arXiv subjects

Gouri Ginde

Publications and source records attributed to Gouri Ginde.

At least 19 recordsLinked to original sources

arXiv2026

FLARE: A Systematic, Uncertainty-Aware Framework for Evidence-Based Adoption of Artificial Intelligence in Healthcare

Artificial intelligence is increasingly being introduced into healthcare workflows, yet most evaluations emphasize model accuracy rather than whether adoption is economically worthwhile in real clinical settings. This study proposes FLARE, a systematic and uncertainty-aware framework for evaluating the financial and operational implications of adopting AI in healthcare. FLARE combines fuzzy logic, time-driven activity-based costing, and return on investment analysis to estimate the cost of clinical service delivery, the cost of AI development and operation, and the economic consequences of workflow integration under uncertainty. The framework was demonstrated through an early health technology assessment case study of AI-assisted large vessel occlusion detection in the CT stroke pathway for acute ischemic stroke. The case study shows how FLARE can quantify conventional pathway cost, AI-related development and recurring costs, and AI-enabled service savings within a unified activity-based model. Under expected assumptions, the analysis identified a break-even threshold of approximately 3,992 patients per year, with positive first-year return on investment at typical annual stroke volumes of about 5,000 patients. The results further show that economic benefit depends not only on algorithmic performance, but also on patient volume, verification time, infrastructure choices, and workflow design. FLARE provides a transparent and practical decision-support framework for early-stage evaluation of AI adoption in healthcare. By making uncertainty, resource use, and implementation trade-offs explicit, it helps clinicians, administrators, and policymakers determine when AI deployment is economically viable and where operational changes may improve value.

cs.AI↗

arXiv2026

Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries

Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, including sections such as Steps-to-Reproduce (S2R), Actual Behavior (AB), and Expected Behavior (EB). However, these models frequently produce hallucinations that can be convincing but unsupported by the source report. This can mislead developers and reduce trust in automated maintenance tools. Existing hallucination detection approaches typically evaluate outputs at the full-response level and do not consider the structure of technical documents. An initial exploratory study on 80 structured bug report summaries found that approximately 47.9% contained missing information, while 12.3% included fabricated content, highlighting the need for systematic hallucination analysis in bug report summarization. In this work, we empirically investigate hallucinations in LLM-generated bug report summaries from a section-aware perspective. Using the BugsRepo dataset, derived from Mozilla OSS projects, we introduce controlled synthetic hallucination injection to construct a benchmark for training and evaluation. We propose a section-aware hallucination detection approach that jointly predicts whether a summary contains hallucinated content, identifies affected sections, and classifies hallucination types. Experimental results across multiple pretrained language models show that the proposed approach achieves strong performance across all tasks, with the best model obtaining 0.89 report-level Macro-F1, 0.83 section-level Macro-F1, and 0.84 hallucination-type Macro-F1. We further analyze common hallucination patterns and model failure modes to better understand limitations of current LLM-generated bug report summaries. The findings highlight the importance of section-aware hallucination analysis for improving the reliability of LLM-assisted bug report summarization in software maintenance workflows.

cs.SE↗

arXiv2026

What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook

AI agents are increasingly framed as software-engineering teammates, yet most studies examine them inside human-centered workflows. Little is known about the discourse autonomous AI agents produce when they interact mainly with one another. This paper examines what autonomous agents discuss on MoltBook, how that discourse is organized, and how it differs from human developer discourse. We combine human open coding of a 500-post sample, a concentration-plus-check topic-analysis pipeline over 4,707 English-filtered MoltBook technology posts, and a matched comparison with 5,211 human-generated GitHub Discussions posts. MoltBook technology discourse spans 12 recurring themes, led by Security and Trust (27.4%). At the community level, activity is highly concentrated: the largest submolt accounts for 63.5% of posts (Gini = 0.88), yet a stability-aware BERTopic pipeline still identifies 32 non-outlier sub-topics. Relative to the GitHub Discussions baseline, MoltBook discourse contains fewer concrete, context-rich cues such as code-formatted artifacts, environment details, runtime failures, and reproduction steps. Social mimicry appears only in limited form, while idealization is reflected mainly through lower hedging. Overall, AI-only technical discourse is coherent but selective. It repeatedly returns to security and trust, memory and context management, tooling and APIs, debugging and error handling, workflow automation, and infrastructure/ops, while omitting much of the project-local and runtime detail common in human developer discourse. This may reflect fewer environment-specific failures, reproduction steps, and other grounding cues in MoltBook.

