The hypothesis does not hold in any of the six scenarios. The figures are read off dommer.json,
tidslinje.json, eierformer.json and terskler.json on step 1 (frozen numbers, 10 000 draws) while the
run still makes folsomheter.json; no sentence rests on the sensitivity list. The wording is a proposal
for the operator.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>