History of openalex_cocitations
The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.
[entries] Add the date when each entry was added, and remove icon_hash beff7c9
The dates are those of the commits that first added the entries' files (2020-08-11 for the entries of the initial commit); renamed entries keep the date of their first name. Changed: none
diff --git a/entries/openalex_cocitations/__init__.py b/entries/openalex_cocitations/__init__.py
index b9ebb73..9c15a48 100644
--- a/entries/openalex_cocitations/__init__.py
+++ b/entries/openalex_cocitations/__init__.py
@@ -46,7 +46,7 @@ url = ['https://github.com/xgi-org/xgi-data',
'https://openalex.org/']
citation = [('K. Nakajima, Y. Sasaki, T. Uno, M. Aida, "Learning Multi-Order Block Structure in Higher-Order Networks." arXiv:2511.21350 (2025)', 'https://doi.org/10.48550/arXiv.2511.21350'),
('J. Priem, H. Piwowar, R. Orr, "OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts." arXiv:2205.01833 (2022)', 'https://doi.org/10.48550/arXiv.2205.01833')]
-icon_hash = None
+date_added = '2026-10-27'
upstream_license = ('CC BY 4.0', 'https://creativecommons.org/licenses/by/4.0/')
upstream_prefix = 'https://zenodo.org/records'
_records = {"biochem": 20601519, "cs": 19477689, "math": 20601560,
[entries] Prefix the properties in the descriptions with (Node), (Edge) or (Graph) bc3dbbd
The lists of properties at the end of the descriptions marked edge properties with "Edge" but left node properties unmarked, or grouped them in "Nodes: `a`, ...; `b`, ..." items, so the kind of a property was often unclear. Every item now starts with (Node), (Edge) or (Graph), followed by the property names, a colon and the explanation, one item per property or group of properties; qualifications (kinds of nodes, networks) follow the names in parentheses. Properties that were only named got a short explanation, and a few items that named the wrong kind of property were corrected.
diff --git a/entries/openalex_cocitations/__init__.py b/entries/openalex_cocitations/__init__.py
index 95f7735..b9ebb73 100644
--- a/entries/openalex_cocitations/__init__.py
+++ b/entries/openalex_cocitations/__init__.py
@@ -34,8 +34,13 @@ In each field, the papers of each subfield were ranked by their numbers of citat
The networks have the following properties:
-- `is_cocitation`: whether the node is a co-citation set (otherwise a paper).
-- Papers: `openalex_id`, the OpenAlex identifier of the paper (e.g. `W2010634640`, see `https://openalex.org/<id>`); `title`, the title of the paper (in lower case); `date`, the publication date (YYYY-MM-DD); `year`, the publication year; `topic`, `subfield`, `field` and `domain`, the primary topic of the paper in OpenAlex and its subfield, field and domain; `cited_by_count`, the number of citations of the paper in OpenAlex."""
+- (Node) `is_cocitation`: whether the node is a co-citation set (otherwise a paper).
+- (Node) `openalex_id` (papers): the OpenAlex identifier of the paper (e.g. `W2010634640`, see `https://openalex.org/<id>`).
+- (Node) `title` (papers): the title of the paper (in lower case).
+- (Node) `date` (papers): the publication date (YYYY-MM-DD).
+- (Node) `year` (papers): the publication year.
+- (Node) `topic`, `subfield`, `field`, `domain` (papers): the primary topic of the paper in OpenAlex and its subfield, field and domain.
+- (Node) `cited_by_count` (papers): the number of citations of the paper in OpenAlex."""
tags = ['Informational', 'Citation', 'Unweighted', 'Metadata']
url = ['https://github.com/xgi-org/xgi-data',
'https://openalex.org/']
[entries] Remove unneeded code from the entries 2c69f19
Unneeded "global files" statements, unused imports and variables, f-strings without placeholders, duplicate keys in foodweb_little_rock (keeping the order and the values used), and the second definition of get_lines() in twitter_higgs. Nothing changes in the networks or descriptions. Changed: none
diff --git a/entries/openalex_cocitations/__init__.py b/entries/openalex_cocitations/__init__.py
index 62a118a..95f7735 100644
--- a/entries/openalex_cocitations/__init__.py
+++ b/entries/openalex_cocitations/__init__.py
@@ -56,7 +56,6 @@ def fetch_upstream(force=False):
@coerce_props()
@annotate()
def parse(alts=None):
- global files
name = __name__.split(".")[-1]
for fname, alt, fmt in files:
if alts is not None and alt not in alts:
[entries] New entry: openalex_cocitations 672b554
diff --git a/entries/openalex_cocitations/__init__.py b/entries/openalex_cocitations/__init__.py
new file mode 100644
index 0000000..62a118a
--- /dev/null
+++ b/entries/openalex_cocitations/__init__.py
@@ -0,0 +1,87 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2026 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+
+
+from .. import *
+
+
+title = "Co-citations of highly cited papers in five fields (OpenAlex, 2024)"
+description = """Bipartite networks of highly cited papers and the sets of them that are cited together, in five fields of research, built by Nakajima et al. from the OpenAlex snapshot of 27 September 2024, as distributed by XGI-data:
+
+- `biochem`: Biochemistry, Genetics and Molecular Biology;
+- `cs`: Computer Science;
+- `math`: Mathematics;
+- `neuro`: Neuroscience;
+- `physics`: Physics and Astronomy.
