diff --git a/popcorn.py b/popcorn.py
index 5d945ec..d095f4d 100644
--- a/popcorn.py
+++ b/popcorn.py
@@ -16,7 +16,12 @@ with app.setup:
 
 @app.cell(hide_code=True)
 def _():
-    mo.md(r"""# Void Linux 'Popcorn' package repository stat analysis""")
+    mo.md(r"""# Void Linux 'Popcorn' package repository stat analysis
+
+    This notebook analyses the daily package repository statistics files,
+    colloquially known as 'popcorn' files, that are generated by the Void Linux
+    package manager `xbps` and uploaded by users who have opted in to share.
+    """)
     return
 
 
@@ -102,6 +107,10 @@ def _():
     between 2019 and the start of 2021, the amount of different stuff
     downloaded grew rapidly, with the pace picking up again starting 2023.
 
+    There are a few outliers with a size of 0 kB, which we will remove from the
+    data. There are also a few days where the modification date of the file
+    does not correspond to the represented statistical date.
+
     """
     )
     return
@@ -127,6 +136,23 @@ def _():
     return
 
 
+@app.cell(hide_code=True)
+def _():
+    mo.md(
+        r"""
+    ## Download statistics
+
+    Now that we have an idea of how the overall interest in the distribution
+    has changed over time, let's look at the actual download statistics.
+
+    The popcorn files contain two main pieces of information: the number of
+    unique installs (i.e. unique machines downloading packages) and the number
+    of downloads per package. We will look at both of these in turn.
+    """
+    )
+    return
+
+
 @app.cell
 def _(df_pkg_lazy: pl.LazyFrame):
     def _():
@@ -299,6 +325,12 @@ def _(sizes_df):
     return
 
 
+@app.cell
+def _(df_lazy):
+    kernel_df = df_lazy.select("date", pl.col("Kernels").struct.unnest())
+    kernel_df
+
+
 # further ideas:
 #
 # - daily download habits: