When many forecasts agree, Zeno checks whether that agreement is earned or fragile.

Zeno · audit

Paste a forecast.
See how it ends.

Words or numbers. Free.

A real past case, outcome included. Nothing new is assessed.

Zeno's verdict · Weather

?

Run the check: Zeno says whether it supports a change, keeps your forecast, needs a range, or has no tested record, computed now by the published model.

economy-ecb: no published example yet · send your own forecasts below, or try another field

Ensemble weatherReplay · outcome already known

Sydney temperature · 24 hours ahead

Case evidence

Zeno moved the panel estimate toward the outcome and flagged two narrow forecasts. UKMO missed; ECMWF's range held, so that one was a false alarm.

Served answer

Zeno correction

Published answer · run it to see today's

Check my forecast · guided
ForecasterLowMiddleHigh
ecmwf_ifs025_ensemble
gem_global_ensemble
icon_seamless_eps
ncep_gefs025
ukmo_global_ensemble_20km
Advanced · edit the raw request

Forecast spectrum

Agreement meets reality.

━ supplied 90% range● forecast│ observed 22.2°C
21.2°C
26.5°C
29°C
21.6°C
27.2°C
26.5°C
25.1°C
18.8°C33°C

Zeno replay · Decision · 2026-09-24 07:00 UTC · n 5 forecasts · 1 replay case

evidence +
Uncertainty · not measuredModel & method ↗

panel

26.5°C

Zeno

25.1°C

actual

22.2°C

UKMO66% · correct warning
ECMWF88% · false alarm

% = chance that forecaster misses its own 90% range · not a chance of “surprise” or profit

Assessment scope
  • range supplied · judged
  • point + range · judged
  • point alone · kept, support named
Show the evidence · past misses, inside a check, review budget

Explore a field · which confident forecasts missed

01 / Explore

dot = checkable forecasts (log)○ hollow = not measured◯ warnings beat every rival◯ ahead of mostrings = practice test on past data · no sealed live result yet

02 / Investigate

ECB

Three skills · this field

  • Correct the forecast

    promising · your forecast returned for now

    Passed, but only 7 distinct outcomes behind 82 test cases.

  • Warn: one forecaster wrong

    ahead of most rivals · +16.8%

    practice test on past data · 12,040 rows · not proven

  • Warn: whole panel wrong

    not measured yet

    no validated test yet

proven only after its own judging · run receipts ↗

No market comparison, shared-miss pairs or replay cases recorded for this field yet.

Check a forecast in this field →

past replay · already resolved

What a check looks inside.

forecast scan · Santiago · Temperature at 2 m · valid 2026-10-18 16:00

systems

6

distinct families

5

own ranges missed

6 of 6

still missed after correction

2 of 6

ECMWF AIFS

family ecmwf

no recordstill misses

ECMWF IFS

family ecmwf

widened ×1.9now covers

GEM · Canada

family cmc

widened ×2.1now covers

ICON · Germany

family dwd

widened ×2.0now covers

GEFS · US

family ncep

widened ×2.3now covers

UKMO · UK

family ukmo

widened ×2.3still misses

14.7°C25.3°C

Read: 5 independent developers agreed, and all 6 ranges missed on the same side. Agreement here was one shared mistake, not five confirmations.

Thin bar: the system's own 90% range. Wide bar: the range after the correction its past record earned (none where no record exists). Teal line: observed 23.1°C. Source Offdiagonal failure-atlas-v1/weather/weather-ensemble-residuals.parquet.

review budget

How many alerts are worth it?

of 100 alerts

62 real misses · 38 false alarms

share of all confident misses caught

33%

The rest still slip through. Alerts fire above the level that flagged the riskiest 10% of training cases.

  • ensemble weather only
  • confirmation period · v0.57
  • retrospective, not prospective