+
+In each field, the papers of each subfield were ranked by their numbers of citations, and the top papers that account for 10% of the cumulative citations of the subfield were selected (at least 100 papers per subfield). For each other paper of OpenAlex, the set of selected papers it cites was determined; each set of at least two papers that is cited by at least 3 papers is a co-citation set, connected to its papers. The sets cited by fewer papers, and the numbers of papers citing each set, are not included in the data.
+
+The networks have the following properties:
+
+- `is_cocitation`: whether the node is a co-citation set (otherwise a paper).
+- Papers: `openalex_id`, the OpenAlex identifier of the paper (e.g. `W2010634640`, see `https://openalex.org/<id>`); `title`, the title of the paper (in lower case); `date`, the publication date (YYYY-MM-DD); `year`, the publication year; `topic`, `subfield`, `field` and `domain`, the primary topic of the paper in OpenAlex and its subfield, field and domain; `cited_by_count`, the number of citations of the paper in OpenAlex."""
+tags = ['Informational', 'Citation', 'Unweighted', 'Metadata']
+url = ['https://github.com/xgi-org/xgi-data',
+ 'https://openalex.org/']
+citation = [('K. Nakajima, Y. Sasaki, T. Uno, M. Aida, "Learning Multi-Order Block Structure in Higher-Order Networks." arXiv:2511.21350 (2025)', 'https://doi.org/10.48550/arXiv.2511.21350'),
+ ('J. Priem, H. Piwowar, R. Orr, "OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts." arXiv:2205.01833 (2022)', 'https://doi.org/10.48550/arXiv.2205.01833')]
+icon_hash = None
+upstream_license = ('CC BY 4.0', 'https://creativecommons.org/licenses/by/4.0/')
+upstream_prefix = 'https://zenodo.org/records'
+_records = {"biochem": 20601519, "cs": 19477689, "math": 20601560,
+ "neuro": 20601541, "physics": 20601460}
+files = [(f'{r}/files/{f}-cocitations.json', f, None) for f, r in _records.items()]
+
+def fetch_upstream(force=False):
+ return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+ force)
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+ global files
+ name = __name__.split(".")[-1]
+ for fname, alt, fmt in files:
+ if alts is not None and alt not in alts:
+ continue
+ # HIF (hypergraph interchange format) of XGI
+ with open_upstream_file(name, fname, "r") as f:
+ d = json.load(f)
+ papers = sorted(d["nodes"], key=lambda n: int(n["node"]))
+ pindex = {n["node"]: i for i, n in enumerate(papers)}
+ N = len(papers)
+ sets = sorted(set(int(x["edge"]) for x in d["incidences"]))
+ sindex = {s: N + i for i, s in enumerate(sets)}
+ g = Graph(directed=False)
+ g.add_vertex(N + len(sets))
+ g.vp.is_cocitation = g.new_vp("bool")
+ g.vp.is_cocitation.a[N:] = True
+ empty = [""] * len(sets)
+ for k, p in [("openalex_id", "openalex_id"), ("title", "title"),
+ ("pub_date", "date"), ("primary_topic_name", "topic"),
+ ("primary_subfield", "subfield"), ("primary_field", "field"),
+ ("primary_domain", "domain")]:
+ g.vp[p] = g.new_vp("string", vals=[n["attrs"][k] for n in papers] + empty)
+ for k in ["year", "cited_by_count"]:
+ g.vp[k] = g.new_vp("int", val=-1)
+ g.vp[k].a[:N] = [n["attrs"][k] for n in papers]
+ g.add_edge_list(sorted(set((pindex[x["node"]], sindex[int(x["edge"])])
+ for x in d["incidences"]), key=lambda e: e[::-1]))
+ yield alt, g