Upload files
Browse files- .gitattributes +10 -0
- abstract_finder_stats.json +81 -0
- percentile_pairs_W2979586175_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W3164014860_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W3166396011_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W3177445623_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W3177828909_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W3209071234_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W4210649579_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W4292779060_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W4321610982_embeddings_midpoints_nearest_with_abstracts.json +3 -0
- percentile_pairs_W4385899778_embeddings_midpoints_nearest_with_abstracts.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
percentile_pairs_W2979586175_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
percentile_pairs_W3164014860_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
percentile_pairs_W3166396011_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
percentile_pairs_W3177445623_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
percentile_pairs_W3177828909_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
percentile_pairs_W3209071234_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
percentile_pairs_W4210649579_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
percentile_pairs_W4292779060_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
percentile_pairs_W4321610982_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
percentile_pairs_W4385899778_embeddings_midpoints_nearest_with_abstracts.json filter=lfs diff=lfs merge=lfs -text
|
abstract_finder_stats.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pkl_file": "pid2abstract_no_html_method_lemma_before_2025_after_2020.pkl",
|
| 3 |
+
"input_folder": "pairs_wk_nearest",
|
| 4 |
+
"output_folder": "pairs_wk_bridge",
|
| 5 |
+
"total_files": 10,
|
| 6 |
+
"total_processed_pairs": 20000,
|
| 7 |
+
"total_found_abstracts": 20000,
|
| 8 |
+
"total_missing_abstracts": 0,
|
| 9 |
+
"files_processed": {
|
| 10 |
+
"percentile_pairs_W4292779060_embeddings_midpoints_nearest.json": {
|
| 11 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W4292779060_embeddings_midpoints_nearest.json",
|
| 12 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W4292779060_embeddings_midpoints_nearest_with_abstracts.json",
|
| 13 |
+
"processed_pairs": 2000,
|
| 14 |
+
"found_abstracts": 2000,
|
| 15 |
+
"missing_abstracts": 0
|
| 16 |
+
},
|
| 17 |
+
"percentile_pairs_W3164014860_embeddings_midpoints_nearest.json": {
|
| 18 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W3164014860_embeddings_midpoints_nearest.json",
|
| 19 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W3164014860_embeddings_midpoints_nearest_with_abstracts.json",
|
| 20 |
+
"processed_pairs": 2000,
|
| 21 |
+
"found_abstracts": 2000,
|
| 22 |
+
"missing_abstracts": 0
|
| 23 |
+
},
|
| 24 |
+
"percentile_pairs_W4385899778_embeddings_midpoints_nearest.json": {
|
| 25 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W4385899778_embeddings_midpoints_nearest.json",
|
| 26 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W4385899778_embeddings_midpoints_nearest_with_abstracts.json",
|
| 27 |
+
"processed_pairs": 2000,
|
| 28 |
+
"found_abstracts": 2000,
|
| 29 |
+
"missing_abstracts": 0
|
| 30 |
+
},
|
| 31 |
+
"percentile_pairs_W4321610982_embeddings_midpoints_nearest.json": {
|
| 32 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W4321610982_embeddings_midpoints_nearest.json",
|
| 33 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W4321610982_embeddings_midpoints_nearest_with_abstracts.json",
|
| 34 |
+
"processed_pairs": 2000,
|
| 35 |
+
"found_abstracts": 2000,
|
| 36 |
+
"missing_abstracts": 0
|
| 37 |
+
},
|
| 38 |
+
"percentile_pairs_W3209071234_embeddings_midpoints_nearest.json": {
|
| 39 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W3209071234_embeddings_midpoints_nearest.json",
|
| 40 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W3209071234_embeddings_midpoints_nearest_with_abstracts.json",
