Google Research·· 2026-05-20
Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
AI summary
Google released Empirical Research Assistance (ERA), a research tool using Gemini to write and optimise scientific code. Its paper was published in Nature today, and the tool is available to scientists worldwide as part of Gemini for Science.
Selection record
Threshold 60Official, first-handFirst 78Second 71
AdmittedSum of both 149 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Google用Gemini开发ERA科研工具，属AI技术应用
- Why it was chosen
- Nature evaluation results, eight application papers and trial access to Computational Discovery show the deployment scope of scientific coding agents.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google