cs.SE↗

arXiv2026

Do Masked Autoencoders Improve Downhole Prediction? An Empirical Study on Real Well Drilling Data

Downhole drilling telemetry presents a fundamental labeling asymmetry: surface sensor data are generated continuously at 1~Hz, while labeled downhole measurements are costly, intermittent, and scarce. Current machine learning approaches for downhole metric prediction universally adopt fully supervised training from scratch, which is poorly suited to this data regime. We present the first empirical evaluation of masked autoencoder (MAE) pretraining for downhole drilling metric prediction. Using two publicly available Utah FORGE geothermal wells comprising approximately 3.5 million timesteps of multivariate drilling telemetry, we conduct a systematic full-factorial design space search across 72 MAE configurations and compare them against supervised LSTM and GRU baselines on the task of predicting Total Mud Volume. Results show that the best MAE configuration reduces test mean absolute error by 19.8\% relative to the supervised GRU baseline, while trailing the supervised LSTM baseline by 6.4\%. Analysis of design dimensions reveals that latent space width is the dominant architectural choice (Pearson $r = -0.59$ with test MAE), while masking ratio has negligible effect, an unexpected finding attributed to high temporal redundancy in 1~Hz drilling data. These results establish MAE pretraining as a viable paradigm for drilling analytics and identify the conditions under which it is most beneficial.

cs.LG↗

arXiv2026

Exploring Ethical Concerns of Mobile Applications from App Reviews: A Literature Survey

Privacy, security, and accessibility, like ethical concerns in mobile applications (a.k.a. apps), commonly subsumed under non-functional requirements, are generally reported by users through app reviews available in app stores. However, these remain unidentified among other types of reviews, such as user experiences, problem reports, and new feature discussions. Over the past decade, extensive research has focused on extracting valuable information from app reviews, including feature requests and bug reports. However, there remains a lack of a synthesis of research related to app review analysis for exploring users' ethical concerns. This paper presents a comprehensive survey of this research area, covering 37 relevant studies published since 2012, identified from the initial 553 studies using specific inclusion and exclusion criteria. The studies examined vary in review counts, ranging from 500 to 626 million, and include between a single and 1.3 million apps. Our detailed analysis highlights diverse objectives, methodologies, and strategies, along with additional resources such as app privacy policies, which researchers generally utilize to analyze ethical concerns. Our findings also identify persistent barriers to privacy, security, accessibility, transparency, fairness, accountability, and safety, as reported by users in app reviews. Furthermore, we propose a research agenda that focuses on four key areas, including automated extraction and classification of ethical concerns-related app reviews. Our survey outcomes can assist developers and system architects in recognizing and prioritizing non-functional requirements at the initial stages of the development lifecycle, whereas researchers can expand upon this synthesis to create tools for the automated detection of ethical concerns.

cs.SE↗

arXiv2026

Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data

Oil and gas drilling operations generate extensive time-series data from surface sensors, yet accurate real-time prediction of critical downhole metrics remains challenging due to the scarcity of labelled downhole measurements. This systematic mapping study reviews thirteen papers published between 2015 and 2025 to assess the potential of Masked Autoencoder Foundation Models (MAEFMs) for predicting downhole metrics from surface drilling data. The review identifies eight commonly collected surface metrics and seven target downhole metrics. Current approaches predominantly employ neural network architectures such as artificial neural networks (ANNs) and long short-term memory (LSTM) networks, yet no studies have explored MAEFMs despite their demonstrated effectiveness in time-series modeling. MAEFMs offer distinct advantages through self-supervised pre-training on abundant unlabeled data, enabling multi-task prediction and improved generalization across wells. This research establishes that MAEFMs represent a technically feasible but unexplored opportunity for drilling analytics, recommending future empirical validation of their performance against existing models and exploration of their broader applicability in oil and gas operations.

cs.LG↗

arXiv2026

Towards Energy-aware Requirements Dependency Classification: Knowledge-Graph vs. Vector-Retrieval Augmented Inference with SLMs

The continuous evolution of system specifications necessitates frequent evaluation of conflicting requirements, a process that is traditionally labour intensive. Although large language models (LLMs) have demonstrated significant potential for automating this detection, their massive computational requirements often result in excessive energy waste. Consequently, there is a growing need to transition toward Small Language Models (SLMs) and energy aware architectures for sustainable Requirements Engineering. This study proposes and empirically evaluates an energy aware framework that compares Knowledge Graph-based Retrieval (KGR) with Vector-based Semantic Retrieval (VSR) to enhance SLM-based inference at the 7B to 8B parameter scale. By leveraging structured graph traversal and high dimensional semantic mapping, we extract candidate requirements, which are then classified as conflicting or neutral by an inference engine. We evaluate these retrieval enhanced strategies across Zero-Shot, Few-Shot, and Chain of Thoughts prompting methods. Using a three-pillar sustainability framework measuring energy consumption (Wh), latency (s), and carbon emissions (gCO2eq) alongside standard accuracy metrics (F1 Score), this research provides a first systematic empirical evaluation and trade off analysis between predictive performance and environmental impact. Our findings highlight the effectiveness of structured versus semantic retrieval in detecting requirement conflicts, offering a reproducible, sustainability aware architecture for energy efficient requirement engineering.

cs.SE↗

arXiv2025

Automatic Classification of User Requirements from Online Feedback -- A Replication Study

Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field to support tasks such as classification and ambiguity detection. Although RE research is rooted in empirical investigation, it has paid limited attention to replicating NLP for RE (NLP4RE) studies. The rapidly advancing realm of NLP is creating new opportunities for efficient, machine-assisted workflows, which can bring new perspectives and results to the forefront. Thus, we replicate and extend a previous NLP4RE study (baseline), "Classifying User Requirements from Online Feedback in Small Dataset Environments using Deep Learning", which evaluated different deep learning models for requirement classification from user reviews. We reproduced the original results using publicly released source code, thereby helping to strengthen the external validity of the baseline study. We then extended the setup by evaluating model performance on an external dataset and comparing results to a GPT-4o zero-shot classifier. Furthermore, we prepared the replication study ID-card for the baseline study, important for evaluating replication readiness. Results showed diverse reproducibility levels across different models, with Naive Bayes demonstrating perfect reproducibility. In contrast, BERT and other models showed mixed results. Our findings revealed that baseline deep learning models, BERT and ELMo, exhibited good generalization capabilities on an external dataset, and GPT-4o showed performance comparable to traditional baseline machine learning models. Additionally, our assessment confirmed the baseline study's replication readiness; however missing environment setup files would have further enhanced readiness. We include this missing information in our replication package and provide the replication study ID-card for our study to further encourage and support the replication of our study.

cs.CL↗

arXiv2025

Enhancing and Accelerating Brain MRI through Deep Learning Reconstruction Using Prior Subject-Specific Imaging

Magnetic resonance imaging (MRI) is a crucial medical imaging modality. However, long acquisition times remain a significant challenge, leading to increased costs, and reduced patient comfort. Recent studies have shown the potential of using deep learning models that incorporate information from prior subject-specific MRI scans to improve reconstruction quality of present scans. Integrating this prior information requires registration of the previous scan to the current image reconstruction, which can be time-consuming. We propose a novel deep-learning-based MRI reconstruction framework which consists of an initial reconstruction network, a deep registration model, and a transformer-based enhancement network. We validated our method on a longitudinal dataset of T1-weighted MRI scans with 2,808 images from 18 subjects at four acceleration factors (R5, R10, R15, R20). Quantitative metrics confirmed our approach's superiority over existing methods (p < 0.05, Wilcoxon signed-rank test). Furthermore, we analyzed the impact of our MRI reconstruction method on the downstream task of brain segmentation and observed improved accuracy and volumetric agreement with reference segmentations. Our approach also achieved a substantial reduction in total reconstruction time compared to methods that use traditional registration algorithms, making it more suitable for real-time clinical applications. The code associated with this work is publicly available at https://github.com/amirshamaei/longitudinal-mri-deep-recon.

cs.CV↗

arXiv2025

Towards Extracting Software Requirements from App Reviews using Seq2seq Framework

Mobile app reviews are a large-scale data source for software improvements. A key task in this context is effectively extracting requirements from app reviews to analyze the users' needs and support the software's evolution. Recent studies show that existing methods fail at this task since app reviews usually contain informal language, grammatical and spelling errors, and a large amount of irrelevant information that might not have direct practical value for developers. To address this, we propose a novel reformulation of requirements extraction as a Named Entity Recognition (NER) task based on the sequence-to-sequence (Seq2seq) generation approach. With this aim, we propose a Seq2seq framework, incorporating a BiLSTM encoder and an LSTM decoder, enhanced with a self-attention mechanism, GloVe embeddings, and a CRF model. We evaluated our framework on two datasets: a manually annotated set of 1,000 reviews (Dataset 1) and a crowdsourced set of 23,816 reviews (Dataset 2). The quantitative evaluation of our framework showed that it outperformed existing state-of-the-art methods with an F1 score of 0.96 on Dataset 2, and achieved comparable performance on Dataset 1 with an F1 score of 0.47.

cs.SE↗

arXiv2025

CMER: A Context-Aware Approach for Mining Ethical Concern-related App Reviews

With the increasing proliferation of mobile applications in our daily lives, the concerns surrounding ethics have surged significantly. Users communicate their feedback in app reviews, frequently emphasizing ethical concerns, such as privacy and security. Incorporating these reviews has proved to be useful for many areas of software engineering (e.g., requirement engineering, testing, etc.). However, app reviews related to ethical concerns generally use domain-specific language and are typically overshadowed by more generic categories of user feedback, such as app reliability and usability. Thus, making automated extraction a challenging and time-consuming effort. This study proposes CMER (A \underline{C}ontext-Aware Approach for \underline{M}ining \underline{E}thical Concern-related App \underline{R}eviews), a novel approach that combines Natural Language Inference (NLI) and a decoder-only (LLaMA-like) Large Language Model (LLM) to extract ethical concern-related app reviews at scale. In CMER, NLI provides domain-specific context awareness by using domain-specific hypotheses, and the Llama-like LLM eliminates the need for labeled data in the classification task. We evaluated the validity of CMER by mining privacy and security-related reviews (PSRs) from the dataset of more than 382K app reviews of mobile investment apps. First, we evaluated four NLI models and compared the results of domain-specific hypotheses with generic hypotheses. Next, we evaluated three LLMs for the classification task. Finally, we combined the best NLI and LLM models (CMER) and extracted 2,178 additional PSRs overlooked by the previous study using a keyword-based approach, thus demonstrating the effectiveness of CMER. These reviews can be further refined into actionable requirement artifacts.

cs.SE↗

arXiv2025

SAGE: A Context-Aware Approach for Mining Privacy Requirements Relevant Reviews from Mental Health Apps

Mental health (MH) apps often require sensitive user data to customize services for mental wellness needs. However, such data collection practices in some MH apps raise significant privacy concerns for users. These concerns are often mentioned in app reviews, but other feedback categories, such as reliability and usability, tend to take precedence. This poses a significant challenge in automatically identifying privacy requirements-relevant reviews (privacy reviews) that can be utilized to extract privacy requirements and address users' privacy concerns. Thus, this study introduces SAGE, a context-aware approach to automatically mining privacy reviews from MH apps using Natural Language Inference (NLI) with MH domain-specific privacy hypotheses (provides domain-specific context awareness) and a GPT model (eliminates the need for fine-tuning). The quantitative evaluation of SAGE on a dataset of 204K app reviews achieved an F1 score of 0.85 without any fine-tuning, outperforming the fine-tuned baseline classifiers BERT and T5. Furthermore, SAGE extracted 748 privacy reviews previously overlooked by keyword-based methods, demonstrating its effectiveness through qualitative evaluation. These reviews can later be refined into actionable privacy requirement artifacts.

