Cezar Sas, PhD – Researcher

About

His work sits at the intersection of AI and software engineering, with a focus on using language models and multi-agent systems to automate and improve software development workflows. He holds a PhD from the University of Groningen, where his doctoral research centred on source code classification and automated software categorisation at scale.

Projects

Human-centred collaboratIVE MultI-ageNt framework for accelerating software Development and maintenance (HIVEMIND) Active

Software

ANT-AI – Lightweight Framework for Multi-Agent AI Systems Active

Publications

Thesis Paper

Understanding Software through Automated Classification: A Taxonomic Perspective

Cezar Sas

Program Comprehension AI4SE Software Classification

Preprint Paper

Embedding-Based Semantic Tracing: Mapping Concepts to Domains in Software Artifacts

Zaki Pauzi, Cezar Sas, Andrea Capiluppi

Software Engineering Traceability AI4SE

Journal Paper

Multi-granular software annotation using file-level weak labelling

Cezar Sas, Andrea Capiluppi Empirical Software Engineering, 2024

Software Engineering Research Advanced Malware Detection Techniques Software System Performance and Reliability

Preprint Paper

Automatic Bottom-Up Taxonomy Construction: A Software Application Domain Study

Cezar Sas, Andrea Capiluppi arXiv, 2024

Software System Performance and Reliability

Preprint Paper

AutoFL: A Tool for Automatic Multi-granular Labelling of Software Repositories

Cezar Sas, Andrea Capiluppi arXiv, 2024

Software Engineering Research

Conference Paper

Weak Labelling for File-level Source Code Classification

Cezar Sas, Andrea Capiluppi 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2023

Software Engineering AI4SE Software Classification

Journal Paper

GitRanking: A ranking of GitHub topics for software classification using active sampling

Cezar Sas, Andrea Capiluppi, Claudio Di Sipio, Juri Di Rocco, Davide Di Ruscio Software: Practice and Experience, 2023

Software Engineering Research Topic Modeling Wikis in Education and Collaboration

Journal Paper

Antipatterns in software classification taxonomies

Cezar Sas, Andrea Capiluppi Journal of Systems and Software, 2022

Software Engineering Research Web Data Mining and Analysis Data Stream Mining Techniques

Conference Paper

Using Structural and Semantic Information to Identify Software Components

Cezar Sas, Andrea Capiluppi 2021 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2021

Software Engineering Mining Software Repositories Component Identification

Preprint Paper

LabelGit: A dataset for software repositories classification using attributed dependency graphs

Cezar Sas, Andrea Capiluppi arXiv, 2021

Software Engineering AI4SE Software Classification

Conference Paper

WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing

Cezar Sas, Meriem Beloucif, Anders Søgaard Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020), 2020

NLP Topic Modeling Semantic Role Labelling

Conference Paper

Word Embeddings for Unsupervised Named Entity Linking

Debora Nozza, Cezar Sas, Elisabetta Fersini, Enza Messina Knowledge Science, Engineering and Management (KSEM 2019), 2019

Topic Modeling NLP Named Entity Linking

Conference Paper

X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension

Mostafa Abdou, Cezar Sas, Rahul Aralikatte, Isabelle Augenstein, Anders Søgaard Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), 2019

NLP Topic Modeling Relation Extraction

Workshop Paper

UNIMIB@NEEL-IT : Named Entity Recognition and Linking of Italian Tweets

Flavio Massimiliano Cecchini, Elisabetta Fersini, Pikakshi Manchanda, Enza Messina, Debora Nozza, Matteo Palmonari, Cezar Sas CLiC-it 2016 & EVALITA 2016, 2016

Topic Modeling NLP Web Data Mining and Analysis