update notes

2 files changed, 29 insertions, 12 deletions

diff --git a/README.md b/README.md
index 72b91b4..342a03a 100644
--- a/README.md
+++ b/README.md
@@ -140,9 +140,28 @@ Cases
 
 * common title, "Books by Our Readers", https://fatcat.wiki/release/4uv5jsy5vnhdvnxvzmucqlksvq, https://fatcat.wiki/release/4uv5jsy5vnhdvnxvzmucqlksvq
 * common title, "The Future of Imprisonment"
-* same title "IEEE Transactions on Wireless Communications", same publisher, different year
+* common title, "In This Issue/Research Watch/News-in-Brief/News from the IASLC Tobacco Control Committee"
+* common title, "IEEE Transactions on Wireless Communications", same publisher, different year
+* common title, "ASMS News" (also different year)
+* common title, "AMERICAN INSTITUTE OF INSTRUCTION"
+* common title, "Contents lists"
 * same, except DOI, but maybe the same item, after all? https://fatcat.wiki/release/kxgsbh66v5bwhobcaiuh4i7dwy, https://fatcat.wiki/release/thl7o44z3jgk3njdypixwrdbve
 
+Authors may be messy:
+
+* IR and published, be we currently yield `Miss.CONTRIB_INTERSECTION_EMPTY` -
+  https://fatcat.wiki/release/2kpa6ynwjzhtbbokqyxcl25gmm,
+https://fatcat.wiki/release/o4dh7w7nqvdknm4j336yrom4wy - may need to tokenize authors
+
 Possible improvements:
 
-* when title and authors match, check the year, and maybe the doi prefix; doi with the same prefix may not be duplicates
+* [ ] when title and authors match, check the year, and maybe the doi prefix; doi with the same prefix may not be duplicates
+* [x] detect arxiv versions directly
+* [ ] if multiple authors, may require more than one overlap, e.g. "by Yuting
+  Yao, Yuting Yao, Yuting Yao, Imperial College London, Imperial College
+London" - will overlap with any other author including "Imperial College
+London" -- we label `OK.SLUG_TITLE_AUTHOR_MATCH`,
+https://fatcat.wiki/release/6qbne2adybegdf6plgb7dnly2a,
+https://fatcat.wiki/release/v6cjc6kxzncztebmfgzxwov7ym
+* [ ] "article-journal" and "article" `release_type` should be treated the same, https://fatcat.wiki/release/k5zdpb45ufcy7grrppqndtxxji, https://fatcat.wiki/release/ypyse6ff4nbzrfd44resyav25m
+
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py
index 58fa0b8..88b7b71 100644
--- a/fuzzycat/verify.py
+++ b/fuzzycat/verify.py
@@ -182,6 +182,14 @@ def compare(a, b):
     if re.match(r"appendix ?[^ ]*$", a.get("title", "").lower()):
         return (Status.AMBIGUOUS, Miss.APPENDIX)
 
+    arxiv_id_a = a.get("ext_ids", {}).get("arxiv")
+    arxiv_id_b = b.get("ext_ids", {}).get("arxiv")
+    if arxiv_id_a and arxiv_id_b:
+        id_a, version_a = arxiv_id_a.split("v")
+        id_b, version_b = arxiv_id_b.split("v")
+        if id_a == id_b:
+            return (Status.STRONG, OK.ARXIV_VERSION)
+
     if a.get("release_type") and b.get(
             "release_type") and a.get("release_type") != b.get("release_type"):
         return (Status.DIFFERENT, Miss.RELEASE_TYPE)
@@ -261,16 +269,6 @@ def compare(a, b):
         if len(a_slug_authors & b_slug_authors) > 0:
             return (Status.STRONG, OK.SLUG_TITLE_AUTHOR_MATCH)
 
-    arxiv_id_a = a.get("ext_ids", {}).get("arxiv")
-    arxiv_id_b = b.get("ext_ids", {}).get("arxiv")
-    if arxiv_id_a and arxiv_id_b:
-        id_a, version_a = arxiv_id_a.split("v")
-        id_b, version_b = arxiv_id_b.split("v")
-        if id_a == id_b:
-            return (Status.STRONG, OK.ARXIV_VERSION)
-        else:
-            return (Status.DIFFERENT, Miss.ARXIV_VERSION)
-
     if a_authors and len(a_slug_authors & b_slug_authors) == 0:
         return (Status.DIFFERENT, Miss.CONTRIB_INTERSECTION_EMPTY)