The Brier ledger is Aequara's public accountability design. Every published prediction will register as a Brier prediction with a stated horizon. At horizon resolution, the prediction is scored, the error is published, and the running cohort calibration is updated. We earn trust by making mistakes legible. The alternative is the rating-agency model that pretends predictions are descriptions.
Every published prediction will register with a stated probability and a stated horizon. At resolution, the squared error between forecast and outcome is published alongside the verdict. The worked example below shows the format. No live ledger has been published yet — the ledger opens with the first publication cycle.
The Brier score (Glenn Brier, 1950) is the mean squared error between forecast probability and realized outcome. 0.0 is perfect; 0.25 is what you'd score by always predicting 50/50. But the score alone is incomplete. The discipline is in the calibration: are confident predictions actually right at the rate the forecaster claimed?
A calibrated forecaster's 0.80-confidence predictions resolve true about 80% of the time — and their low-confidence predictions miss frequently. That's correct behavior: when a forecaster is uncertain, they say so, and uncertain predictions miss often. A calibrated forecaster's miss rate matches their stated confidence; an overconfident one's doesn't. That is how the ledger is designed to be read.
Every cohort. Every cycle. Open math. If our 0.85-confidence predictions don't resolve true at ≥85% rate, our calibration claim is wrong — and the ledger is designed so you can verify that without taking our word for it.
Each prediction will be signed by a named steward, with per-steward Brier histograms planned for Trustee Tier. Stewards who calibrate poorly over multiple cycles rotate out of decision authority.
Once predictions publish, use them as priors for your own analysis — or as a calibration baseline against your own forecasting discipline. The methodology is documented today.
The ledger is designed to hold every published prediction Aequara makes — by index, by steward, by horizon, by confidence band — with cohort statistics computed at each publication cycle. Public read, Trustee write. The queryable interface ships with MENSURA, which is in development.
Send a note with your organization and what you want to know about the ledger. The founder reads the inbox; you’ll get a scoping answer, not a sales sequence.
Talk to a steward →Mail client not opening? Email hello@aequara.ai with subject “Brier Ledger inquiry”.