Public forecast 003 · permanent record
Will UK CPI annual inflation for July 2026, as first published, be lower than the 2.6% recorded for June 2026?
RESOLVED — scored against the source named before the outcome was known.
- Question
- Will UK CPI annual inflation for July 2026, as first published, be lower than the 2.6% recorded for June 2026?
- Probability band
- 42–58% — issued 2026-08-14, data cut-off 2026-08-14
- Frozen criterion
- Resolves TRUE if the CPI 12-month rate for July 2026, as first published by the ONS on 19 August 2026, is strictly less than 2.6%. Resolves FALSE if it is 2.6% or higher. Scored against the figure as first published, not against later revisions.
- Resolves by
- 2026-08-19
- Resolution source (named in advance)
- https://www.ons.gov.uk/economy/inflationandpriceindices/bulletins/consumerpriceinflation/latest
- Model
- judgement — reasoning recorded at issue, unchanged since
- Ledger id
lxf_external_003- Outcome
- FALSE — 2.9%
- Evidence, as first published
- The Consumer Prices Index (CPI) rose by 2.9% in the 12 months to July 2026, up from 2.6% the previous month. (source, published 2026-08-19)
- Brier score
- 0.25 — band midpoint 0.50. 0 is perfect, 0.25 is what always saying 50% scores.
Reasoning recorded at issue — unchanged since, including where it turned out to be wrong: This is deliberately a question we do not know the answer to, and the register needs those: a track record made only of near-certainties cannot demonstrate calibration in the middle of the range. The direction of travel has been downward (2.8% to 2.6%), which is weak evidence for a further fall, but a single month's change in the annual rate is dominated by base effects from the corresponding month a year earlier, which were not analysed here. Absent that analysis the honest position is close to even, tilted very slightly toward a fall by momentum alone.
If ten forecasts were issued at this band, the band claims roughly 4 to 6 of them should come true. Calibration — not certainty — is what the register is scored on.
What would prove this system wrong: a forecast on this register edited after issue, a resolution scored against anything but the source named in advance, or an accuracy claim made before ten outcomes have resolved in a domain. Every one is checkable from the raw ledger — the full falsification list.