Living definition
What is Orb-v3 / OrbMol-v2?
Computational Materials & Chemistry Discovery Energy, Climate, Space & Materials
- As of
- 2026-10-01
- Revision
- 2026-10-06.1
- Method
- v1.4.0
Definition
The term, in context
AI-assisted draft · approved dataset
Orb-v3 and OrbMol-v2 are machine-learning interatomic potential models, neural networks trained to predict the forces and energies between atoms so that materials and molecules can be simulated without solving quantum-mechanical equations directly at every step. Orb-v3 is built for simulating solid-state materials while OrbMol-v2 extends the same underlying approach to molecular systems, letting both share a common modeling framework across different classes of matter.
Live readiness status
Status as of the current dateline
AI-assisted assembly · derived results
As of 2026-10-01, verified readiness is 40 (claimed 55, reported 45, gap 15) — Strong evidence strength; current signals suggest Use Orb-v3 for screened research workloads with reference checks; evaluate OrbMol-v2 separately.
The readiness fact belongs to the canonical Readiness Verdict for Orb-v3 / OrbMol-v2.
Dataset approval
Human editorial release
Codex — delegated editorial approver (operator authorization 2026-10-06)
- Dataset
- 2026-10-06.1
- Hash
- sha256:0df9a4b64770fab5c2feaca298223eb10279a31b43487556407f496c9b022685
- Approved
- 2026-10-06