diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx-small.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx-small.aql
new file mode 100644
index 0000000..f7dcf0e
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx-small.aql
@@ -0,0 +1,20 @@
+use dataverse fuzzy1;
+
+declare type CSXType as open {
+  id: int32, 
+  csxid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1, nc2;
+
+declare dataset CSXSmall(CSXType) 
+  partitioned by key id on group1;
+
+load dataset CSXSmall 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/fuzzyjoin/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;
+
+
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx.aql
new file mode 100644
index 0000000..b5787a1
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-csx.aql
@@ -0,0 +1,20 @@
+use dataverse fuzzy1;
+
+declare type CSXType as open {
+  id: int32, 
+  csxid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1, nc2;
+
+declare dataset CSX(CSXType) 
+  partitioned by key id on group1;
+
+load dataset CSX 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/fuzzyjoin/pub/csx-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;
+
+
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-dblp.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-dblp.aql
new file mode 100644
index 0000000..3ca85bb
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/10-load-dblp.aql
@@ -0,0 +1,20 @@
+use dataverse fuzzy1;
+
+declare type DBLPType as open {
+  id: int32, 
+  dblpid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1; 
+
+declare dataset DBLP(DBLPType) 
+  partitioned by key id on group1;
+
+load dataset DBLP 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/fuzzyjoin/dblp/dblp-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;
+
+
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/20-drop-dblp.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/20-drop-dblp.aql
new file mode 100644
index 0000000..868d534
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/20-drop-dblp.aql
@@ -0,0 +1,17 @@
+use dataverse fuzzy1;
+
+declare type DBLPType as open {
+  id: int32, 
+  dblpid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1, nc2;
+
+declare dataset DBLP(DBLPType) 
+  partitioned by key id on group1;
+
+drop dataset DBLP;
+
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/30-filter-dblp.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/30-filter-dblp.aql
new file mode 100644
index 0000000..45bd1c8
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/30-filter-dblp.aql
@@ -0,0 +1,20 @@
+use dataverse fuzzy1;
+
+declare type DBLPType as open {
+  id: int32, 
+  dblpid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1, nc2;
+
+declare dataset DBLP(DBLPType) 
+  partitioned by key id on group1;
+
+write output to nc1:"/tmp/amerix.adm";
+
+for $dblp in dataset('DBLP')
+where $dblp.id = 1
+return $dblp
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/40-self-join-dblp.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/40-self-join-dblp.aql
new file mode 100644
index 0000000..bc024c3
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/40-self-join-dblp.aql
@@ -0,0 +1,86 @@
+use dataverse fuzzy1;
+
+declare type DBLPType as open {
+  id: int32, 
+  dblpid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1; 
+
+declare dataset DBLP(DBLPType) 
+  partitioned by key id on group1;
+
+write output to nc1:"/tmp/amerix.adm";
+
+//
+// -- - Stage 3 - --
+//
+for $ridpair in 
+    //
+    // -- - Stage 2 - --
+    //
+    for $paperR in dataset('DBLP')
+    let $tokensR :=
+        for $word in counthashed-word-tokens($paperR.title)
+        for $token at $i in
+            //
+            // -- - Stage 1 - --
+            //
+            for $paper in dataset('DBLP')
+            for $word in counthashed-word-tokens($paper.title)
+            group by $item := $word with $paper
+            order by count($paper)
+            return $item
+        where $word = $token
+        order by $i
+        return $i
+    for $prefix_tokenR in subset-collection(
+                                $tokensR, 
+                                0,
+                                prefix-len(
+                                    len($tokensR), 'Jaccard', .8))
+
+    for $paperS in dataset('DBLP')
+    let $tokensS :=
+        for $word in counthashed-word-tokens($paperS.title)
+        for $token at $i in
+            //
+            // -- - Stage 1 - --
+            //
+            for $paper in dataset('DBLP')
+            for $word in counthashed-word-tokens($paper.title)
+            group by $item := $word with $paper
+            order by count($paper)
+            return $item
+        where $word = $token
+        order by $i
+        return $i
+    for $prefix_tokenS in subset-collection(
+                                $tokensS, 
+                                0,
+                                prefix-len(
+                                    len($tokensS), 'Jaccard', .8))
+
+    where $prefix_tokenR = $prefix_tokenS
+
+    let $sim := similarity(
+                    len(counthashed-word-tokens($paperR.title)),
+                    $tokensR,
+                    len(counthashed-word-tokens($paperS.title)),
+                    $tokensS,
+                    $prefix_tokenR,
+                    'Jaccard',
+                    .8)
+    where $sim >= .8 and $paperR.id < $paperS.id
+    group by $idR := $paperR.id, $idS := $paperS.id with $sim
+    return {'idR': $idR, 'idS': $idS, 'sim': $sim[0]}
+
+for $paperR in dataset('DBLP')
+for $paperS in dataset('DBLP')
+where $ridpair.idR = $paperR.id and $ridpair.idS = $paperS.id
+return {'R': {'dblpid': $paperR.dblpid, 'title': $paperR.title}, 
+        'S': {'dblpid': $paperS.dblpid, 'title': $paperS.title}, 
+        'sim': $ridpair.sim}
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/50-self-join-dblp.aql b/asterix-app/src/test/resources/fuzzyjoin/amerix/50-self-join-dblp.aql
new file mode 100644
index 0000000..eb44be7
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/50-self-join-dblp.aql
@@ -0,0 +1,22 @@
+use dataverse fuzzy1;
+
+declare type DBLPType as open {
+  id: int32, 
+  dblpid: string,
+  title: string,
+  authors: string,
+  misc: string
+}
+
+declare nodegroup group1 on nc1, nc2;
+
+declare dataset DBLP(DBLPType) 
+  partitioned by key id on group1;
+
+write output to nc1:"/tmp/amerix.adm";
+
+for   $paperR in dataset('DBLP')
+for   $paperS in dataset('DBLP')
+where $paperR.title ~= $paperS.title
+return { 'R': $paperR,
+         'S': $paperS }
diff --git a/asterix-app/src/test/resources/fuzzyjoin/amerix/line.py b/asterix-app/src/test/resources/fuzzyjoin/amerix/line.py
new file mode 100644
index 0000000..f845bb2
--- /dev/null
+++ b/asterix-app/src/test/resources/fuzzyjoin/amerix/line.py
@@ -0,0 +1,7 @@
+
+m = 0
+for line in open('/data/fuzzyjoin/pub/csx-id.txt'):
+    l = len(line)
+    if (l > m):
+        m = l
+print m