Every prediction, graded.

What is being recorded and scored now.

What the document commits to is an answer about a list, and each answer is written to an append-only record when the list is scored: which school the binding Early Decision application should go to, which schools come off a Regular Decision list, and which schools were offered as additions. The inputs and the published figures the answer was computed from are stored with it, and the record refuses edits and deletions.

Each round is scored on its own stated date — the Early Decision answer on Dec 15, Early Decision II on Feb 15, the Regular Decision list check on Apr 1. The first public report is the Early Decision answer in December 2026.

Because the answer is arithmetic on published figures rather than a model output, it is reproducible: the same inputs and the same published figures return the same answer, and the record shows which figures and which cycle it used. A prediction that cannot be reconstructed cannot be graded later.

The same ledger also holds the school placements recorded in August and September by the earlier account product, before this one was the thing on sale. They are not what the page above describes, and they are not excluded either: they were written the same way, so they are graded in December 2026 alongside everything else.

How the grading works.

Admission decisions arrive in the spring. Students log what actually happened — admitted, rejected, waitlisted — for each school on their list, and that outcome is stored against the placement recorded months earlier.

In December 2026 we compare the two and publish the comparison. The unit is the answer: for the school we named as where the binding application should go, what happened there; for the schools we named as ones to take off a list, the same; for the schools we offered as additions, the same again. The misses are the point of the exercise, so the misses get reported at the same resolution as everything else.

We will also publish how many outcomes the report rests on. If the sample is small, that will be stated at the top rather than buried, because a rate computed on a handful of decisions is not yet evidence and saying so is part of the job.

Why industry claims cannot be checked.

Admissions marketing runs on multiples: some number of times better than the published acceptance rate, some percentage of clients placed at a top choice. Read closely, those figures are usually unfalsifiable — not necessarily false, but impossible to check.

• The denominator is chosen after the fact. A rate is only meaningful if you know who was counted, and clients who were screened out, who left, or who did not apply can be excluded without the number ever looking wrong.
• Selection does the work. A service that admits strong applicants will post strong outcomes with no effect of its own. Comparing its clients to the national acceptance rate compares two different populations.
• There is no prediction on the record. Outcome claims are made after decisions are known. Nothing was committed to in advance, so there is nothing that could have turned out to be wrong.

Our claim is built to fail if it is false. The prediction is recorded before the decision exists, the population is every placement rather than a chosen subset, and the report goes out on a fixed date whether or not it flatters us. That does not make it more accurate than anyone else. It makes it checkable, which is a different and smaller thing that we can actually promise.

What this will not become.

A graded record of positions is not an admission prediction, and the report will not turn into one. We will not publish a percentage chance of getting in, before or after December 2026, because published data cannot support it: essays, recommendations, institutional priorities, and everything else that moves real decisions appear in no public dataset.

What gets graded is the narrower claim we actually make — that the figures each school published are reported correctly, that your own score is placed in them correctly, and that the answer that follows from those two things means something when we make it.