Chart 2 — R3 baseline vs recent distribution

The how. Where Chart 1 shows when the R3 line rose, this chart shows how the R3 score distribution shape shifted. Mass moved right, into the active-alpha / high-fee lane.

What you are looking at

• X-axis: allocation-recommendation score (0 to 100)
• Y-axis: density of recommendations at that score for R3
• Blue distribution: baseline window (first 30 days), what R3 scoring normally looks like
• Orange distribution: recent window (last 30 days), what R3 scoring looked like at Snapshot time
• Vertical line at score 67: threshold for routing to the active-alpha / high-fee lane

What the shape shift means

The orange distribution's mass has moved right compared to the blue distribution. Three things are happening at once:

1. The peak (mode) rises. The most common R3 score used to be well below the active-alpha threshold; now it is at or above it.
2. The right tail grows. More R3 recommendations score above the active-alpha threshold.
3. The left tail shrinks. Fewer R3 recommendations score in the passive-index range.

What KL-divergence quantifies

Kullback-Leibler divergence measures how different one distribution is from another. Values:

• KL < 0.05: the same distribution (random noise)
• KL 0.05-0.2: mild shift, monitor
• KL 0.2-1.0: significant shape shift, flag as event
• KL > 1.0: substantial shape shift, high-severity event
• KL > 2.0: distributions are almost non-overlapping — the client population the AI is scoring is behaviorally different from the client population it was trained on

The sample's R3 KL-divergence hit 2.457 on Day 44, 3.926 on Day 51, and stayed above 2.0 through Day 86. That is far above threshold, and it stayed there.

The client-fit + regulatory read

The next chart

The baseline-vs-recent chart shows how the R3 distribution shifted. The lane-rate chart shows the operational consequence: which lane are R3 clients getting routed to now vs baseline.

Chart 3 — lane rate per client group →