Public track record · no login needed · aggregates only

We grade ourselves in public.

Every prediction is recorded the day it's made, scored when it matures, and dead companies stay in our numbers. This page is the scoreboard — it updates nightly from the same ledger our models are judged against.

Nothing backfilled, nothing hand-picked, nothing quietly deleted.

A record that accrues in the open.

A prediction only counts when its full horizon has elapsed — 60, 90, or 180 days after it was made. Until then it sits on the record, in flight, waiting to be scored. Nothing here is backfilled or hand-picked.

Model v2 · public record since June 10, 2026
Predictions on the record
public record since June 10, 2026
Matured & scored
full horizon elapsed
Win rate
positive return at maturity
vs S&P 500 (SPY)
return relative to SPY, same window
predictions in flight
Each one was written to the ledger on the day it was made and will be scored the day its horizon ends — win or lose.
first picks recorded
first maturities
first full cohort scored
Model v2 public record since June 10, 2026 point-in-time data, leak removal, validated ranking

When we say 60%, does it happen 60% of the time?

This is a reliability diagram — the standard honesty test for probabilistic forecasts. We group matured predictions by the probability we originally published, then plot what actually happened. A perfectly calibrated model sits on the diagonal.

Accruing — fills in as picks mature
How to read this chart

Worked example: suppose we publish 100 picks, each with a “60% probability of rising.” If about 60 of them actually rise by maturity, the dot lands on the diagonal — our 60% really meant 60%. Dots above the line mean we were too cautious; below, overconfident.

Most services never show you this chart, because it can't be massaged: the probabilities were published in advance and the outcomes are just arithmetic. We plot it for you either way.

This chart fills itself in as picks mature — the first cohorts are in flight right now. Bookmark this page and watch the dots appear.

The six rules that keep this honest.

Plain language, no fine print. These rules are enforced by the pipeline itself, not by an editor choosing what to show.

Recorded at prediction time
Every pick is written to an append-style ledger the day it's published, with its probability, price, and horizon. No backfilling, no quiet edits after the fact.
Matured-only scoring
A pick counts only when its full horizon has elapsed. We don't cherry-pick mid-flight winners or quote a position's best day as its result.
Survivorship honesty
A pick that goes to zero stays in our stats. Delisted and acquired companies are tracked to the end, so the averages include the failures — the way real portfolios do.
Calibrated probabilities
Our 60% is meant to mean 60%. Probabilities are statistically recalibrated against realized outcomes, and the chart above is the public audit of whether that's working.
A versioned public record
Our public record begins June 10, 2026 — the day we shipped point-in-time data, lookahead elimination, and a validated ranking. Earlier development-era predictions are preserved internally but are not part of the public record. Future model upgrades appear here as separate versions, each scored on its own record. Nothing is ever deleted.
What we don't claim
No promised returns, ever. Past results don't guarantee future ones, models have known limitations, and nothing on this page is investment advice. We show you the record; the decisions stay yours.

Hold us to this page.

The scoreboard updates nightly, and it doesn't forget. See the product behind the record, or take the 3-minute tour first — no signup needed.