EUVIMED · CrossrefJournal
Empirical Software Engineering
ISSN 1382-3256 · Springer Science and Business Media LLC
Latest articles
Gem-Diff : Fine-grained code differencing via structure-aware graph embedding and matching
Guidelines for empirical studies in software engineering involving large language models
A decade of software reproducibility in the nix package ecosystem
SysML behavior model generation with formal verification feedback leveraging large language models
Refactoring architectural smells with large language models: an exploratory study on cyclic dependencies
Plan-Driven front-end, agile execution: a study of public-sector software development projects
Incubation and Beyond: A Comparative Analysis of ASF Projects Sustainability Impacts on Software Quality
Developing LLM-based multi-agent systems in software engineering: a mixed-method experience report
A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
Silent data thieves: Investigating malicious data exfiltration packages in PyPI
TVR: Automotive system requirements Traceability Validation and Recovery through retrieval-augmented generation
BugReproAgent: an autonomous multimodal agent for user-feedback-driven bug reproduction and augmented reporting
How do copilot suggestions impact developers’ frustration and productivity?
The More You Tune, the More They Spill?
CodeTransBenchmark: evaluating LLM-based code translation and repair across programming languages
WITNESS: Unlocking lightweight and practical fine-grained predictive mutation testing
MigrateLib: A tool for end-to-end Python library migration
Empirical insights on the use of large language models in software verification and validation: evidence from the Brazilian IT industry
On exploring ways to enhance participation in Software Engineering communities
Reproducibility debt: insights from practitioners
Security debt in practice: nuanced insights from practitioners
How software development practices shape inclusion: an exploratory study of equity, diversity, and inclusion
Short-Link-Based collection and vision-based detection of underground economy apps
Leveraging semantic analysis to identify memory copy function in stripped binaries for vulnerability discovery
Understanding developer pain points in federated learning: insights from stack overflow and GitHub
Beyond synthetic benchmarks: evaluating LLM performance on real-world class-level python code generation
Evaluating multi-LLM pipelines for early-stage software requirements elicitation
Differentiating refactoring practices: a comparative analysis of ML and non-ML frameworks
The cost of AI-assisted coding: An extensive investigation of energy vs. accuracy in language models
Following breadcrumbs in code
EUVIMED