diff --git a/.gitattributes b/.gitattributes
index 95340fec1d1bb1282c38d08e7f5cc98dbbf1920a..87e6163cfa31144544d62a4770d16e4fb675b6b1 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -150,3 +150,28 @@ data/clustering/model=dmis-lab__biobert-v1.1/min=5/t=0.6_ALL_FIELDS.csv.gz filte
 data/clustering/model=dmis-lab__biobert-v1.1/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 data/clustering/model=dmis-lab__biobert-v1.1/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 data/clustering/model=dmis-lab__biobert-v1.1/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
+data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c6f7701048553693724a94b92361c87eedc9f249
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478aed641169d2c7f2ac296cb954b0d56431c81b430faad79dc8906ea4344ba4
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..815b9c3a1ce44549aec9221ffb1d0940015f930e
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,10,0.5
+elution_buffer,3530,3530,1,,,10,0.5
+enzyme_name,7975,7975,1,,,10,0.5
+expression_strain,5677,5677,1,,,10,0.5
+inducer,7889,7889,1,,,10,0.5
+induction_temperature,3656,3656,1,,,10,0.5
+lysis_buffer,3714,3714,1,,,10,0.5
+medium_name,4806,4806,1,,,10,0.5
+molecular_weight,295,295,1,,,10,0.5
+organism_source,6292,6292,1,,,10,0.5
+plasmid,5480,5480,1,,,10,0.5
+source_key,8021,8021,1,,,10,0.5
+strain,2444,2444,1,,,10,0.5
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4d5c1746dd615cba54765a0045c3801674545ce7
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10f278185d62e10001998ae890f3be0fb15862ca51ab86d3ca15d75347abcf8
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..d692a69c8ff2d0cb6469033d2d4035360637afc5
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,10,0.6
+elution_buffer,3530,3530,1,,,10,0.6
+enzyme_name,7975,7975,1,,,10,0.6
+expression_strain,5677,5677,1,,,10,0.6
+inducer,7889,7889,1,,,10,0.6
+induction_temperature,3656,3656,1,,,10,0.6
+lysis_buffer,3714,3714,1,,,10,0.6
+medium_name,4806,4806,1,,,10,0.6
+molecular_weight,295,295,1,,,10,0.6
+organism_source,6292,6292,1,,,10,0.6
+plasmid,5480,5480,1,,,10,0.6
+source_key,8021,8021,1,,,10,0.6
+strain,2444,2444,1,,,10,0.6
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..dff8cc184f54681154e587ee51deac0c483b2604
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f694e68f7453eea04c53c37c1cffbdaed65e84a2d5bb1946b565dfe17ecb92
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..154e0ef5fc8c13d77afe95d67764a117842be7d5
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,10,0.7
+elution_buffer,3530,3530,1,,,10,0.7
+enzyme_name,7975,7975,1,,,10,0.7
+expression_strain,5677,5677,1,,,10,0.7
+inducer,7889,7889,1,,,10,0.7
+induction_temperature,3656,3656,1,,,10,0.7
+lysis_buffer,3714,3714,1,,,10,0.7
+medium_name,4806,4806,1,,,10,0.7
+molecular_weight,295,295,1,,,10,0.7
+organism_source,6292,6292,1,,,10,0.7
+plasmid,5480,5480,1,,,10,0.7
+source_key,8021,8021,1,,,10,0.7
+strain,2444,2444,1,,,10,0.7
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6e2aa9f1f53f9b21ad46a94936393aa1d92690bf
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9188d1c4cb399bf4dd4115d8e49b0c3b8bdb8487eee5ac9eb75d1e79cd17f11c
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..b81c0bd68b32507f5f8d362694176bf4553d9a8c
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,10,0.8
+elution_buffer,3530,3530,1,,,10,0.8
+enzyme_name,7975,7975,1,,,10,0.8
+expression_strain,5677,5677,1,,,10,0.8
