KWARD

What it accelerates

KODEX KWARD is a fast, calibrated surrogate for real-device disruption-labelled training (C-Mod/DIII-D/EAST) — reproducing its result at inference speed, so it runs inside a real-time control loop or a design search where the full computation is far too slow to call.

Use it

One line, one contract — a prediction, its uncertainty, and whether the input is in-domain.

from kronos_ml import KWARD

model = KWARD()                          # loads the trained surrogate
y, sigma, in_domain = model.predict(x)   # y = disruption probability
if not in_domain:                       # out of its trusted region
    fall_back_to_full_physics()          # KWARD abstains, never extrapolates

How to trust it

Every KODEX code wraps the shared spine — KHALO for calibrated uncertainty and KGATE for the out-of-domain gate — so it reports how confident it is and abstains rather than extrapolate. Benchmarks are computed on held-out data with a fixed seed; pre-registered misses are kept, not hidden.

In the fleet

Get it · cite it

Part of the open kronos-ml package (Apache-2.0). Open-access deposits with citable DOIs are listed below.

Open-access deposits, each with a citable DOI: