Science should keep living.
From published result to living evidence
Science is not static, and papers are not the final say on any topic. They are the beginning of a journey towards a deeper understanding of the world. AI agents make it possible to revisit influential research as new opportunities arise, asking what still holds, what has changed, and why. Our goal is to not assess whether the paper was correct at the time of publishing but to provide resources and venues for continued discussions of influential research.
Our Approach
We use SAI's replication agent to attempt to reproduce each paper's key findings, documenting what matches and what does not, before extending the analysis to newer data where possible. The AI agent will first look for public replication packages if available and then identify relevant data sources for extending the analysis. As a result, we may not use exactly the same dataset and setup. The exercise is closer to writing a follow-up paper than strict replication. We sanity-check the results and reach out to the original authors for feedback. We also invite the community to identify issues and post comments, helping us improve the analyses over time.
We make our replication repositories public on GitHub so that anyone can start from an existing replication, inspect its choices, and extend it. We hope Living Science will give these efforts a shared home, so that each update can become a starting point for the next.
Read our announcement →Community Effort
We invite the community to participate in the initiative of living science. We welcome nomination of papers for replication and extension.
Nominate a paper →Open to scrutiny
This work is driven by verification agents by SAI. It can make mistakes. We provide the whole replication process, including the methods, figures, and supporting code. We welcome feedback and corrections from the community. You can report issues on github or contact us directly.
SAI