+inducer,7889,7889,1,,,10,0.8
+induction_temperature,3656,3656,1,,,10,0.8
+lysis_buffer,3714,3714,1,,,10,0.8
+medium_name,4806,4806,1,,,10,0.8
+molecular_weight,295,295,1,,,10,0.8
+organism_source,6292,6292,1,,,10,0.8
+plasmid,5480,5480,1,,,10,0.8
+source_key,8021,8021,1,,,10,0.8
+strain,2444,2444,1,,,10,0.8
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3e0edb0ea5db3a80e893fe035f7b31e1b0c845e2
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0809566210f97edea3e2a26580066029e7db724c2b100dbed5c3db4ae85724
+size 1559187
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..6b5fd737369a0fd5a237ed311dff3c7fbb069272
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,10,0.9
+elution_buffer,3530,3530,1,,,10,0.9
+enzyme_name,7975,7975,1,,,10,0.9
+expression_strain,5677,5677,1,,,10,0.9
+inducer,7889,7889,1,,,10,0.9
+induction_temperature,3656,3656,1,,,10,0.9
+lysis_buffer,3714,3710,1,,,10,0.9
+medium_name,4806,4806,1,,,10,0.9
+molecular_weight,295,295,1,,,10,0.9
+organism_source,6292,6292,1,,,10,0.9
+plasmid,5480,5480,1,,,10,0.9
+source_key,8021,8021,1,,,10,0.9
+strain,2444,2443,1,,,10,0.9
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..1d4c5dcd3e82a45f894edf7d852c3da704b5d89e
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edeeef3cfd0089454d91c497e7afd50cfda0c48a2cd9ab5740a12bf81a5a7c71
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..590b820067664f8e12688bcfc3467161c4c08fb4
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,2,0.5
+elution_buffer,3530,3530,1,,,2,0.5
+enzyme_name,7975,7975,1,,,2,0.5
+expression_strain,5677,5677,1,,,2,0.5
+inducer,7889,7889,1,,,2,0.5
+induction_temperature,3656,3656,1,,,2,0.5
+lysis_buffer,3714,3714,1,,,2,0.5
+medium_name,4806,4806,1,,,2,0.5
+molecular_weight,295,295,1,,,2,0.5
+organism_source,6292,6292,1,,,2,0.5
+plasmid,5480,5480,1,,,2,0.5
+source_key,8021,8021,1,,,2,0.5
+strain,2444,2444,1,,,2,0.5
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..93d78d34d8c854897ec14d201e2260ad01482e09
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff664a2120c983d4ffd84d8df33edbf1ae7810b9fb63551603dfe6a51c34500
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..7cad830d9ef04ed12c1be5d0744f8d8c886a0d37
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,2,0.6
+elution_buffer,3530,3530,1,,,2,0.6
+enzyme_name,7975,7975,1,,,2,0.6
+expression_strain,5677,5677,1,,,2,0.6
+inducer,7889,7889,1,,,2,0.6
+induction_temperature,3656,3656,1,,,2,0.6
+lysis_buffer,3714,3714,1,,,2,0.6
+medium_name,4806,4806,1,,,2,0.6
+molecular_weight,295,295,1,,,2,0.6
+organism_source,6292,6292,1,,,2,0.6
+plasmid,5480,5480,1,,,2,0.6
+source_key,8021,8021,1,,,2,0.6
+strain,2444,2444,1,,,2,0.6
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..265df89c9271c0a0911a94fdc8c50802d174a181
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64d4468b39ec7e8a9878219bb0179c9b1a83a439c839d47283e0218b23e54a0
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..3a3a7d9d0f590d73bcd7f3da1df8dd5f85478edf
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,2,0.7
+elution_buffer,3530,3530,1,,,2,0.7
+enzyme_name,7975,7975,1,,,2,0.7
+expression_strain,5677,5677,1,,,2,0.7
+inducer,7889,7889,1,,,2,0.7
+induction_temperature,3656,3656,1,,,2,0.7
+lysis_buffer,3714,3714,1,,,2,0.7
+medium_name,4806,4806,1,,,2,0.7
+molecular_weight,295,295,1,,,2,0.7
+organism_source,6292,6292,1,,,2,0.7
+plasmid,5480,5480,1,,,2,0.7
+source_key,8021,8021,1,,,2,0.7
+strain,2444,2444,1,,,2,0.7
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a40504dbbaa4992b604a409e9fa9c0e63c779468
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0f3ddc8150b539bc53d44f414a1380ca1c730f85eb472eabd19ff1233ebe28
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..2e1da15f5d67a7c393a89a23b5f2b05c6347fbd3
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,2,0.8
+elution_buffer,3530,3530,1,,,2,0.8
+enzyme_name,7975,7975,1,,,2,0.8
+expression_strain,5677,5677,1,,,2,0.8
+inducer,7889,7889,1,,,2,0.8
+induction_temperature,3656,3656,1,,,2,0.8
+lysis_buffer,3714,3714,1,,,2,0.8
+medium_name,4806,4806,1,,,2,0.8
+molecular_weight,295,295,1,,,2,0.8
+organism_source,6292,6292,1,,,2,0.8
+plasmid,5480,5480,1,,,2,0.8
+source_key,8021,8021,1,,,2,0.8
+strain,2444,2444,1,,,2,0.8
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e7d40f2953cc08b04b2b2e553656a432f3a1deda
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063fa9e6effa8eabc55e1bd00958e1921c7340e7821af3e86f0cca62eed46a42
+size 1559236
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..cca27fd7d4ca5e64eaf17bf2fe102a23857e254f
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+lysis_buffer,3714,3714,3,0.782861590385437,0.3267258739364616,2,0.9
+desalting_process,3720,3720,1,,,2,0.9
+elution_buffer,3530,3530,1,,,2,0.9
+enzyme_name,7975,7975,1,,,2,0.9
+expression_strain,5677,5677,1,,,2,0.9
+inducer,7889,7889,1,,,2,0.9
+induction_temperature,3656,3656,1,,,2,0.9
+medium_name,4806,4806,1,,,2,0.9
+molecular_weight,295,295,1,,,2,0.9
+organism_source,6292,6292,1,,,2,0.9
+plasmid,5480,5480,1,,,2,0.9
+source_key,8021,8021,1,,,2,0.9
+strain,2444,2443,1,,,2,0.9
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8eb45759d67aae16bc4e0dea1eac8b9b173d8c84
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93acdd6acf7647cdacb1081be08f52b1340ecfc68872e197489d91660e11623e
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..16390af52db9406cd55c564a2aa72732f691cf1b
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,20,0.5
+elution_buffer,3530,3530,1,,,20,0.5
+enzyme_name,7975,7975,1,,,20,0.5
+expression_strain,5677,5677,1,,,20,0.5
+inducer,7889,7889,1,,,20,0.5
+induction_temperature,3656,3656,1,,,20,0.5
+lysis_buffer,3714,3714,1,,,20,0.5
+medium_name,4806,4806,1,,,20,0.5
+molecular_weight,295,295,1,,,20,0.5
+organism_source,6292,6292,1,,,20,0.5
+plasmid,5480,5480,1,,,20,0.5
+source_key,8021,8021,1,,,20,0.5
+strain,2444,2444,1,,,20,0.5
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6eb37699fafe50c2acdda6e474fea31157c910d4
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5007f3eaddd7f80e1f41554e24f16ac9c25346b2db3a867f1d785ea356af8c
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..8e6f421a7eb2e140261828ae38afea920707cabb
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,20,0.6
+elution_buffer,3530,3530,1,,,20,0.6
+enzyme_name,7975,7975,1,,,20,0.6
+expression_strain,5677,5677,1,,,20,0.6
+inducer,7889,7889,1,,,20,0.6
+induction_temperature,3656,3656,1,,,20,0.6
+lysis_buffer,3714,3714,1,,,20,0.6
+medium_name,4806,4806,1,,,20,0.6
+molecular_weight,295,295,1,,,20,0.6
+organism_source,6292,6292,1,,,20,0.6
+plasmid,5480,5480,1,,,20,0.6
+source_key,8021,8021,1,,,20,0.6
+strain,2444,2444,1,,,20,0.6
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..0544da05918eb4c6467468c09e172b860939c10f
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfca6d7f9a136da713c67caf46318e9f07e3a98c204b22790e595b71007067db
