FORECAST METHOD
How the Codex reset forecast works
Codex Reset separates public wording from historical cadence, publishes the evidence behind each percentage, and keeps the limits close to the claim.
What the percentage means
The displayed percentage follows the strongest current public wording from Tibo. A dated commitment ranks above a plain promise, and a plain promise ranks above a tease. In quiet periods the page returns to the cadence model.
| public signal | score | what it establishes |
|---|---|---|
| Dated commitment on Tibo's timeline | 93% | Tibo names a date or window in a top-level post or self-thread. |
| Plain promise on Tibo's timeline | 83% | Tibo plainly says a reset is coming but gives no time. |
| Dated commitment in a reply | 80% | The same dated wording appears in a reply to another account. |
| Tease with additional evidence | 55% | A public tease is supported by additional evidence without changing what Tibo said. |
| Tease on Tibo's timeline | 50% | Hedged, joking, or suggestive wording appears in a top-level post or self-thread. |
| Tease in a reply | 40% | Suggestive wording appears only in a reply to another account. |
At 50% or above, subscribers are notified. Lower scores stay visible in the radar without a loud alert.
The cadence model, honestly
When no scored wording is live, rate-v3 estimates a recent reset rate from the latest eight intervals with a 60-day half-life. It treats arrivals as memoryless: waiting longer does not raise the odds.
The model rounds its 24-hour and 48-hour outputs to five-percentage-point steps. It describes irregular goodwill resets in the verified record; it does not turn them into a schedule.
inference In the live API snapshot observed 2026-08-28, the walk-forward test covered 295 predictions. rate-v3 recorded a Brier score of 0.104, versus 0.106 for the naive baseline; lower is better. It tied the previous rate-v2 score at 0.104, so this is evidence against the naive baseline, not proof that rate-v3 beats every alternative.
Track record
The score-v1 calibration snapshot dated 2026-08-27 reports resolved samples exactly as observed. Small samples stay small: no smoothing, extrapolation, or hidden misses.
| band | resolved n | hits | hit rate | open |
|---|---|---|---|---|
| dated commitment | 2 | 1 | 50% | none |
| plain promise | 0 | — | insufficient history | none |
| tease | 0 | — | insufficient history | 1 open sample at score 50; excluded from n until its evaluation window closes. |
| additional-evidence watch | 0 | — | insufficient history | none |
Updated monthly as an append-only snapshot; an earlier month is never overwritten.
The curated timeline is the best public landing-time proxy, not direct per-account telemetry. A hit means a verified reset landed inside the declared window plus the published 60-minute grace.
When resets happen
The UTC histogram below groups the verified announcement record by hour. The pattern is a rhythm, not a schedule: historical clustering cannot name the next arrival.
Every recorded announcement is shown in the same hourly bins used on the homepage.
Boundaries
These limits travel with the forecast so an excerpt does not overstate what Codex Reset knows.
- Codex Reset cannot see anyone's OpenAI account, quota, or usage. Personal countdowns use only times the visitor enters, and the /codex-usage paste analyzer keeps supplied text in the browser.
- A reset forecast is a probability derived from verified public signals and cadence. It is not an OpenAI schedule, leak, or commitment, and it does not predict outages.
- A reset is called verified only when a public announcement says so. Timing that merely sits near an incident is labeled temporal, never causal.
- Codex limit numbers are quoted from OpenAI's published pages with their checked date. Where OpenAI publishes no number, including the weekly quota size, Codex Reset says so instead of estimating.