Verification registry
Every run, and the gates it survived.
Nothing appears on this page until five checks pass. The stamps on each entry are those checks; the certificate lets you recompute every number from the data.
Model-implied success matches the observed rate within 10 points.
On data the model generated itself, fit statistics read ≈ 1. A broken meter fails here.
No impossible values ship: fit means near 1, no |Z| > 10 unjustified, no perfect correlations.
Every filter named, every row accounted for. Prose and table cannot disagree.
Engine and an independently written reference agree to 1e-6, item by item.
Public-data calibrations
Novel numbers on real public datasetsFinding Percents
ASSISTments 2012–13 · CML Rasch · WLE persons
Ordering Fractions
ASSISTments 2012–13 · CML Rasch · WLE persons
Synthetic recoveries
Known effects, planted and found — the engine’s examTwo kinds of entries, honestly labeled. Synthetic recoveries reproduce published effects from data calibrated to published parameters. Public-data calibrations produce new numbers from real datasets — and carry revision notes whenever a defect was caught, because catching them is the product.