Research & tooling
Every position you hold has a range of outcomes, not an answer. Sanctuary Research publishes the shape of that range — scored by nine academic factor models, graded on five years of data they never saw, and capped so no single name can decide your year.
Free tier: the daily briefing and one tracked portfolio. No card required.
The graphic below is an illustrative probability distribution: a dense centre of likely outcomes with thin tails either side. Its labelled points are:
the tail we size for p10 median p90Start with the free briefing
Indices, macro prints and what actually moved, with a source pinned to every claim — the cheapest way to find out whether we think the way you do.
Free, no card. Unsubscribe from any of them.
That sentence is the whole company. Everything below it is plumbing.
Nobody knows what a single stock does next quarter. Anybody who tells you they do is selling you something, and the price of that something is usually your capital.
But the shape of the odds is knowable. Which names have historically sat in the better half of the spread. How wide the spread gets. How heavy the left tail becomes when leverage, accruals and distress signals stack up. That is a measurable thing, and it is measurable in advance.
This is why there is no ticker of the day on this website, and no number at the top of it pretending to be a promise.
Illustrative geometry, not a backtest. The models shift where the centre sits; the caps decide how much of the left tail can reach your account.
Growth of $1. Deciles of the composite score — 179 months, Feb 2011 to Dec 2025, rebalanced monthly, entered the day after scoring; the dashed line marks the starting $1.
Nothing skips a stage, and every stage leaves an audit trail you can open.
Nine academic factor models score the large-cap universe on each name's own earnings clock. The composite weights them by walk-forward-validated predictive power — a model that only worked in the rear-view mirror gets a smaller vote.
Macro is anchored to FRED prints and prediction-market odds rather than vibes, and every sector stance gets a second pass that strikes stale evidence and unsourced claims.
Four frontier models argue a candidate book over three rounds — their job is to break the case, not to make it. Quorum is required, and a gate rejects any ticker that doesn't resolve.
Drift, drawdown, concentration and thesis-break alerts run against your book. You approve or reject every rebalance. Nothing trades on its own.
| Name | Factor profile | Composite | Decile |
|---|---|---|---|
| NAME 01 | 88.4 | D1 | |
| NAME 02 | 84.1 | D1 | |
| NAME 03 | 79.6 | D2 | |
| NAME 04 | 61.2 | D4 | |
| NAME 05 | 22.7 | D9 |
Illustrative layout, anonymised names — not live scores. Six of the nine model families shown.
The free tier is the daily briefing and one tracked portfolio, and it stays free. If the research is worth paying for you'll know inside a week — and if it isn't, we'd rather you found that out before you paid us.
Or get the briefing by email
One email before the open. Unsubscribe from any of them.