Rapid advances in Artificial Intelligence (AI) are transforming scientific research. Although geoscience foundation models are still emerging, it is already clear that their development depends on access to large volumes of data. At the same time, the reliability and trustworthiness of AI systems depend on understanding the quality, provenance, timeliness, and governance of the data they are built on. As the saying goes: garbage in, garbage out.

Over the past two decades, the Open Science principle of “as open as possible, as closed as necessary” has encouraged greater transparency and accessibility across the scientific process. However, the rise of AI raises new questions about how to apply this principle in an era of large-scale data aggregation and automated knowledge extraction.

Who benefits from AI systems built on openly shared scientific data? Are our data, metadata, and repositories AI-ready? Can existing research infrastructures support the demands that AI agents may place on them? How can provenance, attribution, licensing, and data-governance principles (particularly Indigenous) be preserved when scientific outputs become inputs for AI models?

This session invites researchers, data stewards, repository operators, infrastructure providers, and AI practitioners to discuss the opportunities and challenges that AI presents for Open Science. Contributions are encouraged on AI readiness, data quality and provenance, repository sustainability, attribution and reward mechanisms, governance frameworks, and emerging tensions between the goals of scientific openness and the development of AI systems. Together, we will explore how the scientific community can uphold the values of Open Science while adapting to a rapidly evolving AI landscape.