Methodology

Evidence first. Forecast second.

The system records what a source actually establishes, preserves uncertainty, and withholds probability claims until they beat a simple baseline in repeated evaluations.

The core rule

Timing and proof are different questions.

A statement that a reset is planned can support a forecast. It cannot prove the action happened. An official completion post can establish that the action was triggered. It cannot prove the change reached every account. Reset Beacon tracks these as separate states.

When the evidence feed fails, the forecast disappears. Stale confidence is worse than an explicit unknown.

State model

What each label establishes.

The public label advances only when evidence meets the rule for that state. Corrections can move an event backward.

No current signal
No fresh evidence supports a special reset event.
Unverified report
A claim exists, but its origin, context or independence is not strong enough for scheduling.
Official intent
An authorized source states that a reset is planned, without a usable time.
Officially scheduled
An official source gives a date, time or bounded window. The original wording and timezone are retained.
Action claimed
An official source says the reset action completed. Account propagation may still be pending.
Rollout observed
Fresh, non-duplicate paid-account reports show before-and-after changes across more than one plan and region. Sample limits remain visible.
Account confirmed
A user’s fresh account reading shows a material allowance change outside its natural reset and without consuming a banked credit.
Window passed, unconfirmed
The scheduled window ended without enough action or rollout evidence.
Corrected or cancelled
A source changed the timing, withdrew the plan, or later evidence invalidated the event.

Time handling

One instant, three useful views.

Every machine-readable time is stored as an exact UTC instant. The page then renders it in the visitor’s device timezone with Intl.DateTimeFormat. The source timezone remains directly below it, and UTC is available as an audit fallback.

No Chicago defaultA visitor in California sees Pacific local time. A visitor in Chicago sees Central local time. If a source writes “PST” during daylight time, the literal offset and likely local-time interpretation remain distinguishable until clarified.

Evidence weight

Source strength is not a vote count.

Ten reposts of one claim remain one underlying source. We cluster duplicates before they can affect the state.

Evidence classTypical useCannot prove
Official explicit timeScheduling a reset windowCompletion or account propagation
Official clarificationResolving date, hour or wordingThat the action happened
Official completion statementAdvancing to action claimedThat every account updated
Fresh account readingPersonal account confirmationUniversal rollout by itself
Independent paid-user reportsMeasuring rollout breadthOfficial scheduling
Status incidents and historical patternsContext and prior probabilityA special reset commitment

Accuracy

Scores must earn their place.

A future probability model will use time-bucketed event forecasting and be tested on data it did not train on. Published evaluations will include Brier score, log loss, calibration, interval coverage, false alerts, missed events and detection delay.

No probability will appear on the public forecast until the model beats a deterministic baseline in two consecutive rolling evaluations. Until then, Reset Beacon publishes evidence states and bounded windows, not decorative percentages.

Corrections

Source edits, timezone ambiguity and missed windows remain in the event record. Corrections are sent immediately to subscribers who received the affected alert.