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..3ed40eb67255b9d35ee329cf846068d0e2b84236
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,20,0.7
+elution_buffer,3530,3530,1,,,20,0.7
+enzyme_name,7975,7975,1,,,20,0.7
+expression_strain,5677,5677,1,,,20,0.7
+inducer,7889,7889,1,,,20,0.7
+induction_temperature,3656,3656,1,,,20,0.7
+lysis_buffer,3714,3714,1,,,20,0.7
+medium_name,4806,4806,1,,,20,0.7
+molecular_weight,295,295,1,,,20,0.7
+organism_source,6292,6292,1,,,20,0.7
+plasmid,5480,5480,1,,,20,0.7
+source_key,8021,8021,1,,,20,0.7
+strain,2444,2444,1,,,20,0.7
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e27485e84e1878b0b0c6ebdb910812768bab72c5
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de581ceb82eabd700f5f69b3ac11f0305b59f30b3b3038cbcafcac7897439db5
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..f1b29487a2930e7532082bf1394f78fa710ddcfb
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,20,0.8
+elution_buffer,3530,3530,1,,,20,0.8
+enzyme_name,7975,7975,1,,,20,0.8
+expression_strain,5677,5677,1,,,20,0.8
+inducer,7889,7889,1,,,20,0.8
+induction_temperature,3656,3656,1,,,20,0.8
+lysis_buffer,3714,3714,1,,,20,0.8
+medium_name,4806,4806,1,,,20,0.8
+molecular_weight,295,295,1,,,20,0.8
+organism_source,6292,6292,1,,,20,0.8
+plasmid,5480,5480,1,,,20,0.8
+source_key,8021,8021,1,,,20,0.8
+strain,2444,2444,1,,,20,0.8
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b02efb976d21e8daedf91ade83ce6bc393514a65
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da99b4b5886a80e84129bd667d314c53150f358c9ae9e0c03c3036d379f7dc63
+size 1559187
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..9d4053641d79d5295da455e7c012f1a68d3c0a74
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,20,0.9
+elution_buffer,3530,3530,1,,,20,0.9
+enzyme_name,7975,7975,1,,,20,0.9
+expression_strain,5677,5677,1,,,20,0.9
+inducer,7889,7889,1,,,20,0.9
+induction_temperature,3656,3656,1,,,20,0.9
+lysis_buffer,3714,3710,1,,,20,0.9
+medium_name,4806,4806,1,,,20,0.9
+molecular_weight,295,295,1,,,20,0.9
+organism_source,6292,6292,1,,,20,0.9
+plasmid,5480,5480,1,,,20,0.9
+source_key,8021,8021,1,,,20,0.9
+strain,2444,2443,1,,,20,0.9
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..c56381593826f1d1e36def27eed691690f244cf4
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f786c9cdc6dbe462c1903d618178b3895d4138e0f91edf0d213715dce412f429
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..560e48120e0b1c35ec315d6e722ea4474213ce4b
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,30,0.5
+elution_buffer,3530,3530,1,,,30,0.5
+enzyme_name,7975,7975,1,,,30,0.5
+expression_strain,5677,5677,1,,,30,0.5
+inducer,7889,7889,1,,,30,0.5
+induction_temperature,3656,3656,1,,,30,0.5
+lysis_buffer,3714,3714,1,,,30,0.5
+medium_name,4806,4806,1,,,30,0.5
+molecular_weight,295,295,1,,,30,0.5
+organism_source,6292,6292,1,,,30,0.5
+plasmid,5480,5480,1,,,30,0.5
+source_key,8021,8021,1,,,30,0.5
+strain,2444,2444,1,,,30,0.5
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a11e53cf73eca0b94d68f9e5f5b7a679b5dfece4
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0c61ed88478584af78f836a09793fe68ce6680d4a89460b368c996c162ca6c
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..c1c7ecd93365aac458718d5715bb47b6fbcd0a5e
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,30,0.6
+elution_buffer,3530,3530,1,,,30,0.6
+enzyme_name,7975,7975,1,,,30,0.6
+expression_strain,5677,5677,1,,,30,0.6