cs.SE↗

arXiv2025

Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation

Bug reports contain the information developers need to triage and fix software bugs. However, unclear, incomplete, or ambiguous information may lead to delays and excessive manual effort spent on bug triage and resolution. In this paper, we explore whether Instruction fine-tuned Large Language Models (LLMs) can automatically transform casual, unstructured bug reports into high-quality, structured bug reports adhering to a standard template. We evaluate three open-source instruction-tuned LLMs (\emph{Qwen 2.5, Mistral, and Llama 3.2}) against ChatGPT-4o, measuring performance on established metrics such as CTQRS, ROUGE, METEOR, and SBERT. Our experiments show that fine-tuned Qwen 2.5 achieves a CTQRS score of \textbf{77%}, outperforming both fine-tuned Mistral (\textbf{71%}), Llama 3.2 (\textbf{63%}) and ChatGPT in 3-shot learning (\textbf{75%}). Further analysis reveals that Llama 3.2 shows higher accuracy of detecting missing fields particularly Expected Behavior and Actual Behavior, while Qwen 2.5 demonstrates superior performance in capturing Steps-to-Reproduce, with an F1 score of 76%. Additional testing of the models on other popular projects (e.g., Eclipse, GCC) demonstrates that our approach generalizes well, achieving up to \textbf{70%} CTQRS in unseen projects' bug reports. These findings highlight the potential of instruction fine-tuning in automating structured bug report generation, reducing manual effort for developers and streamlining the software maintenance process.

cs.SE↗

arXiv2025

BugsRepo: A Comprehensive Curated Dataset of Bug Reports, Comments and Contributors Information from Bugzilla

Bug reports help software development teams enhance software quality, yet their utility is often compromised by unclear or incomplete information. This issue not only hinders developers' ability to quickly understand and resolve bugs but also poses significant challenges for various software maintenance prediction systems, such as bug triaging, severity prediction, and bug report summarization. To address this issue, we introduce \textnormal{{\fontfamily{ppl}\selectfont BugsRepo}}, a multifaceted dataset derived from Mozilla projects that offers three key components to support a wide range of software maintenance tasks. First, it includes a Bug report meta-data & Comments dataset with detailed records for 119,585 fixed or closed and resolved bug reports, capturing fields like severity, creation time, status, and resolution to provide rich contextual insights. Second, {\fontfamily{ppl}\selectfont BugsRepo} features a contributor information dataset comprising 19,351 Mozilla community members, enriched with metadata on user roles, activity history, and contribution metrics such as the number of bugs filed, comments made, and patches reviewed, thus offering valuable information for tasks like developer recommendation. Lastly, the dataset provides a structured bug report subset of 10,351 well-structured bug reports, complete with steps to reproduce, actual behavior, and expected behavior. After this initial filter, a secondary filtering layer is applied using the CTQRS scale. By integrating static metadata, contributor statistics, and detailed comment threads, {\fontfamily{ppl}\selectfont BugsRepo} presents a holistic view of each bug's history, supporting advancements in automated bug report analysis, which can enhance the efficiency and effectiveness of software maintenance processes.

cs.SE↗

arXiv2024

"So what if I used GenAI?" -- Implications of Using Cloud-based GenAI in Software Engineering Research

Generative Artificial Intelligence (GenAI) advances have led to new technologies capable of generating high-quality code, natural language, and images. The next step is to integrate GenAI technology into various aspects while conducting research or other related areas, a task typically conducted by researchers. Such research outcomes always come with a certain risk of liability. This paper sheds light on the various research aspects in which GenAI is used, thus raising awareness of its legal implications to novice and budding researchers. In particular, there are two risks: data protection and copyright. Both aspects are crucial for GenAI. We summarize key aspects regarding our current knowledge that every software researcher involved in using GenAI should be aware of to avoid critical mistakes that may expose them to liability claims and propose a checklist to guide such awareness.

