diff --git a/exploration/expl_esm.py b/exploration/expl_esm.py
index 5f469f4..6e332c2 100644
--- a/exploration/expl_esm.py
+++ b/exploration/expl_esm.py
@@ -34,9 +34,7 @@ from features.esm import *
 # Only take data from the main part of the study. The pilot data have different structure, there were especially many additions to ESM_JSON.
 
 # %%
-participants_inactive_usernames = participants.query_db.get_usernames(
-    collection_start=datetime.date.fromisoformat("2020-08-01")
-)
+participants_inactive_usernames = participants.query_db.get_usernames(collection_start=datetime.date.fromisoformat("2020-08-01"))
 df_esm_inactive = get_esm_data(participants_inactive_usernames)
 
 # %%
@@ -51,7 +49,7 @@ df_esm_preprocessed.columns
 
 # %% [markdown]
 # The purpose of concordance is to count the number of EMA sessions that a participant answered in a day and possibly compare it to some maximum number of EMAs that could theoretically be presented for that day.
-# Traditionally, concordance (adherence) in EMA study is simply calculated as the ratio of (daily) answered EMAs.
+# Traditionally, concordance (adherence) in EMA study is simply calculated as the ratio of (daily) answered EMAs. 
 # This is possible for studies with simple EMA design, such that they are presented at fixed schedule and expired within a certain limit.
 #
 # Since EMAs were triggered more flexibly in our study, a different approach is needed.
@@ -63,9 +61,12 @@ df_esm_preprocessed.columns
 # One approach would be to count distinct session IDs which are incremented for each group of EMAs. However, since not every question answered counts as a fulfilled EMA, some unique session IDs should be eliminated first.
 
 # %%
-session_counts = df_esm_preprocessed.groupby(["participant_id", "esm_session"])[
-    "esm_session"
-].count()
+session_counts = df_esm_preprocessed.groupby(["participant_id","esm_session"]).count()["id"]
+
+# %% [markdown]
+# Group data by participant_id and esm_session and count the number of instances (by id). Session counts are therefore counts of how many times a specific session ID appears *within* a specific participant.
+#
+# In the plot below, it is impossible to distinguish whether a specific count appears many times within the same or across different participants.
 
 # %%
 sns.displot(session_counts.to_numpy(), binwidth=1, height=8)
@@ -74,11 +75,9 @@ sns.displot(session_counts.to_numpy(), binwidth=1, height=8)
 # ### Unique session IDs
 
 # %%
-df_session_counts = pd.DataFrame(session_counts)
-df_session_1 = df_session_counts[(df_session_counts["esm_session"] == 1)]
-df_esm_unique_session = df_session_1.join(
-    df_esm_preprocessed.set_index(["participant_id", "esm_session"])
-)
+df_session_counts = pd.DataFrame(session_counts).rename(columns={"id": "esm_session_count"})
+df_session_1 = df_session_counts[(df_session_counts["esm_session_count"] == 1)]
+df_esm_unique_session = df_session_1.join(df_esm_preprocessed.set_index(["participant_id","esm_session"]))
 
 # %%
 df_esm_unique_session["esm_user_answer"].value_counts()
@@ -88,14 +87,10 @@ df_esm_unique_session["esm_user_answer"].value_counts()
 # What do the answers "Ne" represent?
 
 # %%
-df_esm_unique_session.query("esm_user_answer == 'Ne'")[
-    ["esm_trigger", "esm_instructions", "esm_user_answer"]
-].head()
+df_esm_unique_session.query("esm_user_answer == 'Ne'")[[ "esm_trigger", "esm_instructions", "esm_user_answer"]].head()
 
 # %%
-df_esm_unique_session.loc[
-    df_esm_unique_session["esm_user_answer"].str.contains("Ne"), "esm_trigger"
-].value_counts()
+df_esm_unique_session.loc[df_esm_unique_session["esm_user_answer"].str.contains("Ne"), "esm_trigger"].value_counts()
 
 # %% [markdown]
 # These are all "first" questions of EMAs which serve as a way to postpone the daytime or evening EMAs.
@@ -110,30 +105,36 @@ df_esm_unique_session.loc[
 # There are some session IDs that only appear twice or three times.
 
 # %%
-df_session_counts[
-    (df_session_counts["esm_session"] < 4) & (df_session_counts["esm_session"] > 1)
-]
+df_session_counts[(df_session_counts["esm_session_count"] < 4) & (df_session_counts["esm_session_count"] > 1)]
 
 # %% [markdown]
 # Some represent the morning EMAs that only contained three questions.
 
 # %%
-df_esm_preprocessed.query("participant_id == 89 & esm_session == 158")[
-    ["esm_trigger", "esm_instructions", "esm_user_answer"]
-]
+df_esm_preprocessed.query("participant_id == 89 & esm_session == 158")[[ "esm_trigger", "esm_instructions", "esm_user_answer"]]
 
 # %%
-df_esm_preprocessed.query("participant_id == 89 & esm_session == 157")[
-    ["esm_trigger", "esm_instructions", "esm_user_answer"]
-]
+df_esm_preprocessed.query("participant_id == 89 & esm_session == 157")[[ "esm_trigger", "esm_instructions", "esm_user_answer"]]
 
 # %% [markdown]
 # Others represent interrupted EMA sessions.
 
 # %%
-df_esm_preprocessed.query("participant_id == 31 & esm_session == 77")[
-    ["esm_trigger", "esm_instructions", "esm_user_answer"]
-]
+df_esm_preprocessed.query("participant_id == 31 & esm_session == 77")[[ "esm_trigger", "esm_instructions", "esm_user_answer"]]
+
+# %% [markdown]
+# ### Long sessions
+
+# %%
+df_session_counts[(df_session_counts["esm_session_count"] > 40)]
+
+# %%
+df_esm_preprocessed.query("participant_id == 83").sort_values("_id")[[ "esm_trigger","datetime_lj", "_id", "username"]]
+
+# %% [markdown]
+# Both, session ID and \_ID (and others) reset on application reinstall. Here, it can be seen that the application was reinstalled on 2 April (actually, the phone was replaced as reported by the participant).
+#
+# Session IDs should therefore be grouped while taking the timestamp into account (e.g. by sorting first).
 
 # %% [markdown]
 # ## Other possibilities