arXiv subjects

Daniel Rodriguez-Cardenas

Publications and source records attributed to Daniel Rodriguez-Cardenas.

At least 19 recordsLinked to original sources

arXiv2026

On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study

Modern software systems require earlier and more scalable vulnerability severity assessment to reduce exposure to high-impact security flaws. Security analysts typically assign CVSS scores, but this manual triage does not scale with the growth of disclosed vulnerabilities and often depends on cloud LLM services that raise confidentiality concerns. This paper presents an industrial case study on predicting CVSS v3.1 scores directly from vulnerable C/C++ snippets using in-context learning with locally deployable, open-source LLMs. We compare proprietary data with the Big-Vul dataset, showing sufficiently aligned CVSS distributions to justify Big-Vul as a proxy for industrial data when constructing prompt-based testbeds. We then vary in-context configurations and model parameters, evaluating CodeLlama2-7B, CodeLlama2-13B, Mistral-7B, gpt-oss, and GPT4o-mini using mean squared error (MSE) and feasibility metrics. Our results show that medium-sized open-source code models, particularly CodeLlama2-7B, can approximate the best cloud performance for CVSS regression when guided by lightweight, output-constraining prompts, offering a practical, privacy-preserving building block for severity triage in industrial settings.

cs.CR↗

arXiv2026

CauSec: Unboxing the Causal Drivers of Static Vulnerability Analysis Performance

Static Application Security Testing (SAST) tools are widely used in both industry and academia. Such tools often make design choices that sacrifice detection to achieve higher performance, i.e., increased precision, decreased runtime, or increased scalability. These design choices rely on certain assumptions regarding the target code or the analysis technique itself. Hence, the assumptions directly impact the detection outcome through the design choices they influence. This motivates a key question: do the sacrifices in the detection capabilities actually help tools achieve the expected performance gains? That is, are the underlying assumptions valid? This paper seeks to address this question by relying on a key observation that the assumptions made by these tools are generally of a causal nature. We propose CAUSEC, a causal analysis framework that makes SAST assumptions testable and explains why the performance changes given certain assumptions, beyond simple correlations. CAUSEC formalizes the assumptions of the SAST tool into the abstraction of a security assumption and combines assumption-driven causal modeling with effect estimation and validation to test its validity and investigate the factors affecting it. To understand what security assumptions generally entail, we perform a systematic literature review of SASTs that detect crypto-API misuse, leading to the discovery and qualitative analysis of 57 assumptions. We then demonstrate the utility and robustness of CAUSEC by testing a popular assumption in four highly relevant tools, using a manually labeled ground truth dataset consisting of 57,038 alerts. Our analysis leads to several key findings that represent insights regarding assumptions and causal effects, which we distill into 3 takeaways for future work.

cs.CR↗

arXiv2026

ECLAIR: A Causally-Grounded AI Framework for Scientific Discovery in Empirical Software Engineering

The scientific method has long guided empirical research in Software Engineering (SE), but the complexity of modern software systems often hinders its systematic application. This paper introduces ECLAIR, a causally grounded AI framework that integrates Large Language Models (LLMs) into every stage of the scientific process, from hypothesis generation to analysis and interpretation. ECLAIR treats LLMs as active scientific agents operating under the principles of causal inference, within a human-in-the-loop design that safeguards against the risks of unsound automated reasoning. We demonstrate the framework through a case study examining how prompt design influences code generation accuracy in two LLMs. Results show that, for both models, instruction-style, longer few-shot, and signature-augmented prompts yield small negative causal effects on accuracy, illustrating how causal reasoning provides a principled foundation for explaining why software phenomena occur. This study presents the first causally grounded structured methodology for embedding LLMs within the scientific method in SE, designed around the epistemological demands of empirical SE research, establishing a basis for rigorous AI-assisted research.

cs.SE↗

arXiv2026

Rethinking Software Empirical Studies with Structural Causal Models

Causal Inference offers a fundamental approach for advancing empirical software engineering (ESE) beyond traditional statistical association, enabling researchers to rigorously identify and quantify causal relationships in software experiments. This paper introduces CausalSE, a framework that operationalizes Judea Pearl's causal inference paradigm in ESE context. The paper focuses on Structural Causal Models (SCMs) to address the limitations of classical statistical methods in mitigating confounding bias. Through a case study using the Galeras dataset and propensity score matching, we demonstrate how CausalSE disentangles the effect of prompt engineering strategies on code generation outcomes in a popular LLM (i.e., GPT-3). The results reveal that while associational analyses can suggest improvements in certain interventions (e.g., more complex prompts), causal analysis often does not find a significant treatment effect, highlighting the risk of false positives when confounding is not addressed. By providing a tutorial-based methodology and a real-world case study, this work equips software researchers with practical tools to design, analyze, and interpret software experiments with methodological rigor, ultimately enabling more informed and actionable conclusions in both research and practice.

cs.SE↗

arXiv2026

Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures

Software engineering research has focused on automating maintenance and evolution processes to reduce costs and improve reliability. The emergence of foundation models (FMs) with strong code understanding and reasoning abilities offers new opportunities for autonomous software behavior. Inspired by Artificial Life (ALife), we propose a fundamental shift in the Software Development Life-Cycle (SDLC) by introducing self-construction mechanisms that enable software to evolve and maintain autonomously. This position paper explores the potential of Autopoietic Architectures, specifically Psi-Arch, as a foundational framework for self-constructing software. We first analyze the limitations of traditional maintenance approaches and identify gaps in current SDLC automation. Subsequently, we outline the core challenges in achieving self-construction, including the integration of foundation-model-based reasoning units and the establishment of novel architectural paradigms. Although this paper does not present a definitive solution, it seeks to catalyze discourse and inspire research toward a new paradigm in software engineering, one in which self-constructing software represents the next frontier in SDLC automation.

cs.SE↗

arXiv2026

Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering

Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical gaps in robustness, interpretability, fairness, efficiency, and real-world usability. They also suffer from inconsistent data engineering practices, limited software engineering context, and widespread contamination issues. To understand these problems and chart a path forward, we combined an in-depth survey of existing benchmarks with insights gathered from a dedicated community workshop. We identified three core barriers to reliable evaluation: the absence of software-engineering-rich datasets, overreliance on ML-centric metrics, and the lack of standardized, reproducible data pipelines. Building on these findings, we introduce BEHELM, a holistic benchmarking infrastructure that unifies software-scenario specification with multi-metric evaluation. BEHELM provides a structured way to assess models across tasks, languages, input and output granularities, and key quality dimensions. Our goal is to reduce the overhead currently required to construct benchmarks while enabling a fair, realistic, and future-proof assessment of LLMs in software engineering.

cs.SE↗

arXiv2026

Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis

Large Language Models (LLMs) for code generation boost productivity but frequently introduce Knowledge Conflicting Hallucinations (KCHs), subtle, semantic errors, such as non-existent API parameters, that evade linters and cause runtime failures. Existing mitigations like constrained decoding or non-deterministic LLM-in-the-loop repair are often unreliable for these errors. This paper investigates whether a deterministic, static-analysis framework can reliably detect \textit{and} auto-correct KCHs. We propose a post-processing framework that parses generated code into an Abstract Syntax Tree (AST) and validates it against a dynamically-generated Knowledge Base (KB) built via library introspection. This non-executing approach uses deterministic rules to find and fix both API and identifier-level conflicts. On a manually-curated dataset of 200 Python snippets, our framework detected KCHs with 100\% precision and 87.6\% recall (0.934 F1-score), and successfully auto-corrected 77.0\% of all identified hallucinations. Our findings demonstrate that this deterministic post-processing approach is a viable and reliable alternative to probabilistic repair, offering a clear path toward trustworthy code generation.