cs.SE↗

arXiv2024

Beyond Keywords: A Context-based Hybrid Approach to Mining Ethical Concern-related App Reviews

With the increasing proliferation of mobile applications in our everyday experiences, the concerns surrounding ethics have surged significantly. Users generally communicate their feedback, report issues, and suggest new functionalities in application (app) reviews, frequently emphasizing safety, privacy, and accountability concerns. Incorporating these reviews is essential to developing successful products. However, app reviews related to ethical concerns generally use domain-specific language and are expressed using a more varied vocabulary. Thus making automated ethical concern-related app review extraction a challenging and time-consuming effort. This study proposes a novel Natural Language Processing (NLP) based approach that combines Natural Language Inference (NLI), which provides a deep comprehension of language nuances, and a decoder-only (LLaMA-like) Large Language Model (LLM) to extract ethical concern-related app reviews at scale. Utilizing 43,647 app reviews from the mental health domain, the proposed methodology 1) Evaluates four NLI models to extract potential privacy reviews and compares the results of domain-specific privacy hypotheses with generic privacy hypotheses; 2) Evaluates four LLMs for classifying app reviews to privacy concerns; and 3) Uses the best NLI and LLM models further to extract new privacy reviews from the dataset. Results show that the DeBERTa-v3-base-mnli-fever-anli NLI model with domain-specific hypotheses yields the best performance, and Llama3.1-8B-Instruct LLM performs best in the classification of app reviews. Then, using NLI+LLM, an additional 1,008 new privacy-related reviews were extracted that were not identified through the keyword-based approach in previous research, thus demonstrating the effectiveness of the proposed approach.

cs.CL↗

arXiv2024

Ethical software requirements from user reviews: A systematic literature review

Context: The growing focus on ethics within SE, primarily due to the significant reliance of individuals' lives on software and the consequential social and ethical considerations that impact both people and society has brought focus on ethical software requirements identification and elicitation. User safety, privacy, and security concerns are of prime importance while developing software due to the widespread use of software across healthcare, education, and business domains. Thus, identifying and elicitating ethical software requirements from app user reviews, focusing on various aspects such as privacy, security, accountability, accessibility, transparency, fairness, safety, and social solidarity, are essential for developing trustworthy software solutions. Objective: This SLR aims to identify and analyze existing ethical requirements identification and elicitation techniques in the context of the formulated research questions. Method: We conducted an SLR based on Kitchenham et al's methodology. We identified and selected 47 primary articles for this study based on a predefined search protocol. Result: Ethical requirements gathering has recently driven drastic interest in the research community due to the rise of ML and AI-based approaches in decision-making within software applications. This SLR provides an overview of ethical requirements identification techniques and the implications of extracting and addressing them. This study also reports the data sources used for analyzing user reviews. Conclusion: This SLR provides an understanding of the ethical software requirements and underscores the importance of user reviews in developing trustworthy software. The findings can also help inform future research and guide software engineers or researchers in addressing software ethical requirements.

cs.SE↗

arXiv2024

Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems

Artificial Intelligence (AI) has paved the way for revolutionary decision-making processes, which if harnessed appropriately, can contribute to advancements in various sectors, from healthcare to economics. However, its black box nature presents significant ethical challenges related to bias and transparency. AI applications are hugely impacted by biases, presenting inconsistent and unreliable findings, leading to significant costs and consequences, highlighting and perpetuating inequalities and unequal access to resources. Hence, developing safe, reliable, ethical, and Trustworthy AI systems is essential. Our team of researchers working with Trustworthy and Responsible AI, part of the Transdisciplinary Scholarship Initiative within the University of Calgary, conducts research on Trustworthy and Responsible AI, including fairness, bias mitigation, reproducibility, generalization, interpretability, and authenticity. In this paper, we review and discuss the intricacies of AI biases, definitions, methods of detection and mitigation, and metrics for evaluating bias. We also discuss open challenges with regard to the trustworthiness and widespread application of AI across diverse domains of human-centric decision making, as well as guidelines to foster Responsible and Trustworthy AI models.

cs.AI↗