+inducer,7889,7889,1,,,30,0.6
+induction_temperature,3656,3656,1,,,30,0.6
+lysis_buffer,3714,3714,1,,,30,0.6
+medium_name,4806,4806,1,,,30,0.6
+molecular_weight,295,295,1,,,30,0.6
+organism_source,6292,6292,1,,,30,0.6
+plasmid,5480,5480,1,,,30,0.6
+source_key,8021,8021,1,,,30,0.6
+strain,2444,2444,1,,,30,0.6
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..02b743d4cfd13d34e311ac13e09b33b6d5f08ab2
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b488381e9f79d1e8ad391abb7f9e27b7991eb8666b3c29bb509fe3536273e9
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..7b958b4a2aa0166053862e24eba1fc08c5435b30
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,30,0.7
+elution_buffer,3530,3530,1,,,30,0.7
+enzyme_name,7975,7975,1,,,30,0.7
+expression_strain,5677,5677,1,,,30,0.7
+inducer,7889,7889,1,,,30,0.7
+induction_temperature,3656,3656,1,,,30,0.7
+lysis_buffer,3714,3714,1,,,30,0.7
+medium_name,4806,4806,1,,,30,0.7
+molecular_weight,295,295,1,,,30,0.7
+organism_source,6292,6292,1,,,30,0.7
+plasmid,5480,5480,1,,,30,0.7
+source_key,8021,8021,1,,,30,0.7
+strain,2444,2444,1,,,30,0.7
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..3354cdaa197501f1c45521117c01294c7f08a24d
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4924992367ad50abe02214ec3fae53742dcb607300a5a657d508a9da5e4a96
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..a00251b3dd30a3dc94da3a55ee153b1058cbf72b
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,30,0.8
+elution_buffer,3530,3530,1,,,30,0.8
+enzyme_name,7975,7975,1,,,30,0.8
+expression_strain,5677,5677,1,,,30,0.8
+inducer,7889,7889,1,,,30,0.8
+induction_temperature,3656,3656,1,,,30,0.8
+lysis_buffer,3714,3714,1,,,30,0.8
+medium_name,4806,4806,1,,,30,0.8
+molecular_weight,295,295,1,,,30,0.8
+organism_source,6292,6292,1,,,30,0.8
+plasmid,5480,5480,1,,,30,0.8
+source_key,8021,8021,1,,,30,0.8
+strain,2444,2444,1,,,30,0.8
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f70c1c788876017b3ddf2fd11b2759ac3a825968
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc7331353ca777d3b1f144bf33182e5ae5c91a525cb6f649bce3fb2b9f7d4d1
+size 1559187
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..d7bd408c3756b716b9994a00519d373fc1b1d373
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,30,0.9
+elution_buffer,3530,3530,1,,,30,0.9
+enzyme_name,7975,7975,1,,,30,0.9
+expression_strain,5677,5677,1,,,30,0.9
+inducer,7889,7889,1,,,30,0.9
+induction_temperature,3656,3656,1,,,30,0.9
+lysis_buffer,3714,3710,1,,,30,0.9
+medium_name,4806,4806,1,,,30,0.9
+molecular_weight,295,295,1,,,30,0.9
+organism_source,6292,6292,1,,,30,0.9
+plasmid,5480,5480,1,,,30,0.9
+source_key,8021,8021,1,,,30,0.9
+strain,2444,2443,1,,,30,0.9
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e8dd81550df4d5dd33d27c294c75fe9aa1987928
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d0ec83d0e5befa1e84a0e7045e776b55601606daa02278e8514a95bd2e3cd4
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..a93b8e60e56a6d7db5edf122d94ba5a7324fdb86
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,5,0.5
+elution_buffer,3530,3530,1,,,5,0.5
+enzyme_name,7975,7975,1,,,5,0.5
+expression_strain,5677,5677,1,,,5,0.5
+inducer,7889,7889,1,,,5,0.5
+induction_temperature,3656,3656,1,,,5,0.5
+lysis_buffer,3714,3714,1,,,5,0.5
+medium_name,4806,4806,1,,,5,0.5
+molecular_weight,295,295,1,,,5,0.5
+organism_source,6292,6292,1,,,5,0.5
+plasmid,5480,5480,1,,,5,0.5
