Theorizer

“Theorizer: Turning thousands of papers into scientific laws”

• allenai.org/blog/theorizer
• github.com/allenai/asta-theorizer/

Memo

Each theory that Theorizer outputs is structured as a set of ⟨LAW, SCOPE, EVIDENCE⟩ tuples:

• The law is a qualitative or quantitative statement—a regularity Theorizer believes holds. A qualitative law might express a directional relationship (“X increases Y” or “A causes B”), while a quantitative law specifies explicit numerical bounds.
• The scope indicates where the law should hold, including domain constraints, boundary conditions, and known exceptions (e.g., “applies only for small R” or “does not hold when P is present”).
• The evidence is extracted empirical or observational support traced back to specific papers in the input corpus (additional details below), including experimental findings, reported effects, and quantitative results that bear on the law.