Deep dive — chart 1

Chart 1 — rolling mean admissions-recommendation score by applicant group

The chart your General Counsel and Chief Diversity Officer should look at first. Where the silent A3 divergence begins, in one visual.

7-day rolling mean admissions-recommendation score per applicant group over 90 days

7-day rolling mean admissions-recommendation score per applicant group over the 90-day audit period. A3 divergence begins Day 44 and does not recover.

What you are looking at

X-axis: Day 1 through Day 90 of the audit period
Y-axis: 7-day rolling mean of the AI's admissions-recommendation score (0-100 scale)
Each line: one applicant group (A1 = full-pay well-resourced, A2 = mid-income mixed-resource, A3 = first-generation under-resourced, A4 = international, A5 = transfer + non-traditional)
Baseline window: the first 30 days establishes what "normal" looks like per applicant group

What the eye sees

Four applicant groups stay roughly parallel across the 90 days. One applicant group — A3 — rises (higher scores mean higher probability of deny-or-waitlist). The rise begins around Day 44, and it does not recover. The line separates from the pack.

This is the pattern an admissions-committee chair instinctively recognizes: something in the A3 stream changed, and the AI is scoring it as less admissible than baseline. The 45 percentage-point deny-lane follow-on is the operational consequence.

What the sensor fires on

The sensor is not looking at the eye's pattern. It is running four quantitative thresholds against each 7-day window per applicant group:

Mean-shift: is the 7-day mean > 1.5 standard deviations from baseline mean?
Variance-ratio: is the 7-day variance > 1.5x baseline variance?
KL-divergence: is the shape divergence between baseline and current distribution > 0.2?
Group-differential: is the max cross-group shift > 12%?

Day 44 fires A3 KL-divergence 0.5498 (well above the 0.2 threshold). By Day 51 A5 also hits KL 1.22. The pattern the eye sees is the pattern the sensor quantifies.

What OCR + accreditors care about

OCR investigators and accreditor site-visit teams do not read charts — they read attestations. But when an attestation is challenged, the chart is the exhibit. HHS OCR peers, ED OCR investigators, state AG investigators, accreditor review committees, and plaintiff's expert witnesses all understand the "one applicant group drifts silently" pattern instantly.

The chart also tells the counterfactual story: had this monitoring been in place operationally, the drift window would have been 7-14 days rather than 45+.

The next chart

The rolling-mean chart shows when. The baseline-vs-drifted chart shows how the A3 score distribution shape shifted.

Chart 2 — baseline vs recent distribution →

$499 Snapshot. 3 business days.

Same 3-chart set for your institution's actual AI surface + full analysis report.

Buy $499

Back to education sample hub.