
Highest temperature in Denver on Oct 28, 2026: PBE moves “71° to 72°” down to 5% from 30%
New forecast guidance reached the model between 17:00 UTC and 23:00 UTC on Oct 27. Same model version, later data cutoff: here is exactly which inputs changed.
Photo: Quintin Soloviev · CC BY 4.0 · Wikimedia Commons
71° to 72° · pbe-weather-maxtemp@1.1.0 · 17:00 UTC → 23:00 UTC
Highest temperature in Denver on Oct 28, 2026?
71° to 72° · PRE-WINDOW
Quick read
- pbe-weather-maxtemp@1.1.0 moved “71° to 72°” from 30% to 5% (−25 pts).
- Later data cutoff: Oct 27 17:00Z → Oct 27 23:00Z; same model version, so the move reflects inputs, not a model change.
- Primary inputs changed: GFS MOS forecast high, National Blend of Models forecast high.
- The Kalshi mid captured with each snapshot went from 2% to 2%.
What changed in the inputs
Between the snapshot captured at Oct 27 17:00Z (data cutoff Oct 27 17:00Z) and the one at Oct 27 23:00Z (cutoff Oct 27 23:00Z), the same model version — pbe-weather-maxtemp@1.1.0 — moved “71° to 72°” from 30% to 5%. The model inputs that changed: GFS MOS forecast high from 68°F to 67°F; National Blend of Models forecast high from 70°F to 66°F.
| Input | Before | After | Primary |
|---|---|---|---|
| Guidance lead time | 19h | 13h | — |
| GFS MOS forecast high | 68°F | 67°F | yes |
| National Blend of Models forecast high | 70°F | 66°F | yes |
This page reports which stored inputs differ between two immutable forecasts. It does not claim why the underlying weather guidance changed.
The forecast path
Data table
| Time (UTC) | Source | Value % |
|---|---|---|
| Oct 27 14:04Z | PBE pbe-weather-maxtemp@1.1.0 | 21 |
| Oct 27 14:04Z | Kalshi mid | 6 |
| Oct 27 14:06Z | Kalshi mid | 5 |
| Oct 27 14:08Z | Kalshi mid | 3 |
| Oct 27 14:13Z | Kalshi mid | 2 |
| Oct 27 15:00Z | Kalshi mid | 2 |
| Oct 27 16:00Z | Kalshi mid | 2 |
| Oct 27 16:36Z | Kalshi mid | 2 |
| Oct 27 17:00Z | PBE pbe-weather-maxtemp@1.1.0 | 30 |
| Oct 27 17:00Z | Kalshi mid | 2 |
| Oct 27 18:01Z | Kalshi mid | 2 |
| Oct 27 19:04Z | Kalshi mid | 2 |
| Oct 27 20:00Z | Kalshi mid | 2 |
| Oct 27 21:00Z | Kalshi mid | 2 |
| Oct 27 22:00Z | Kalshi mid | 2 |
| Oct 27 23:00Z | PBE pbe-weather-maxtemp@1.1.0 | 5 |
| Oct 27 23:00Z | Kalshi mid | 2 |
The Kalshi mid captured with each snapshot went from 2% to 2%.
The two snapshots
| Earlier | Later | |
|---|---|---|
| Captured | Oct 27 17:00Z | Oct 27 23:00Z |
| Data cutoff | Oct 27 17:00Z | Oct 27 23:00Z |
| Guidance runs | NWS GFS MOS 2026-10-27T12Z, NWS National Blend of Models 2026-10-27T12Z | NWS GFS MOS 2026-10-27T18Z, NWS National Blend of Models 2026-10-27T18Z |
| PBE | 30% | 5% |
| Market at capture | 2% | 2% |
Evidence & method
What this story is based on. Every value above was read from these immutable records.
- Model
- pbe-weather-maxtemp@1.1.0 · RESEARCH
- Snapshot
- cccf922b-f429-41fb-83fa-d44c1e639f7c
- Compared with
- 4b896143-4e06-4528-864b-8cae9d5081c4
- Captured
- Oct 27 23:00Z
- Data cutoff
- Oct 27 23:00Z
- Market observation
- 2% · captured with the snapshot
- Source families
- NOAA/NWS via Iowa Environmental Mesonet archive · NOAA Regional Climate Centers ACIS · NOAA/NWS api.weather.gov
- Resolves on
- The Weather Company (weather.com/kalshi) — The Weather Company daily maximum temperature for CLIDEN (weather.com/kalshi)
- Independent check
- NWS Daily Climate Report CLIDEN (WFO BOU); NOAA RCC-ACIS USW00003017
- Measurement
- Maximum temperature for the climate day 2026-10-28, 00:00-24:00 local standard time (UTC-7)
- Rounding
- Whole degrees Fahrenheit as reported; preliminary values may differ by rounding/conversion
- Exceptions
- Preliminary data may be revised; the exchange may hold expiration until a non-erroneous revision, else last fair price
- Pre-window only; no current-conditions input
- Guidance can run cold/hot in unusual regimes (see LA diagnostic, 2026-10-04)
Weather · daily high — inputs: National Blend of Models day max (GFS MOS fallback) + station empirical guidance-error tables. This model on the research board →
Market prices are a benchmark only and never enter a PropBetEdge model. Research-stage probabilities; not advice.