Loading…

Prediction evidence

correctPolicy v1.0

Source post

Published 18 May 2026, 11:24 UTC · fetched 6 Nov 2026, 14:20 UTC

exitpump

@exitpumpBTC

Quoting · 18 May 2026, 10:43 UTC · context given to the AI

$BTC We had strong absorption of buyers by passive sellers at 78.4k just before price nuked. At that point it was obvious that things not looking good. https://t.co/sYQVWg2omw

$BTC It's only in hindsight now, i talked about it in discord before price nuked, said more likely will go lower, now I just explain it for those who want to learn. https://t.co/ocb8G4WOq0 https://t.co/1pVhsM9LDx

View original on X ↗

How this was scored

Deterministic: the same prices and policy always give the same result

Baseline: first BTC price at or after publication, $77,239 at 18 May 2026, 12:00 UTC.
Evaluation: price at the end of the 24 hours horizon, $76,641 at 19 May 2026, 12:00 UTC.
r = 76641.3 / 77238.52 − 1 = -0.8%
Direction d = −1 (bearish), so d × r = +0.8% (neutral only if the price is unchanged) → correct

Only the end-of-horizon price counts. A brief move followed by a reversal is not a success. Read the methodology

AI interpretation

Uses only text available at publication time

Asset: Bitcoin (BTC)
Direction: ▼ Bearish
Intent: explicit
Horizon: 24 hours (default, none stated)
Evidence span: “$BTC It's only in hindsight now, i talked about it in discord before price nuked, said more likely will go lower, now I just explain it for those who want to learn.”
Confidence: 98%
Review state: auto accepted
Model / prompt: gpt-6-luna+decisions · decisions-v3

Prediction evidence

Source post

How this was scored

AI interpretation

Outcome record

Request a correction