fix(overton): correct 3 critical data errors and 3 high-severity caveats

CRIT-1: Stylistic extremity direction reversed — both dimensions declined
  (stijl 1.875→1.744, not increased +0.097). Holistic moderation, not divergence.
CRIT-2: Masking rate corrected from 36.1% to 9.7% (S≤2, M≥4 on full dataset).
  Original 36.8% was from 117-motion manual audit, not extrapolatable.
CRIT-3: Material impact values harmonized to motion-level means (2.79→2.45).
  Old values (2.78→2.43) used undisclosed mean-of-yearly-means aggregation.
HIGH-1: Migration domain provenance caveat — category column is NULL,
  analysis relies on title keyword matching (approximate boundaries).
HIGH-2: 2026-Q2 bounce caveat — n=44, bimodal distribution, sensitive to
  composition (many consensus defense motions among CS=1.0 items).
HIGH-3: Non-right-wing control group corrected — CS rose 58%→62% (+3.5pp),
  not 'flat at 49%'. Surge was disproportionate for right-wing content.

Also: fixed 6-party centrist definition (line 30) to 4-party,
removed 'did not shift rightward' phrasing, added Phase 4 synthesis
reminder to build_all_reports.py.

reports/overton_window/overton_report.html

@@ -141,7 +141,7 @@
 
   <!-- 4. Gravity-Controlled Analysis -->
   <h2>Gravity-Controlled Analysis</h2>
-  <p>Centrist support (all-party definition) by gravity level, before and after July 2024. As expected, higher gravity levels show lower centrist support. The post-2024 window shows increased centrist support at levels M3 and above, consistent with a rightward shift in the Overton window.</p>
+  <p>Centrist support (all-party definition) by gravity level, before and after July 2024. As expected, higher gravity levels show lower centrist support. The post-2024 window shows increased centrist support at levels M3 and above, consistent with a widening of the Overton window.</p>
 
   <div class="chart-block">
     <div class="bar-legend">