Capability benchmark · Materials science · Chemistry · Climate

OpenDAC releases a large dataset for direct-air-capture sorbents

OpenDAC releases a large dataset for direct-air-capture sorbents: capability signal for AI systems on research-adjacent tasks.

Summary

The arXiv paper introduces Open DAC 2023, a dataset of more than 38 million DFT calculations on over 8,400 metal-organic framework materials containing adsorbed CO2 and water. It also provides baseline machine-learning models for direct-air-capture sorbent discovery.

AI role

AI systems are tested on research-adjacent capabilities relevant to materials science, chemistry, climate.

Narrative role

This is supporting evidence for whether AI systems can perform research-adjacent tasks needed before stronger discovery or acceleration claims.

Caveat

Benchmark, model, or tool performance is an upstream capability indicator, not proof of new scientific discovery.