The model
One network reads the crowd.
9.16M shared parameters compare forecasts, history and cross-member behaviour.
forecast set
members × features
→shared encoder
9.16M parameters
→surprise kernel
cross-member relations
→native head
distribution + warning
forecast set
members × features
shared encoder
9.16M parameters
surprise kernel
cross-member relations
native head
distribution + warning
01 · distribution
What improved.
Every comparison uses later weeks and that source's named reference.
02 · warning
Confidence can be ranked.
Only ensemble weather passed the v0.57 warning gate.
Known limit · 90% ranges covered about 81% (crypto), 85% (ensemble weather), 87–89% (others)
03 · serving
Proof controls the switch.
A shared model does not mean a universal claim.
Crypto price ranges
Zeno correction
+11.7%
Ensemble weather
Zeno correction
+5.6%
Deterministic weather
correction · no history
+6.2%
COVID-19 hospitalisations
correction · no history
+11.8%
Sea conditions
correction · no history
+3.2%
Prediction markets
reference kept
RSV
reference kept
FluSight
reference kept
ForecastBench
reference kept
Numinous AI forecasters
learn-only
04 · boundary
No future leaks backward.
Inputs are admitted only when they were knowable; missing history remains missing.
input
forecast set + available history
kernel
member and pair relations
output
distribution + warning + identity