diff --git a/Figure_1.png b/Figure_1.png
new file mode 100644
index 0000000..c4f2755
Binary files /dev/null and b/Figure_1.png differ
diff --git a/pos_recovery.py b/pos_recovery.py
index 0b3399a..182e300 100644
--- a/pos_recovery.py
+++ b/pos_recovery.py
@@ -7,6 +7,7 @@
 def compute_pos(dist, dim=2):
     """
     This function computes the positions of points in space from their distance matrix.
+    https://math.stackexchange.com/questions/156161/finding-the-coordinates-of-points-from-distance-matrix
     :param dist: is a square distance matrix
     :param dim: dimention of the coord system
     :return: returns points coordinates
diff --git a/readme.md b/readme.md
index bdfe0f2..b21694c 100644
--- a/readme.md
+++ b/readme.md
@@ -1,3 +1,4 @@
+![Alt text](Figure_1.png?raw=true "")
 ## What?
 This project is a playground for trying out ideas about sorting signals.
 ## Why?
diff --git a/unscramler.py b/unscramler.py
index da70c9a..de8bdcf 100644
--- a/unscramler.py
+++ b/unscramler.py
@@ -38,10 +38,20 @@ def calc_dist(data):
 def compute_pos(dist, dim=2):
     """
     This function computes the positions of points in space from their distance matrix.
+    https://math.stackexchange.com/questions/156161/finding-the-coordinates-of-points-from-distance-matrix
+    http://www.galileoco.com/literature/OCRyoungHouseholder38.pdf
     :param dist: is a square distance matrix
     :param dim: dimention of the coord system
     :return: returns points coordinates
     """
+    # ToDo: read on eigenvalue constraints and threasholding
+    # http: // www.galileoco.com / literature / OCRyoungHouseholder38.pdf
+    # https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4303596/
+    # https://dl.acm.org/citation.cfm?id=2398462
+    # https://www.stat.berkeley.edu/~bickel/BL2008Aos-thresholding.pdf
+    # use tSNE to project higher dimensions down to 2. http://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html
+
+
     d1j2 = np.expand_dims(np.square(dist[0, :]), 0)
     di12 = np.expand_dims(np.square(dist[:, 0]), 1)
     dij2 = np.square(dist)