|
| 41 |
+
"processed_pairs": 2000,
|
| 42 |
+
"found_abstracts": 2000,
|
| 43 |
+
"missing_abstracts": 0
|
| 44 |
+
},
|
| 45 |
+
"percentile_pairs_W3166396011_embeddings_midpoints_nearest.json": {
|
| 46 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W3166396011_embeddings_midpoints_nearest.json",
|
| 47 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W3166396011_embeddings_midpoints_nearest_with_abstracts.json",
|
| 48 |
+
"processed_pairs": 2000,
|
| 49 |
+
"found_abstracts": 2000,
|
| 50 |
+
"missing_abstracts": 0
|
| 51 |
+
},
|
| 52 |
+
"percentile_pairs_W3177828909_embeddings_midpoints_nearest.json": {
|
| 53 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W3177828909_embeddings_midpoints_nearest.json",
|
| 54 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W3177828909_embeddings_midpoints_nearest_with_abstracts.json",
|
| 55 |
+
"processed_pairs": 2000,
|
| 56 |
+
"found_abstracts": 2000,
|
| 57 |
+
"missing_abstracts": 0
|
| 58 |
+
},
|
| 59 |
+
"percentile_pairs_W4210649579_embeddings_midpoints_nearest.json": {
|
| 60 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W4210649579_embeddings_midpoints_nearest.json",
|
| 61 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W4210649579_embeddings_midpoints_nearest_with_abstracts.json",
|
| 62 |
+
"processed_pairs": 2000,
|
| 63 |
+
"found_abstracts": 2000,
|
| 64 |
+
"missing_abstracts": 0
|
| 65 |
+
},
|
| 66 |
+
"percentile_pairs_W3177445623_embeddings_midpoints_nearest.json": {
|
| 67 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W3177445623_embeddings_midpoints_nearest.json",
|
| 68 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W3177445623_embeddings_midpoints_nearest_with_abstracts.json",
|
| 69 |
+
"processed_pairs": 2000,
|
| 70 |
+
"found_abstracts": 2000,
|
| 71 |
+
"missing_abstracts": 0
|
| 72 |
+
},
|
| 73 |
+
"percentile_pairs_W2979586175_embeddings_midpoints_nearest.json": {
|
| 74 |
+
"input_file": "pairs_wk_nearest/percentile_pairs_W2979586175_embeddings_midpoints_nearest.json",
|
| 75 |
+
"output_file": "pairs_wk_bridge/percentile_pairs_W2979586175_embeddings_midpoints_nearest_with_abstracts.json",
|
| 76 |
+
"processed_pairs": 2000,
|
| 77 |
+
"found_abstracts": 2000,
|
| 78 |
+
"missing_abstracts": 0
|
| 79 |
+
}
|
| 80 |
+
}
|
| 81 |
+
}
|
percentile_pairs_W2979586175_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6938f9cf034fca104ae4c3e688532228c2c7e31fc75db2a7dc0b03631032a444
|
| 3 |
+
size 27383764
|
percentile_pairs_W3164014860_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:581c30afa3d1f0650d787f2ebafc5d89983822c0c851fe375bcbbcfa68a4e4d4
|
| 3 |
+
size 31985938
|
percentile_pairs_W3166396011_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dafb1d70f09b760bf295b07544da950c4a622b6ed95438043952e6ee8dff00de
|
| 3 |
+
size 31022088
|
percentile_pairs_W3177445623_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f20e30b06390bf042820227e078df877e2676825f8b6bfe422330b3ea4a505ce
|
| 3 |
+
size 27833964
|
percentile_pairs_W3177828909_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd57b3520493b853b5a4d5c70166e73206eb986f00905f80e78bc5600927919f
|
| 3 |
+
size 31766146
|
percentile_pairs_W3209071234_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0005102a7e3847c1077ab3635e939734bf5d515a5019fa1fafc02ccdc12181a1
|
| 3 |
+
size 31197927
|
percentile_pairs_W4210649579_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8df4b5005b9d92e36806ab239031aea4c1098e21eeda21f5aef50a2acf216443
|
| 3 |
+
size 30813869
|
percentile_pairs_W4292779060_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc1374d9389124a48b43ece634b4e7a7032dc477eb4c18fa79f20de2efdc2dd8
|
| 3 |
+
size 31620511
|
percentile_pairs_W4321610982_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff10085819088f443969c98256ddfdf06fc60fc5e2ff86908b362e74a37f269a
|
| 3 |
+
size 31383714
|
percentile_pairs_W4385899778_embeddings_midpoints_nearest_with_abstracts.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2477c76990d98e48631f3f2001754b6bbd0a08d2dfa325fe643b4698b4c9daf0
|
| 3 |
+
size 28550300
|