CSCC: Simple, Efficient, Context Sensitive Code Completion
Abstract
Code Completion helps developers learn APIs and frees them from remembering every detail. In this paper, we describe a novel technique called CSCC (Context Sensitive Code Completion) for improving the performance of API method call completion. CSCC is context sensitive in that it uses new sources of information as the context of a target method call. CSCC indexes method calls in code examples by their contexts. To recommend completion proposals, CSCC ranks candidate methods by the similarities between their contexts and the context of the target call. Evaluation using a set of subject systems and five popular state of-the-art techniques suggests that CSCC performs better than existing type or example-based code completion systems. We also investigate how the different contextual elements of the target call benefit CSCC.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prior work indicates a perceived necessity of very precise, context-sensitive recommendations.
“This was also consistent with the perceived necessity of very precise, context-sensitive recommendations (Asaduzzaman et al., 2014).”
From Understanding user mental models in AI-driven code completion tools: Insights from an elicitation study (2025) · cites this paper as Asaduzzaman et al., 2014
Cites
How Program History Can Improve Code Completion
Robbes, R., & Lanza, M. (2008) · 2008 23rd IEEE/ACM International Conference on Automated Software Engineering · doi:10.1109/ase.2008.42 · Cited by 155 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
IntelliCode compose: code generation using transformer
Svyatkovskiy, A., Deng, S. K., Fu, S., & Sundaresan, N. (2020) · Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3368089.3417058 · Cited by 474 · see citing works
“Numerous intelligent code completion systems for both statically and dynamically typed languages have been proposed [6, 11, 41, 42].”
BackgroundMethodSignificant Productivity Gains through Programming with Large Language Models
Weber, T., Brandmaier, M., Schmidt, A., & Mayer, S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3661145 · Cited by 64 · see citing works
“…and industry have explored different mechanisms how these suggestions and code completions can be generated, from semantic analysis of the source code [3, 22, 28, 48, 49] to machine learning approaches [43, 57] Programming with Large Language Models 256:3 and different combinations [7, 47].”
BackgroundDesolda, G., Esposito, A., Greco, F., Tucci, C., Buono, P., & Piccinno, A. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103648 · Cited by 7 · see citing works
- Authors
- Asaduzzaman, M., Roy, C. K., Schneider, K. A., & Hou, D.
- Affiliations
- University of Saskatchewan (CA)
- Clarkson University (US)
- Venue
- 2014 IEEE International Conference on Software Maintenance and Evolution
- Publisher
- IEEE
- Published
- 2014-09
- Pages
- 71-80
- ISSN
- 1063-6773 (ISSN-L)
- OpenAlex
- W2052468877
- Cited by
- 55
- References
- 1
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 4 · 2023: 5 · 2022: 1 · 2021: 10 · 2020: 4 · 2019: 3 · 2018: 5 · 2017: 4 · 2016: 6 · 2015: 5 · 2014: 2
- FWCI
- 4.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Software Maintenance (ICSM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- code completion, code examples, contextual similarity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review