OMol25 and UMA: quantum-chemistry data and a universal model for atoms
Archived from discovery counts: the represented event releases a molecular dataset and an interatomic model, without identifying a specific new chemical finding or application outcome. Meta released Open Molecules 2025, which it calls the largest and most varied set of high-accuracy quantum calculations for biomolecules, metal complexes, and electrolytes (about six billion compute hours), and UMA, an interatomic potential trained on over 30 billion atoms. The post gives no numerical accuracy values.
Technology: UMA (interatomic potential), OMol25
Publication: Preprint · Test context: Test context unspecified in annotation. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Preprint
- Test type: not reported
- Tested: Not reported
- Still unknown: The post gives no numerical accuracy values or evaluation method, and no limitations are stated.
- AI role: A machine learning interatomic potential (UMA) was trained on the OMol25 calculations and data from Meta's datasets.
Evidence sources: https://ai.meta.com/blog/meta-fair-science-new-open-source-releases/ · https://arxiv.org/abs/2505.08762
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: blog. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Editorial assessment: Impact 4/5 · Validation 1/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.