Foundation potential
Broad coverage
Pretrained on public and licensed DFT data across the periodic table.
Product 3 of 5 · Interatomic potentials
Equiva is the model layer: equivariant graph neural network potentials that predict energies, forces and stresses at near-DFT accuracy, fine-tuned on your chemistry and served on GPUs.
Abstract
01 · Capabilities
Foundation potential
Pretrained on public and licensed DFT data across the periodic table.
Vertical fine-tunes
Fine-tuned packs for battery materials, then catalysts and semiconductors.
Your fine-tune
Fine-tune on your DFT and experimental data; the result stays in your tenant.
Uncertainty
A calibrated uncertainty with every energy and force, used to flag and route candidates.
Accuracy reports
Error on held-out structures against DFT and, where available, experiment.
GPU serving
Low-latency endpoints for relaxation and MD, served with Triton and TensorRT.
02 · Method
Train the foundation model on large DFT datasets on DGX/HGX.
Adapt to a vertical or to your data, keeping a held-out set aside.
Fit uncertainty so that predicted error matches observed error.
Publish a pinned version as a GPU endpoint used by Dynara and Inventa.
03 · Specification
| Item | Detail |
|---|---|
| Architecture | Equivariant message-passing graph neural network |
| Predicts | Total energy, atomic forces, stress tensor; uncertainty per prediction |
| Accuracy target | ≤ 30 meV/atom MAE on held-out structures in a fine-tuned chemistry (design target) |
| Training data | Public DFT datasets, licensed data where agreed, tenant data only with consent |
| Versions | Semantic versions; campaigns pin a version |
| Synthetic augmentation | Generated structures to cold-start sparse chemistries Planned |
04 · Place in the loop
Equiva sits in the middle of the loop. Inventa asks it for predictions, Dynara runs dynamics with it, and Synthex's measurements come back to fine-tune it. It is the part of the platform that gets better with every round.
Reads the literature and your notebooks, frames the question and drafts the campaign.
Turns the target into candidates and picks the next batch by expected information.
Predicts energies, forces and stresses at near-DFT accuracy, with an uncertainty for each.
Relaxes, scores against the hull and runs GPU molecular dynamics on the survivors.
Sends the short list to partner or in-house labs and brings measurements back.
05 · Questions
Equiva is trained to reproduce DFT, so it inherits DFT's systematic errors and adds its own. It is for screening at scale, with DFT spot checks on the short list.
The uncertainty will tell you. High uncertainty routes candidates to DFT or the lab, and those results fine-tune the model for your space.
Fine-tuned weights trained on your data are yours. Export terms for on-premises use are part of the commercial agreement.
Next step
The 2027 pilot pairs one of your programs with our scientists for twelve weeks. You bring a target and reference data; we bring the GPUs and the models.