fix: separate raised citation markers with a space, not a comma

The comma sits at the baseline, so between two raised digits it drops away from
them and reads as a stray mark on the line. A space separates them without
introducing a character that lives at the wrong height.

[1][2] and [1, 2] both still arrive as two raised digits, still in the order the
model wrote them, and a run containing a number we were never shown is still
left exactly as written.

docs/superpowers/specs/2026-10-07-source-citations-design.md

@@ -163,9 +163,10 @@ The pass follows the rules the rest of the pipeline already follows.
   machinery the maths pass uses. A `[1]` inside a snippet is text.
 - **`[n]`, `[^n]`, comma lists, and runs.** `[1, 3]` is two sources inside one
   marker, and `[1][2]` is two markers written touching. Both are drawn as raised
-  digits separated by a comma, because `¹²` reads as a single number and leaves the
+  digits separated by a space, because `¹²` reads as a single number and leaves the
   reader no way to tell where one citation ends, which is a defect the first version
-  of this shipped with.
+  of this shipped with. A space rather than a comma, because a comma sits at the
+  baseline and so drops away from digits that are raised above it.
 - **All or nothing.** A marker is linked only when every index it names is a
   known source. `[1, 9]` where 9 was never seen stays exactly as written, rather
   than becoming half a link.