v0.3 · multi-fidelity campaign
**multi-fidelity Bayesian-optimization campaign manager** — extends KSEEK from a single next-point to a budget-constrained campaign that chooses which operating point AND which fidelity (reduced twin / μ=400 CGYRO / real-mass gold) to run next. Triage-then-escalate: cheap twin on every uncertain hotspot, escalate the most-uncertain to μ=400, reserve real-mass gold. Under a tight GPU-hour budget it reaches ~2.3× the mean truth-confidence of a naive all-μ=400 plan. Honest: fidelity correlations are assumptions (gold not yet run); GPU-hours only, **no cost figures**.
KODEX KSCOUT is a fast, calibrated surrogate for the full multi-fidelity CGYRO campaign (twin + μ=400 + real-mass gold) — 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.
One line, one contract — a prediction, its uncertainty, and whether the input is in-domain.
from kronos_ml import KSCOUT
model = KSCOUT() # loads the trained surrogate
y, sigma, in_domain = model.predict(x) # y = prediction
if not in_domain: # out of its trusted region
fall_back_to_full_physics() # KSCOUT abstains, never extrapolatesEvery 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.
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: