Oracle Lab
The model, published.
The Oracle watches every pump.fun launch for its first ninety seconds and scores it. This page is the machine that makes the score, not a summary of it: every bucket weight with the number of labeled launches behind it, what actually happened to those launches, the reliability curve it earned on data it had never seen, and the full history of every version it has tried, including the ones that were refused.
It is a lookup table, roughly 32KB. Download it and you can reproduce any score we have ever published, offline, with no key.
What is scoring right now
The exact model this platform is using this second, with the numbers it earned on launches held out of its own training.
Does each tier earn what it claims
The score line is not a percentage: 86 claims a 45% chance, not an 86% one. Each rung is a public promise about measured frequency, so here is the promise next to the measurement, on launches the model never saw. A model whose top band stops clearing its own claim is refused by the promotion gate rather than shipped.
Drive it yourself
Every control below feeds the real weights, in your browser. Nothing is sent anywhere. This is the same arithmetic that scores the live feed.
Every weight, and the evidence for it
One row per bucket. Log-odds is what that bucket adds to the score. Win, rug and run are what actually happened to the launches in it, and n is how many there were. A claim with a small n is a weak claim, and you can see which is which.
What it has learned, and when
The model refits every six hours and only takes over if it beats the incumbent on held-out ranking. Refused candidates are listed here too, with the reason: a registry that shows only the winners is a highlight reel, not a record.
Use it
Zero dependencies. Node, Deno, Bun, Workers, browser. One request, then it is local arithmetic forever.
verify() is the important one. Feed it launches with outcomes you collected yourself and it re-measures our AUC, Brier score and reliability curve on your data. If our published numbers do not survive an independent sample, you should be able to find that out from us.