AI & Environment Resource HubRiebesell et al. · 2025-05-09
Matbench Discovery is a benchmarking framework for machine learning models used in materials discovery, highlighting the importance of task-specific metrics and demonstrating that universal interatomic potentials can effectively pre-screen stable inorganic materials in high-throughput workflows.
Intended audience has not been documented.
Source-specific limitations have not been reviewed. Inclusion and topic labels do not establish effectiveness or reliability.
Riebesell et al.. 2025-05-09. A Framework to Evaluate Machine Learning Crystal Stability Predictions. https://www.nature.com/articles/s42256-025-01055-1.epdf?sharing_token=N5dTEbyOD6QKy6FqnDBy0dRgN0jAjWel9jnR3ZoTv0PaSYjLgi7y4a9LlN5TLXDR9GV8xb903gJNOmMcvEA1s-IflC0MqzHFlYb05uaO2ZVcxc-CBkK1a1bKsjpAEOJUM6we7W9XYousvJRsLsk_y_9a-ZvEp4bgGlLEXvRvw-Q%3D (AI & Environment Resource Hub; record paper-325; collection snapshot 2026-10-04).
Included in the original Scientific Paper collection. Labels below are metadata based suggestions. They are not verified findings, claims of effectiveness, or endorsements.
Source sheet: Scientific Paper · Row 329 · Original ID: paper-325.
A paper listing is not a quality assessment. Peer review and findings require source-level confirmation. Source link reachable · checked 2026-09-28. Metadata not yet corroborated. The import date is not the original date added.
Suggest a correction for this record →Publication, placement, and evidence are tracked separately. A legacy coverage flag alone does not prove an appearance.
No issue-specific evidence recorded.
Ordered by the number of shared provisional topic labels. This indicates a browsing connection, not agreement between sources.
Shared topics: Materials and critical minerals; E-waste and circularity
Adaptis is a diverse team of carbon reduction experts supercharged by a proprietary software platform for evaluating and optimizing building performance, whole-life carbon, and capex. We generate and recommend decarbonization scenarios, build project sequences, and keep all the data live in real-time so financial decision-makers can find answers in 15 minutes, not 15 days.
Shared topics: Materials and critical minerals; E-waste and circularity
Exponential acceleration meets materials innovation. Our AI-integrated platform is transforming how advanced materials are discovered, designed, and deployed - bringing next-generation solutions from concept to reality.
Shared topics: Materials and critical minerals; E-waste and circularity
Solving the Earth's largest challenge at it's smallest scale. We use genetically engineered bacteria and enzymatic cascades to produce polymers for carbon capture, fuels, industrials, and biotech.
Shared topics: Materials and critical minerals; E-waste and circularity
This dataset provides a large and diverse collection of DFT calculation trajectories for heterogeneous catalysis research. It encompasses a wide range of adsorbates and catalyst surfaces. The data is designed for training and testing machine learning interatomic potentials. AQCat25 consists of approximately 5K materials, 40K intermediate-catalyst systems, and 11.1M frames.