diff --git a/docs/formats/core-data-regions.md b/docs/formats/core-data-regions.md
index 5d1d65d..ceca9c1 100644
--- a/docs/formats/core-data-regions.md
+++ b/docs/formats/core-data-regions.md
@@ -983,3 +983,51 @@ array is a per-type field, not a common one at a fixed offset.
 
 The moby reference itself is unaffected: 38.6x excess measured across all
 records stands, since it does not depend on which slots were counted.
+
+## Shrub body records on level 0: six varying bytes, two constant
+
+**Range measured:** level 0, shrub class table 7 entries at core index offset
+10176. Six classes are bounded by a successor; the seventh runs to the end of
+`core_data` and is excluded, because its span contains the whole post-shrub
+region and is not wholly records.
+
+**Method:** bound each span by the next class's geometry offset, take the body
+from `data_offset` to the span end, and split into 8-byte records.
+
+**Result: 164 records across 6 bounded bodies**, body lengths 192 (twice), 208
+(twice), 224, 240.
+
+Per-byte, over those 164 records:
+
+| byte | distinct | zero |
+|---|---|---|
+| 0 | 74 | 60 |
+| 1 | 58 | 65 |
+| 2 | 76 | 43 |
+| 3 | 62 | 48 |
+| 4 | 72 | 35 |
+| 5 | 59 | 38 |
+| **6** | **1** | **164** |
+| **7** | **1** | **164** |
+
+Bytes 6 and 7 are zero in every record. Bytes 0 to 5 take 58 to 76 distinct
+values of a possible 164, with only 21-39% zero -- that is, uniformly varied
+rather than sparse.
+
+Read as `u32` the fields are not plausible: `u32[0]` ranges 0 to 4,294,871,316
+and no field is monotone across the body. So the six bytes are not two packed
+32-bit values.
+
+**What this settles.** The six-varying-plus-two-constant shape holds on level 0
+as a per-level partition rather than only in aggregate across the disc's
+8,938 records, which is what rule 3a asks for. Two trailing zero bytes are
+padding or a flag pair, not data.
+
+**What it does not.** Whether the six bytes are six `u8` fields, or an `f32`
+plus two `u16`, or something else, is unresolved -- the `u32` reading is
+excluded but no positive reading is established.
+
+**Process note.** The first attempt at this used `ClassEntry` and a
+hand-computed `o_class` offset instead of `ShrubClassEntry`, and every
+`ShrubHeader::region` call failed. The parser was not wrong; the caller was.
+The working call shape was already in the disc test.