diff --git a/docs/faces.md b/docs/faces.md
index 0a99b95..11a6ec0 100644
--- a/docs/faces.md
+++ b/docs/faces.md
@@ -556,6 +556,26 @@ as 34 — a 3.3× enlargement — against a mean of 178. An upsampled crop does
 produces a confident 512-d embedding describing detail that was interpolated rather than
 photographed, and the damage appears three stages later as clusters that will not separate.
 
+### Measured again, against the implementation
+
+The figures above are read out of a catalog after the fact, so they describe what the old code did
+rather than what the new code does. `examples/face_native.rs` renders one file and indexes it both
+ways, so the difference can be attributed to the resolution and nothing else. Fourteen originals
+from the reference library — 5472×3648 Canon CR2 and DNG — each rendered once and indexed twice:
+
+| Path | Faces found | Mean `crop_px` |
+|---|---|---|
+| Native (this specification) | 9 | **287** |
+| Everything from a 1024 proxy | 5 | **75** |
+
+Crops 3.8× larger, and on the right side of the line that matters: 75 px is *below* [`ALIGNED_EDGE`]
+so the proxy path was upsampling into the embedder on average, where the native path downsamples
+into it.
+
+**Sample of fourteen images and nine faces.** Enough to show the direction and to catch a wrong
+landmark scaling, which is what it was written for; not enough to quote a ratio as the library-wide
+figure. §12's M4 is still where the recall curve gets established.
+
 A second effect, recorded here because it was measured and because the mechanism is **not**
 established. Grouping the same runs by `face_index.source_edge` — the buffer detection ran
 against — gives 0.078 faces per image at 1024 or below, against 1.82 at 2048 or better. Controlled
@@ -567,6 +587,13 @@ itself a downscale of a larger preview, so the detector sees a twice-resampled i
 larger buffer is resampled once — but that is a hypothesis, not a finding, and §12's M4 is where it
 should be settled. **The crop measurement above stands on its own and does not depend on it.**
 
+The A/B is evidence for that hypothesis without settling it. Native found nine faces where the
+1024 path found five, on four files where the proxy path found none at all — so detector input
+*does* affect recall, which the letterbox says it should not. The two paths differ in their
+resampling as well as their size (one box filter and one letterbox against a downscale and a
+letterbox), and this experiment does not separate those. Isolating it means holding the chain fixed
+and varying only the buffer, which is M4's job.
+
 ---
 
 ## 8. Calibration — cosine to probability
diff --git a/ui/dr-ui/src/faces.rs b/ui/dr-ui/src/faces.rs
index 79f66be..5182445 100644
--- a/ui/dr-ui/src/faces.rs
+++ b/ui/dr-ui/src/faces.rs
@@ -1395,7 +1395,7 @@ mod tests {
     }
 
     #[test]
-    fn an_audit_summary_names_both_kinds_of_outstanding() {
+    fn an_audit_summary_counts_the_outstanding_as_one_number() {
         let a = IndexAudit {
             coverage: faces::Coverage {
                 images: 100,
@@ -1410,11 +1410,13 @@ mod tests {
         assert!(s.contains("60/100"), "{s}");
         assert!(s.contains("60%"), "{s}");
         assert!(!s.contains("60.0%"), "whole numbers above ten percent: {s}");
-        assert!(s.contains("30 ready"), "{s}");
-        // "to fetch", not "awaiting a proxy": the whole-library pass fetches
-        // these rather than being blocked by them, and the line must not send
-        // the user off to run the thumbnail sweep first.
-        assert!(s.contains("10 to fetch"), "{s}");
+        // One number, not two. The split described a pass that could index
+        // whatever already had a proxy; detection now refuses that proxy's
+        // size (§7), so both halves cost the same fetch and "30 ready, 10 to
+        // fetch" would imply a distinction that decides nothing.
+        assert!(s.contains("40 to index"), "{s}");
+        assert!(!s.contains("ready"), "the split should be gone: {s}");
+        assert!(!s.contains("to fetch"), "the split should be gone: {s}");
     }
 
     #[test]