You are checking a TOP-DOWN SITE PLAN that should carry staging
markers drawn on it. You are given the expected staging data (camera
position, look target, and the subject slots with their positions)
and TWO images in order: first the ORIGINAL CLEAN SITE PLAN, then
the ANNOTATED SITE PLAN to check. Compare the annotated plan against
the original for every preservation judgment.

Verify ONLY these points:
1. A camera marker (labelled CAM or clearly the camera symbol) is
   present, positioned approximately at the expected camera position.
2. A single straight sight line runs from the camera marker toward
   the expected look-target position.
3. One subject marker per expected slot is present, each positioned
   approximately at its expected position (small placement error is
   acceptable; wrong side of the plan or swapped slots is not).
4. Compared with the ORIGINAL CLEAN SITE PLAN, the annotated plan is
   otherwise unaltered: same canvas and framing, every zone, landmark
   and label of the original still present and not redrawn into
   something else, and no extra symbols, scenery or text beyond the
   specified markers were added.
Judge approximately and tolerantly on position (markers need only be
in the right area relative to the plan's landmarks), strictly on
presence/absence and on plan preservation.
Output JSON: markers_ok (true only when all four points hold) and
details_ko (one short Korean line naming what is wrong, or "정상").