diff --git a/paper/Divilkovskiy2024SourceSpace_en.aux b/paper/Divilkovskiy2024SourceSpace_en.aux
index c8ec3b7..982ef27 100644
--- a/paper/Divilkovskiy2024SourceSpace_en.aux
+++ b/paper/Divilkovskiy2024SourceSpace_en.aux
@@ -23,9 +23,9 @@
 \citation{Biosignals}
 \citation{boyd2017multiperiod}
 \citation{MulticorrelatedQuadratic}
+\citation{jadon2022comprehensive}
 \babel@aux{english}{}
 \@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{1}{section.1}\protected@file@percent }
-\citation{jadon2022comprehensive}
 \@writefile{toc}{\contentsline {section}{\numberline {2}Formulation of the problem of pointwise forecasting of a set of time series}{2}{section.2}\protected@file@percent }
 \@writefile{toc}{\contentsline {section}{\numberline {3}Algorithm in case of predicting a single distance matrix}{2}{section.3}\protected@file@percent }
 \@writefile{toc}{\contentsline {section}{\numberline {4}Existence of several values of a series satisfying same distance matrix}{2}{section.4}\protected@file@percent }
@@ -37,7 +37,7 @@
 \@writefile{lof}{\contentsline {subfigure}{\numberline{(b)}{\ignorespaces {Modified functions where 3 is subtracted from the last values}}}{3}{subfigure.1.2}\protected@file@percent }
 \citation{puchkin2023sharper}
 \@writefile{toc}{\contentsline {section}{\numberline {5}Pairwise correlation between time series as the distance function}{4}{section.5}\protected@file@percent }
-\newlabel{fig:fig5}{{\caption@xref {fig:fig5}{ on input line 250}}{6}{Pairwise correlation between time series as the distance function}{figure.caption.2}{}}
+\newlabel{fig:fig5}{{\caption@xref {fig:fig5}{ on input line 248}}{6}{Pairwise correlation between time series as the distance function}{figure.caption.2}{}}
 \@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Function $||\hat  {\mathbf  {\Sigma }}_{t+1} - \bar  {\mathbf  {\Sigma }}_{t+1}||_2^2$ for following series: $(1, 3)$ and $(2, 4)$. Minumums: (3; 4) is desired and (-1; 0) is alternative.\relax }}{6}{figure.caption.2}\protected@file@percent }
 \citation{mikhalevich2024methodsnonconvexoptimization}
 \@writefile{toc}{\contentsline {section}{\numberline {6}Algorithm for recovering time series values in case of accurate prediction of the matrix}{8}{section.6}\protected@file@percent }
diff --git a/paper/Divilkovskiy2024SourceSpace_en.pdf b/paper/Divilkovskiy2024SourceSpace_en.pdf
index 26fc5f4..31b70cf 100644
Binary files a/paper/Divilkovskiy2024SourceSpace_en.pdf and b/paper/Divilkovskiy2024SourceSpace_en.pdf differ
diff --git a/paper/Divilkovskiy2024SourceSpace_en.synctex.gz b/paper/Divilkovskiy2024SourceSpace_en.synctex.gz
index 6834b21..353391d 100644
Binary files a/paper/Divilkovskiy2024SourceSpace_en.synctex.gz and b/paper/Divilkovskiy2024SourceSpace_en.synctex.gz differ
diff --git a/paper/Divilkovskiy2024SourceSpace_en.tex b/paper/Divilkovskiy2024SourceSpace_en.tex
index 18f4e52..d39313a 100644
--- a/paper/Divilkovskiy2024SourceSpace_en.tex
+++ b/paper/Divilkovskiy2024SourceSpace_en.tex
@@ -90,8 +90,6 @@ \section{Introduction}
 
 	Existing time series prediction methods such as LSTM \cite{LSTM}, SSA \cite{SSA} and other \cite{Biosignals}, \cite{boyd2017multiperiod} are based on predicting the value of a single series. These methods can be modified to forecast also a set of time series. For this purpose, it is sufficient to consider a set of series as one multivariate series. However, this approach does not explicitly model the dependencies between different series. In this paper, we propose to analyze the change in \textit{set} of time series. This approach explicitly uses the relationships between them as information. A similar study is carried out in the \cite{MulticorrelatedQuadratic} paper, but it emphasizes on the feature selection task. This task consists in selecting such a subset of the original time series for which it is possible to make a forecast of sufficient quality.
 	
-	In this paper, forecasting is done not in the original space, but in the space of pairwise distances. The advantage of this method is that in real sets of time series (natural, physical, financial, etc.), there is often a dependence close to linear. This additional information can improve the quality of the final prediction.
-	
 	Further, we consider conditions on the distance function between rows under which there is a way to recover the values of time series. The insufficiency of one matrix to recover the answer is proved. Two methods using several matrices are proposed for the case of accurate forecast and for the case of forecast with non-zero noise. Also, we propose a recovery algorithm based on two theorems about the explicit form of the response using pairwise correlation as a function of pairwise distance between rows. Mean Squared Error and Mean Absolute Error are used as quality criteria. It is shown in the article\cite{jadon2022comprehensive} that they are the most suitable for the task of time series forecasting.
 
 \section{Formulation of the problem of pointwise forecasting of a set of time series}