cs.SE↗

arXiv2026

Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions

Large language models (LLMs) are increasingly integrated into software development workflows, yet they often introduce subtle logic or data-misuse errors that differ from human bugs. To study how these two error types interact, we construct Tricky$^2$, a hybrid dataset that augments the existing TrickyBugs corpus of human-written defects with errors injected by both GPT-5 and OpenAI-oss-20b across C++, Python, and Java programs. Our approach uses a taxonomy-guided prompting framework to generate machine-originated bugs while preserving original human defects and program structure. The resulting corpus spans human-only, LLM-only, and human+LLM splits, enabling analysis of mixed-origin error behavior, multi-bug repair robustness, and reliability in hybrid human-machine code. This paper outlines the dataset construction pipeline and illustrates its use through small-scale baseline evaluations of classification, localization, and repair tasks.

cs.SE↗

arXiv2025

A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code

Recent advances in large language models (LLMs) have accelerated their adoption in software engineering contexts. However, concerns persist about the structural quality of the code they produce. In particular, LLMs often replicate poor coding practices, introducing code smells (i.e., patterns that hinder readability, maintainability, or design integrity). Although prior research has examined the detection or repair of smells, we still lack a clear understanding of how and when these issues emerge in generated code. This paper addresses this gap by systematically measuring, explaining and mitigating smell propensity in LLM-generated code. We build on the Propensity Smelly Score (PSC), a probabilistic metric that estimates the likelihood of generating particular smell types, and establish its robustness as a signal of structural quality. Using PSC as an instrument for causal analysis, we identify how generation strategy, model size, model architecture and prompt formulation shape the structural properties of generated code. Our findings show that prompt design and architectural choices play a decisive role in smell propensity and motivate practical mitigation strategies that reduce its occurrence. A user study further demonstrates that PSC helps developers interpret model behavior and assess code quality, providing evidence that smell propensity signals can support human judgement. Taken together, our work lays the groundwork for integrating quality-aware assessments into the evaluation and deployment of LLMs for code.

cs.SE↗

arXiv2025

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation

As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering little insight into how decisions are made. Although post-hoc interpretability methods attempt to fill this gap, they often restrict explanations to local, token-level insights, which fail to provide a developer-understandable global analysis. Our work highlights the urgent need for \textbf{global, code-based} explanations that reveal how models reason across code. To support this vision, we introduce \textit{code rationales} (CodeQ), a framework that enables global interpretability by mapping token-level rationales to high-level programming categories. Aggregating thousands of these token-level explanations allows us to perform statistical analyses that expose systemic reasoning behaviors. We validate this aggregation by showing it distills a clear signal from noisy token data, reducing explanation uncertainty (Shannon entropy) by over 50%. Additionally, we find that a code generation model (\textit{codeparrot-small}) consistently favors shallow syntactic cues (e.g., \textbf{indentation}) over deeper semantic logic. Furthermore, in a user study with 37 participants, we find its reasoning is significantly misaligned with that of human developers. These findings, hidden from traditional metrics, demonstrate the importance of global interpretability techniques to foster trust in LM4Code.

cs.SE↗

arXiv2025

Testing Practices, Challenges, and Developer Perspectives in Open-Source IoT Platforms

As the popularity of Internet of Things (IoT) platforms grows, users gain unprecedented control over their homes, health monitoring, and daily task automation. However, the testing of software for these platforms poses significant challenges due to their diverse composition, e.g., common smart home platforms are often composed of varied types of devices that use a diverse array of communication protocols, connections to mobile apps, cloud services, as well as integration among various platforms. This paper is the first to uncover both the practices and perceptions behind testing in IoT platforms, particularly open-source smart home platforms. Our study is composed of two key components. First, we mine and empirically analyze the code and integrations of two highly popular and well-maintained open-source IoT platforms, OpenHab and HomeAssitant. Our analysis involves the identification of functional and related test methods based on the focal method approach. We find that OpenHab has only 0.04 test ratio ($\approx 4K$ focal test methods from $\approx 76K$ functional methods) in Java files, while HomeAssitant exhibits higher test ratio of $0.42$, which reveals a significant dearth of testing. Second, to understand the developers' perspective on testing in IoT, and to explain our empirical observations, we survey 80 open-source developers actively engaged in IoT platform development. Our analysis of survey responses reveals a significant focus on automated (unit) testing, and a lack of manual testing, which supports our empirical observations, as well as testing challenges specific to IoT. Together, our empirical analysis and survey yield 10 key findings that uncover the current state of testing in IoT platforms, and reveal key perceptions and challenges. These findings provide valuable guidance to the research community in navigating the complexities of effectively testing IoT platforms.

