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 · Crypto

?

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.

Crypto price rangesReplay · outcome already known

ETH hourly close

Case evidence

These forecasts are single prices with no 90% range, so Zeno keeps the panel estimate instead of guessing a correction. Send q05/q95 to get one.

Served answer

reference kept

Published answer · run it to see today's

Check my forecast · guided
ForecasterLowMiddleHigh
crypto-replay/meanrev-7d-v1
crypto-replay/momentum-24h-v1
crypto-replay/persistence-v1
Advanced · edit the raw request

Forecast spectrum

Agreement meets reality.

━ supplied 90% range● forecast│ observed 4,614.1
4,441.5
4,174.7
4,431.5
4,431.5
4,121.94,666.8

Zeno replay · Decision · 2025-08-26 06:00 UTC · n 3 forecasts · 1 replay case

evidence +
Uncertainty · not measuredModel & method ↗

panel

4,431.5

Zeno

reference

actual

4,614.1

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

Crypto

Three skills · this field

  • Correct the forecast

    served · beats the best rival

    Passed the sealed exam (after adjusting for testing 13 fields at once) and held on later weeks; 7.9% less error than the previous model on the same cases.

  • Warn: one forecaster wrong

    beats every rival · +13.4%

    practice test on past data · 50,106 rows · not proven

  • Warn: whole panel wrong

    not measured yet

    no validated test yet

proven only after its own judging · run receipts ↗

Surprise Timeline

coinbase-btc-usd-1h: value at 2025-09-01 18:00 UTC

retrospective replay

1 · Forecasts

Forecasters
3 · meanrev-7d-v1, momentum-24h-v1, persistence-v1
Consensus
—
Zeno · warning
—
Outcome
hidden

Zeno replay · Decision 2025-09-01 18:00 UTC · n 1 case of 8,654 in the confirmation period

evidence +
Uncertainty · not measuredrun v044-h200-20261004T1335Z ↗
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