. The project will create programming tools that will make knowledge networks and their applications far less expensive to build. This infrastructure of programming tools will facilitate the creation of a large and novel set of informational tools and will also significantly expand the set of people who can participate in creating knowledge network resources. Because knowledge networks combine unique data analysis qualities with the topical breadth of the entire World Wide Web, the potential growth of knowledge tools is very large and potentially transformative. This project includes partnerships with a strong set of non-academic and academic partners. This convergence research team will integrate their multidisciplinary expertise in data management, artificial intelligence, programming languages, biomedical topics relevant to COVID-19, and economics, with the other domains represented in the projects funded in the Track A Phase II cohort. Creating this knowledge programming infrastructure and concrete knowledge networks will require solving several technical challenges. The first is an intelligent “knowledge compilation layer” that makes useful but rapidly-changing knowledge networks appear to be stable enough for programmers to use them when writing reliable code. The second is the creation of a mechanism for transparently sharing knowledge resources and debugging information within and across organizations. The third is a method for collecting knowledge provenance metadata — details about how every individual data element was created — via automatic instrumentation of user software. A last challenge is the creation of knowledge-from-document systems that can produce high accuracy knowledge networks with very little explicit human oversight.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.