Source code and data published at computational linguistics (*CL) venues are increasingly being shared via GitHub. While this generally is a favourable development for the accessibility and potential reusability of research artifacts in natural language processing (NLP), the long-term availability of such repositories has not been evaluated. In this squib, we discuss the availability of repositories linked in papers published in the Computational Linguistics (CL) journal as well as at ACL and its co-located events over the past ten years. Contrary to our expectations, we find that GitHub repositories linked in more recent ACL publications are unavailable at similar rates as in older publications, in parts due to an increase in empty and placeholder repositories. Similar trends hold for other *CL venues, but not for platforms other than GitHub.
Figures & tables
Figure 1 : Share of unavailable GitHub repositories linked in ACL papers. While older links might reasonably decay, the consistent unavailability in recent years is concerning.
Figure 2Figure 3
Conference
Unavailable
/
Total Links (%)
Own Code
Unavailability type
404
Empty
Placeholder
ACL
186
/
4454 (4%)
88%
43%
13%
44%
NAACL
85
/
1961 (4%)
87%
55%
12%
32%
EMNLP
196
/
4104 (5%)
92%
37%
17%
46%
EACL
37
/
826 (4%)
95%
60%
9%
31%
AACL
38
/
551 (7%)
92%
51%
17%
31%
Table 1 : Share of papers with GitHub links at EACL and LREC 2024 as well as ACL, COLING, EMNLP, AACL and NAACL 2025 and percentage of those links pointing to unavailable repositories. Share of unavailable repositories for papers’ own code/data, with breakdown of unavailability types within that subset provided in brackets.