Forecast evidence, frozen at the decision

See which forecasters miss together.

Every forecast kept as issued, with its real clocks.

What is in the record · measured 2026-10-22

Headline numbers

13.5M
forecasts

ForecastBench panels: 13,523,509 rows, 6,311,674 with real answers

19,019
markets with full price history

Of 19,030 verified temperature markets; 11 have no Polymarket history, 0 failed (v6.11)

808
forecasters in 82 families

756 AI models, 38 human groups, 6 baselines, 8 aggregates

12
domains

Geopolitics & world events, Single-run weather, Ensemble weather, Prediction markets, Market traders, Crypto, Central-bank surveys, Economics, Energy, Health, Space weather, Hurricanes

431k
weather training cases

205,746 single-run + 225,235 ensemble, 59 sites, 18 weeks

38
data defects published

Two audits on 2026-10-20: all 11 critical fixed (invented or early clocks, answer-conditioned forecasts, stalled collectors); 12 lower-severity still open. Affected rows are excluded or flagged, never silently kept.

At a glance · 2026-10-22

What changed this week

Market prices

99.94%

19,019 of 19,030 markets priced. 11 have no history; none filled with zeros.

Forecasters with fixed IDs

  • COVID-19 hub (legacy)129
  • FluSight126
  • FluSight (legacy)44
  • COVID-19 hub29
  • RSV hub20
  • Weather ensembles5
  • Crypto replay3

356 forecasters, 10 documented links. Without a link, independence is unknown.

Warning list

1,386 cases · 0 resolved so far

Every case is registered before the outcome, at most 50 alerts per run. Outcomes arrive as events resolve.

Releases

  1. v6.6 Variable catalogue, GFS, 2.96M station readings
  2. v6.7 Warning ledger, forecaster scores
  3. v6.8 Corrected market ranges
  4. v6.9 Price history begins (1,517)
  5. v6.10 ForecastBench dates, track records
  6. v6.11 All 19,030 markets priced
  7. v6.12 Market events with pre-deadline prices (18,466)
  8. v6.13 ECB labels, Numinous episodes, energy, river flow (current pin)

Each release is fingerprint-checked after download. Pin v6.13 (3c16e8fd) or its parent 8c5d3ad1; older revision IDs were removed on 23 Oct.

Latest frozen release

handoff-v6.13-20261024

commit 3c16e8fde1ac · +13 files · verified 2026-10-24

All data we hold is cleared for sharing with Zeno and training. Only leakage, missing outcomes and Zeno's own test set are kept out. Every new file was re-downloaded with the repository token and matches its fingerprint.

The signature view

Which forecasters miss together?

Nine weather models, 7 marine sites, 21 frozen days. The live miss-together file covers 543 weather system pairs, each with its shared-outcome count.

Inspect full report
cma grapesecmwf aifsecmwf ifsgemgfsiconjmameteofranceukmocma grapesecmwf aifsecmwf ifsgemgfsiconjmameteofranceukmo
pair
ecmwf aifs × ecmwf ifs
shared outcomes
1,592
miss rate A / B
16% / 16%
missed together
7.5%
if independent
2.4%
ratio
3.12×
Each cell is one pair of models. Darker means they missed the same outcome more often than chance alone would predict. Select a cell for the exact counts. On small screens, drag sideways to see every column.
SHARED OUTCOMES
1,592
WORST PAIR
3.1× chance
CONFIDENT AND WRONG
35,970 cases
More — coverage, method, paths, live record

Coverage

13 domains, one set of clocks

Bar length on a log scale. Muted bars are test-only: kept out of training because their publication times can't be proven.

  • Geopolitics & world eventsForecastBench56,013answered question-horizons · Jul 2024 – Sep 2026
  • Single-run weather7 model centres205,746cases · Jun – Oct 2026
  • Ensemble weatherOpen-Meteo ensembles225,235cases · Sep – Oct 2026
  • Prediction marketsManifold, Polymarket, Numinous170,096resolved questions with prices (97,788 Manifold, 71,195 Polymarket, 1,113 Numinous) · Aug – Oct 2026
  • Market tradersPolymarket wallets457,874trades · 2026
  • CryptoKalshi, Deribit, reference models255,807forecasts (mostly replays) + 51,459 venue quotes · Jul – Oct 2026
  • Central-bank surveysECB SPF156,912probability distributions · 42 rounds
  • EconomicsPhiladelphia Fed SPF1,979,271survey responses (2,250 first-release outcomes, RGDP/PGDP only) · 1968 – 2026
  • EnergyNESO demand vs Elexon outturn137resolved half-hours (1,449 admitted forecasts at release) · Oct 2026
  • HealthCDC FluSight, COVID-19 and RSV hubs567,189distinct dated outcomes (12,433 flu, 536,748 COVID, 18,008 RSV) · 2020 – 2023
  • Space weatherKp observations103,623observations · Sep – Oct 2026
  • HurricanesNOAA NHC ATCF forecast decks + best track152,707forecast rounds (one per method and cycle) + 1,711 best-track rounds · 2024–2025 seasons · collecting
  • Market pricesPolymarket price history119,744pre-deadline price points on 19,019 temperature markets · 2026

Honest comparison

Not the biggest archive. The one built to show shared failure.

Single-domain archives

ECMWF, CDC forecast hubs

They have more: Decades of history in one field.

We add: Many domains joined, each forecaster tagged by family.

Market price feeds

Polymarket, Kalshi

They have more: Deeper live price history.

We add: Individual forecasters and outcomes dated by when they were actually known.

Forecasting benchmarks

ForecastBench, Metaculus, Good Judgment

They have more: Longer human track records in their own question sets.

We add: Who misses together, across benchmarks and the physical world, without future leakage.

Door A / Decision teams

Audit the forecasts you already buy

Analyst estimates, vendor feeds or internal models, assessed against observed outcomes and each other — like the marine audit above, on your data.

Door B / Zeno and ML teams

Train on decision-time episodes

Whole episodes as seen at the decision: every forecast available then, each forecaster's track record, the outcome kept apart. Explicit clocks, verified packs, no leakage.

Current record / Separate from the frozen example

Live evidence, as recorded

Evidence at the decision

The forecast and prior history are kept apart from what was known only afterward.

The frozen worked receipt is temporarily unreadable. Nothing is substituted for it.

Source provenance

Shared-case comparison

Signed errors on outcomes both models answered; not an explanation of shared failure.

Reading recorded comparisons…

Explore coverage