Public forecast documentation
80% forecast confidence-band performance
An 80% band is an interval intended to contain outcomes at a stated long-run rate under the method's assumptions. It is not an 80% certainty guarantee.
Historical audit snapshot created 2026-09-10 — not a live/current forecast
Coverage is not certainty
A published 80% confidence band is a lower and upper interval with a nominal target: across an appropriate collection of comparable resolved outcomes, the method aims for the interval to contain about 80% of outcomes. It is not an 80% certainty guarantee for one price.
The September 10, 2026 audit observed 95% coverage for bands labeled 80%. That is higher than the nominal target, but higher observed coverage is not automatically better. Broad intervals can include more outcomes while providing less precise information, so interval width and horizon-level outcomes are needed to assess usefulness.
The related calibration evidence explanation discusses why coverage is one reliability signal rather than proof of predictive accuracy.
| Metric | Value | Sample N | Evaluation period | Interpretation | Limitation |
|---|---|---|---|---|---|
| Observed coverage of nominal 80% bands | 95% observed; 80% nominal | n=40 (retained resolved SOL rows) | Observed target span: 2026-09-07T07:14:30Z–2026-09-10T10:59:20Z; not a prespecified evaluation window | 38 of 40 retained resolved outcomes fell inside the published bands (95%), above the nominal target in this snapshot. | Without interval widths, horizon-level coverage, or a prespecified evaluation design, higher coverage cannot establish useful accuracy. |
Coverage evidence still has limits
The snapshot does not supply interval widths, horizon-level coverage, a prespecified evaluation window, or a non-overlapping evaluation design. The 95% observation therefore cannot be described as 95% accuracy, a guarantee, or evidence that the forecast is better than a baseline.
Data provenance and export status
The statistics shown here come only from the forecast audit snapshot created 2026-09-10. Current values remain on the external live product. The local scheduled-worker forecast table is a distinct implementation and is not represented as that external production feed.
Citation-ready public export status: NOT READY. The retained historical evidence contains 56 total SOL forecast rows and 40 resolved rows, with resolved horizon counts of 6h n=13, 12h n=12, 24h n=9, 48h n=6 and observed target span 2026-09-07T07:14:30Z–2026-09-10T10:59:20Z. These are point-in-time observations, not an immutable issued-and-resolved archive, complete history, or prespecified evaluation window. A current public feed may expose rows, but it is not an immutable versioned research archive. Metrics calculated from a changing feed are not automatically comparable to this dated snapshot. A research export would need versioned records with forecast ID, asset and venue, UTC issue and target timestamps, horizon, point prediction, interval bounds, direction probability, model version, outcome source, observed price, resolved-at time, scoring-rule version, and content hash. No research export is available from these pages.
The existing Dataset JSON-LD preserves the audit date rather than implying freshness.