analysis: enforce complete 81-cell crossover

1 files changed, 8 insertions, 0 deletions

diff --git a/CROSS_ARCHITECTURE_CROSSOVER.md b/CROSS_ARCHITECTURE_CROSSOVER.md
index eb3dfbe..cc27097 100644
--- a/CROSS_ARCHITECTURE_CROSSOVER.md
+++ b/CROSS_ARCHITECTURE_CROSSOVER.md
@@ -162,6 +162,14 @@ runtime plus a predeclared multiplier; a timeout is plotted at its achieved
 metric and charged elapsed cost.  Nonfinite cells are plotted at chance (or
 their last finite language loss) with a failure marker, not omitted.
 
+The global X1 joiner (`experiments/analyze_crossover_81.py`) opens only after
+the complete audited plain-CNN P2, ResNet R2, and Transformer T2 artifacts
+exist.  It rejects any missing, duplicate, or unregistered cell and checks
+that every architecture-size point contains all nine methods.  Failed,
+nonfinite, and timed-out records remain members of the 81-cell panel; they
+reduce the finite-cell count instead of silently reducing the denominator.
+Every joined input is content-hashed.
+
 ### X2: complete confirmation matrix
 
 X2 uses untouched seeds and the X1-selected settings without a new grid.  The