cs.SE↗

arXiv2025

SnipGen: A Mining Repository Framework for Evaluating LLMs for Code

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code repositories, exhibit remarkable capabilities for SE tasks. However, evaluating their effectiveness poses significant challenges, primarily due to the potential overlap between the datasets used for training and those employed for evaluation. To address this issue, we introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering across various downstream tasks for code generation. SnipGen aims to mitigate data contamination by generating robust testbeds and crafting tailored data points to assist researchers and practitioners in evaluating LLMs for code-related tasks. In our exploratory study, SnipGen mined approximately 227K data points from 338K recent code changes in GitHub commits, focusing on method-level granularity. SnipGen features a collection of prompt templates that can be combined to create a Chain-of-Thought-like sequence of prompts, enabling a nuanced assessment of LLMs' code generation quality. By providing the mining tool, the methodology, and the dataset, SnipGen empowers researchers and practitioners to rigorously evaluate and interpret LLMs' performance in software engineering contexts.

cs.SE↗

arXiv2024

How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study

Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, which primarily focus on accuracy, fall short in assessing the quality of the code generated by these models, specifically their tendency to produce code smells. To address this limitation, we introduce CodeSmellEval, a benchmark designed to evaluate the propensity of LLMs for generating code smells. Our benchmark includes a novel metric: Propensity Smelly Score (PSC), and a curated dataset of method-level code smells: CodeSmellData. To demonstrate the use of CodeSmellEval, we conducted a case study with two state-of-the-art LLMs, CodeLlama and Mistral. The results reveal that both models tend to generate code smells, such as simplifiable-condition and consider-merging-isinstance. These findings highlight the effectiveness of our benchmark in evaluating LLMs, providing valuable insights into their reliability and their propensity to introduce code smells in code generation tasks.

cs.SE↗

arXiv2024

Lost in Transmission: An Information-Theoretic Account of Unsupervised Software Traceability

Traceability remains a critical capability to ensure system reliability, maintainability, and compliance in modern software development. Although unsupervised Information Retrieval (IR) and Machine Learning (ML) techniques are widely adopted for automated trace link recovery, their effectiveness is often limited by the quality and structure of the underlying artifacts. In practice, these approaches assume that meaningful traceability signals are embedded in textual data, an assumption that rarely holds in industrial settings with sparse, inconsistent, or unbalanced documentation. Furthermore, conventional evaluation metrics (e.g., precision, recall, F1) can misrepresent performance when data characteristics are not explicitly considered. We introduce TraceXplainer, an information-theoretic framework for evaluating the reliability and limits of unsupervised traceability. Our approach leverages self-information and mutual information (MI) to quantify the informativeness and alignment of source and target artifacts. Through a comprehensive empirical analysis of industry datasets, we show that typical traceability corpora exhibit significant information imbalances, where the source code contains on average more information than the corresponding documentation. In addition, the observed levels of mutual information, loss, and noise reveal inherent constraints on the ability of unsupervised techniques to recover accurate trace links. These findings suggest that improving traceability in practice requires a shift to data-centric engineering, focusing on artifact quality, consistency, and information alignment; rather than solely advancing model sophistication (or complexity). Our results provide insights for practitioners to better assess traceability readiness and guide improvements in documentation and development workflows.

cs.SE↗

arXiv2024

Measuring Emergent Capabilities of LLMs for Software Engineering: How Far Are We?

