Spacer: Towards Engineered Scientific Inspiration

TL;DR

Spacer is a novel scientific discovery system that creatively generates grounded scientific concepts by disassembling information into keywords and exploring unexplored connections, outperforming current LLMs in similarity to top publications.

Contribution

This work introduces Spacer, combining an inspiration engine and a manifesting pipeline to develop creative, factually grounded scientific ideas without external input, leveraging a large academic keyword graph.

Findings

Nuri classifies high-impact publications with AUROC 0.737.

The Manifesting Pipeline reconstructs core concepts with over 85% plausibility.

Spacer outputs are more similar to top publications than SOTA LLMs.

Abstract

Recent advances in LLMs have made automated scientific research the next frontline in the path to artificial superintelligence. However, these systems are bound either to tasks of narrow scope or the limited creative capabilities of LLMs. We propose Spacer, a scientific discovery system that develops creative and factually grounded concepts without external intervention. Spacer attempts to achieve this via 'deliberate decontextualization,' an approach that disassembles information into atomic units - keywords - and draws creativity from unexplored connections between them. Spacer consists of (i) Nuri, an inspiration engine that builds keyword sets, and (ii) the Manifesting Pipeline that refines these sets into elaborate scientific statements. Nuri extracts novel, high-potential keyword sets from a keyword graph built with 180,000 academic publications in biological fields. The Manifesting Pipeline finds links between keywords, analyzes their logical structure, validates their plausibility, and ultimately drafts original scientific concepts. According to our experiments, the evaluation metric of Nuri accurately classifies high-impact publications with an AUROC score of 0.737. Our Manifesting Pipeline also successfully reconstructs core concepts from the latest top-journal articles solely from their keyword sets. An LLM-based scoring system estimates that this reconstruction was sound for over 85% of the cases. Finally, our embedding space analysis shows that outputs from Spacer are significantly more similar to leading publications compared with those from SOTA LLMs.