Fix remaining stale RM strings and update review status

Update two remaining instances of "max pre-period violation" to
"max pre-period first difference" in result summary and class docstring.

Downgrade METHODOLOGY_REVIEW.md status to "Complete (pending R comparison)"
to accurately reflect that R benchmark validation is still outstanding.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: igerber

METHODOLOGY_REVIEW.md

@@ -618,8 +618,8 @@ variables appear to the left of the `|` separator.
 | Module | `honest_did.py` |
 | Primary Reference | Rambachan & Roth (2023) |
 | R Reference | `HonestDiD` package |
-| Status | **Complete** |
-| Last Review | 2026-03-31 |
+| Status | **Complete** (pending R comparison) |
+| Last Review | 2026-04-01 |
 
 **Verified Components:**
 - [x] Delta^SD: second-difference constraints [1,-2,1] with delta_0=0 boundary handling

diff_diff/honest_did.py

@@ -288,7 +288,7 @@ def summary(self) -> str:
 
         if self.method == "relative_magnitude":
             lines.append(
-                f"Post-treatment violations bounded at {self.M:.1f}x max pre-period violation."
+                f"Post-treatment first differences bounded at {self.M:.1f}x max pre-period first difference."
             )
         elif self.method == "smoothness":
             if self.M == 0:
@@ -1976,7 +1976,7 @@ class HonestDiD:
     M : float, optional
         Restriction parameter. Interpretation depends on method:
         - smoothness: Max second difference
-        - relative_magnitude: Scaling factor for max pre-period violation
+        - relative_magnitude: Scaling factor for max pre-period first difference
         Default is 1.0 for relative_magnitude, 0.0 for smoothness.
     alpha : float
         Significance level for confidence intervals.