16 citations · 30 across the 8 of their papers we have counts for
9 papers
The Code of Theseus: Can Agents Rebuild Software from Recovered Design Documents?
Cezar Sas, Sandra Mitrović, Fabio Barth +2
LLM agents increasingly design a system before implementing it, yet the data to train and evaluate them centres on implementation and testing: requirements and design artefacts are…
Automatic Bottom-Up Taxonomy Construction: A Software Application Domain Study
Cezar Sas, Andrea Capiluppi
Previous research in software application domain classification has faced challenges due to the lack of a proper taxonomy that explicitly models relations between classes. As a res…
AutoFL: A Tool for Automatic Multi-granular Labelling of Software Repositories
Cezar Sas, Andrea Capiluppi
Software comprehension, especially of new code bases, is time consuming for developers, especially in large projects with multiple functionalities spanning various domains. One str…
Multi-granular Software Annotation using File-level Weak Labelling
Cezar Sas, Andrea Capiluppi
One of the most time-consuming tasks for developers is the comprehension of new code bases. An effective approach to aid this process is to label source code files with meaningful…
GitRanking: A Ranking of GitHub Topics for Software Classification using Active Sampling
Cezar Sas, Andrea Capiluppi, Claudio Di Sipio +2
GitHub is the world's largest host of source code, with more than 150M repositories. However, most of these repositories are not labeled or inadequately so, making it harder for us…
Antipatterns in Software Classification Taxonomies
Cezar Sas, Andrea Capiluppi
Empirical results in software engineering have long started to show that findings are unlikely to be applicable to all software systems, or any domain: results need to be evaluated…
LabelGit: A Dataset for Software Repositories Classification using Attributed Dependency Graphs
Cezar Sas, Andrea Capiluppi
Software repository hosting services contain large amounts of open-source software, with GitHub hosting more than 100 million repositories, from new to established ones. Given this…
Using Structural and Semantic Information to Identify Software Components
Cezar Sas, Andrea Capiluppi
Component Based Software Engineering (CBSE) seeks to promote the reuse of software by using existing software modules into the development process. However, the availability of suc…
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension
Mostafa Abdou, Cezar Sas, Rahul Aralikatte +2
Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in different languages. Exploiting this, we introduc…