+source_key,8021,8021,1,,,5,0.5
+strain,2444,2444,1,,,5,0.5
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..13d0ca0b92ecb85bc3250b255b11dd083d250c1f
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7899fa664ccca9149070970e0be02f8332b1d0264037e26c2d8eed6f93e5e929
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..a698f94d11f0b8e94d9b0a0679f88b0f40424611
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,5,0.6
+elution_buffer,3530,3530,1,,,5,0.6
+enzyme_name,7975,7975,1,,,5,0.6
+expression_strain,5677,5677,1,,,5,0.6
+inducer,7889,7889,1,,,5,0.6
+induction_temperature,3656,3656,1,,,5,0.6
+lysis_buffer,3714,3714,1,,,5,0.6
+medium_name,4806,4806,1,,,5,0.6
+molecular_weight,295,295,1,,,5,0.6
+organism_source,6292,6292,1,,,5,0.6
+plasmid,5480,5480,1,,,5,0.6
+source_key,8021,8021,1,,,5,0.6
+strain,2444,2444,1,,,5,0.6
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..66ec84458a0a43da4cee6f326dd6c06ec92ff6b7
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2deaf400ed7509f280ac9f7fbfe6814174f80a0d3328309305b17d717acbe7
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..e0258c2fe55d97a067126c9acefd3db90bf5a7cf
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,5,0.7
+elution_buffer,3530,3530,1,,,5,0.7
+enzyme_name,7975,7975,1,,,5,0.7
+expression_strain,5677,5677,1,,,5,0.7
+inducer,7889,7889,1,,,5,0.7
+induction_temperature,3656,3656,1,,,5,0.7
+lysis_buffer,3714,3714,1,,,5,0.7
+medium_name,4806,4806,1,,,5,0.7
+molecular_weight,295,295,1,,,5,0.7
+organism_source,6292,6292,1,,,5,0.7
+plasmid,5480,5480,1,,,5,0.7
+source_key,8021,8021,1,,,5,0.7
+strain,2444,2444,1,,,5,0.7
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6e2aa9f1f53f9b21ad46a94936393aa1d92690bf
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9188d1c4cb399bf4dd4115d8e49b0c3b8bdb8487eee5ac9eb75d1e79cd17f11c
+size 1559184
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..cf68188873a75a70fc29ea5c4e41503cb9717c64
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,5,0.8
+elution_buffer,3530,3530,1,,,5,0.8
+enzyme_name,7975,7975,1,,,5,0.8
+expression_strain,5677,5677,1,,,5,0.8
+inducer,7889,7889,1,,,5,0.8
+induction_temperature,3656,3656,1,,,5,0.8
+lysis_buffer,3714,3714,1,,,5,0.8
+medium_name,4806,4806,1,,,5,0.8
+molecular_weight,295,295,1,,,5,0.8
+organism_source,6292,6292,1,,,5,0.8
+plasmid,5480,5480,1,,,5,0.8
+source_key,8021,8021,1,,,5,0.8
+strain,2444,2444,1,,,5,0.8
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e58269e3f6222ede7848403c7968adfa14af31b9
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76247df7e62975e5497e06664aab5edc769c0b5a42e2f83b22bababe69bcb11d
+size 1559187
diff --git a/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv
new file mode 100644
index 0000000000000000000000000000000000000000..3823d3cbcb00eb5c160c166561cf43d9e6b3f79a
--- /dev/null
+++ b/data/clustering/model=microsoft__BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv
@@ -0,0 +1,14 @@
+field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
+desalting_process,3720,3720,1,,,5,0.9
+elution_buffer,3530,3530,1,,,5,0.9
+enzyme_name,7975,7975,1,,,5,0.9
+expression_strain,5677,5677,1,,,5,0.9
+inducer,7889,7889,1,,,5,0.9
+induction_temperature,3656,3656,1,,,5,0.9
+lysis_buffer,3714,3710,1,,,5,0.9
+medium_name,4806,4806,1,,,5,0.9
+molecular_weight,295,295,1,,,5,0.9
+organism_source,6292,6292,1,,,5,0.9
+plasmid,5480,5480,1,,,5,0.9
+source_key,8021,8021,1,,,5,0.9
+strain,2444,2443,1,,,5,0.9