The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale

TL;DR

This paper introduces the Scientific Contribution Graph, a large-scale AI/NLP resource linking scientific contributions and prerequisites to enable automated technological roadmapping and discovery.

Contribution

It presents a novel large-scale graph of scientific contributions and prerequisites, and introduces the task of scientific prerequisite prediction for discovery.

Findings

The graph contains 2 million contributions from 230k papers.

Models achieve 0.48 MAP on predicting scientific prerequisites.

The resource supports impact assessment and automated discovery.

Abstract

Scientific contributions rarely develop in isolation, but instead build upon prior discoveries. We formulate the task of automated technological roadmapping as extracting scientific contributions from scholarly articles and linking them to their prerequisites. We present the Scientific Contribution Graph, a large-scale AI/NLP-domain resource containing 2 million detailed scientific contributions extracted from 230k open-access papers and connected by 12.5 million prerequisite edges. We further introduce scientific prerequisite prediction, a scientific discovery task in which models predict which existing technologies can enable future discoveries, and show that contemporary models are rapidly improving on this task, reaching 0.48 MAP when evaluated using temporally filtered backtesting. We anticipate technological roadmapping resources such as this will support scientific impact assessment and automated scientific discovery.