Reproduce “Organizational Learning in Materials Discovery Campaigns: Which Databases, Calculations, and Agent Teams Pay Off” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kinston Ackölf, Taylor D. Sparks
The authors assess how databases affect materials-discovery campaigns by running every subset as a campaign and attributing outcomes to each source. In a measured band-gap campaign, the seven-database pool reached Kendall tau of 0.737, while the best three-source pool reached 0.851 in the first half of the budget. This result is specific to its receiver, pooling method, and early-budget window.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.