From df70259a6c42fc17245df419fdcdc73f9c7776f1 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Fri, 11 Dec 2020 00:43:33 +0100
Subject: update stats

---
 notes/2020_11_testruns.md | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

(limited to 'notes')

diff --git a/notes/2020_11_testruns.md b/notes/2020_11_testruns.md
index b8b35c9..ec186ac 100644
--- a/notes/2020_11_testruns.md
+++ b/notes/2020_11_testruns.md
@@ -58,37 +58,42 @@ The cluster size distribution is:
 Preliminary case distribution:
 
 ```
-3578378 OK.TITLE_AUTHOR_MATCH
-2989618 Miss.CONTRIB_INTERSECTION_EMPTY
-2731528 OK.SLUG_TITLE_AUTHOR_MATCH
-2654787 Miss.YEAR
+3487747 OK.TITLE_AUTHOR_MATCH
+2659228 OK.SLUG_TITLE_AUTHOR_MATCH
+2608963 Miss.YEAR
 2434532 OK.WORK_ID
-2050468 OK.DUMMY
-1619330 Miss.SHARED_DOI_PREFIX
+2191541 Miss.CONTRIB_INTERSECTION_EMPTY
+1567346 OK.DUMMY
+1398049 Miss.SHARED_DOI_PREFIX
 1145571 Miss.BOOK_CHAPTER
-1023925 Miss.DATASET_DOI
+1024912 Miss.RELEASE_TYPE
+1023906 Miss.DATASET_DOI
+1002941 OK.PMID_DOI_PAIR
  934075 OK.DATACITE_RELATED_ID
  868951 OK.DATACITE_VERSION
  704154 OK.FIGSHARE_VERSION
- 682784 Miss.RELEASE_TYPE
- 607117 OK.TOKENIZED_AUTHORS
- 298928 OK.PREPRINT_PUBLISHED
- 270658 Miss.SUBTITLE
- 227537 Miss.SHORT_TITLE
- 196402 Miss.COMPONENT
- 163158 Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW
- 122614 Miss.CUSTOM_PREFIX_10_7916
+ 387207 Miss.COMPONENT
+ 347777 OK.TOKENIZED_AUTHORS
+ 338607 OK.JACCARD_AUTHORS
+ 294490 OK.PREPRINT_PUBLISHED
+ 269171 Miss.SUBTITLE
+ 224872 Miss.SHORT_TITLE
+ 158070 Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW
+ 122600 Miss.CUSTOM_PREFIX_10_7916
+  97030 Miss.PAGE_COUNT
   79687 OK.CUSTOM_IEEE_ARXIV
-  69648 OK.PMID_DOI_PAIR
   46649 Miss.CUSTOM_PREFIX_10_14288
+  39797 Miss.JSTOR_ID
   38598 OK.CUSTOM_BSI_UNDATED
+  24219 OK.VERSIONED_DOI
+  18907 OK.CUSTOM_BSI_SUBDOC
   15465 OK.DOI
   13393 Miss.CUSTOM_IOP_MA_PATTERN
   10378 Miss.CONTAINER
    3045 Miss.BLACKLISTED
    2504 Miss.BLACKLISTED_FRAGMENT
-   1574 Miss.TITLE_FILENAME
    1273 Miss.APPENDIX
+   1074 Miss.TITLE_FILENAME
     104 Miss.NUM_DIFF
       4 OK.ARXIV_VERSION
 ```
-- 
cgit v1.2.3