From beed391ca46bb5e5227cc848f2e7db1ae8973843 Mon Sep 17 00:00:00 2001
From: Frank Haverland <fspapaping@googlemail.com>
Date: Tue, 14 Mar 2023 21:29:10 +0100
Subject: [PATCH] add explanation on extendedResolution and neg.Rates #1714

---
 docs/Correction Algorithm.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/Correction Algorithm.md b/docs/Correction Algorithm.md
index ceb36b9..b1599a8 100644
--- a/docs/Correction Algorithm.md	
+++ b/docs/Correction Algorithm.md	
@@ -72,6 +72,8 @@ If the value is set to true, the result of the last digit is used completely.
 
 When using dig-class11 models, the setting is ignored.
 
+Due to inaccuracies of the neural networks, it sometimes happens that the results jump back and forth between two decimal places. Therefore, when using `ÀllowNegatives``= false, no error is output if the value is only off by 0.2. Nevertheless, the value then remains at the higher determined value.
+
 ###### ``IgnoreLeadingNaN``
 
 The parameter is only be used, if a dig-class11 model is selected. ``ÌgnoreLeadingNaN`` removes in the CheckDigitIncreaseConsistency process the leading `N` values.