The Sloan Foundation has announced funding for a project to develop Formal Abstracts in Mathematics (FABSTRACTS).
To develop software and services for transforming mathematical results as they appear in journal article abstracts into formally structured data that machines can read, process, search, check, compute with, and learn from as logical statements.
- Careful and curated capture of at least 5,000 formal definitions and 2,000 formal abstracts of theorems.
- A “training set” that allows for Machine Learning and other automation techniques to improve the efficiency in capturing formal abstracts by at least 30%.
- A functional service for mathematicians to search and contribute formal abstracts.
- Wide adoption of the service as measured by thousands of unique uses of the service in the first six months it is available.