The adoption of Large Language Models (LLMs) across multiple contexts has sparked interest in understanding how scaling model size might lead to behavioral changes, as LLMs can exhibit behaviors not observed in their smaller counterparts. Understanding these emergent capabilities is essential for advancing LLM development and improving their interpretability across diverse tasks. However, whether LLMs exhibit true emergence in the context of Software Engineering remains an unexplored topic, as most research has focused on NLP tasks. In this paper, we investigate the emergence of capabilities in the context of SE. We propose a model-agnostic pipeline for evaluating this phenomenon across three SE tasks: bug fixing, code translation, and commit message generation. More precisely, for each task, we present a case study instantiating our pipeline to analyze the emergence of capabilities in CodeGen1-multi across four scales ranging from 350M to 16.1B parameters. Our findings do not not provide evidence to support the idea of emergent capabilities resulting from scaling the model size in the selected set of tasks. We hope our results can pave the way to a more nuanced understanding of emergent capabilities of LLMs within the SE domain, guiding future research to focus on task-specific evaluations and the identification of alternative factors contributing to this phenomenon. Our work underscores the importance of task diversity in examining model behaviors and highlights potential limitations in transferring prior understandings of and approaches to emergence from NLP to Software Engineering.

cs.SE↗

arXiv2024

Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations

Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, current techniques for interpreting LLMs when applied to code-related tasks largely focus on accuracy measurements, measures of how models react to change, or individual task performance instead of the fine-grained explanations needed at prediction time for greater interpretability, and hence trust. To improve upon this status quo, this paper introduces ASTrust, an interpretability method for LLMs of code that generates explanations grounded in the relationship between model confidence and syntactic structures of programming languages. ASTrust explains generated code in the context of syntax categories based on Abstract Syntax Trees and aids practitioners in understanding model predictions at both local (individual code snippets) and global (larger datasets of code) levels. By distributing and assigning model confidence scores to well-known syntactic structures that exist within ASTs, our approach moves beyond prior techniques that perform token-level confidence mapping by offering a view of model confidence that directly aligns with programming language concepts with which developers are familiar. To put ASTrust into practice, we developed an automated visualization that illustrates the aggregated model confidence scores superimposed on sequence, heat-map, and graph-based visuals of syntactic structures from ASTs. We examine both the practical benefit that ASTrust can provide through a data science study on 12 popular LLMs on a curated set of GitHub repos and the usefulness of ASTrust through a human study.

cs.SE↗

arXiv2024

Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?

This paper discusses the limitations of evaluating Masked Language Models (MLMs) in code completion tasks. We highlight that relying on accuracy-based measurements may lead to an overestimation of models' capabilities by neglecting the syntax rules of programming languages. To address these issues, we introduce a technique called SyntaxEval in which Syntactic Capabilities are used to enhance the evaluation of MLMs. SyntaxEval automates the process of masking elements in the model input based on their Abstract Syntax Trees (ASTs). We conducted a case study on two popular MLMs using data from GitHub repositories. Our results showed negative causal effects between the node types and MLMs' accuracy. We conclude that MLMs under study fail to predict some syntactic capabilities.

cs.SE↗

arXiv2023

Benchmarking Causal Study to Interpret Large Language Models for Source Code

One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. Although a number of studies have shown that LLMs have been effectively evaluated on popular accuracy metrics (e.g., BLEU, CodeBleu), previous research has largely overlooked the role of Causal Inference as a fundamental component of the interpretability of LLMs' performance. Existing benchmarks and datasets are meant to highlight the difference between the expected and the generated outcome, but do not take into account confounding variables (e.g., lines of code, prompt size) that equally influence the accuracy metrics. The fact remains that, when dealing with generative software tasks by LLMs, no benchmark is available to tell researchers how to quantify neither the causal effect of SE-based treatments nor the correlation of confounders to the model's performance. In an effort to bring statistical rigor to the evaluation of LLMs, this paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks (i.e., code completion, code summarization, and commit generation) to help aid the interpretation of LLMs' performance. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods. The results of the case study demonstrate the positive causal influence of prompt semantics on ChatGPT's generative performance by an average treatment effect of $\approx 3\%$. Moreover, it was found that confounders such as prompt size are highly correlated with accuracy metrics ($\approx 0.412\%$). The end result of our case study is to showcase causal inference evaluations, in practice, to reduce confounding bias. By reducing the bias, we offer an interpretable solution for the accuracy metric under analysis.

cs.SE↗