Digital Commons Network^™

Metarag: Identifying Website Owner Using Meta-Path-Guided Dynamic Graph Retrieval-Augmented Generation, Cheng Tu, Yunshan Ma, Bingyang Guo, Qianyu Li, Yang Li, Min Zhang, Fan Shi, Xiang Wang

Research Collection School Of Computing and Information Systems

Website owner identification aims to link websites to their real-world owners, which is crucial for credibility assessment and information provenance in information retrieval and vital for applications in cybersecurity, Internet governance, and digital regulation. Existing approaches for website owner identification primarily rely on querying infrastructure registration records or analyzing webpage content. However, these methods often fail due to incomplete or outdated registration records and sparse webpage content. We observe that inter-website relationships, derived from shared infrastructure data such as primary domains, IP blocks, and geolocations, can provide valuable but underutilized ownership cues. To exploit this insight, we propose MetaRAG, a …

Artificial Intelligence And Translation: Exploring Current Applications, Limitations And Future Potential Of Language Models Through Japanese-English Translation, Loklin Elias Nord

Undergraduate Theses, Capstones, and Recitals

This thesis highlights the recent improvements and capabilities of Large Language Models (LLMs), specifically their ability to produce translations between different languages. The continued up-scaling of model sizes has led to breakthroughs in the level of their observed intelligence, allowing them to produce translations that are similar in quality to highly skilled human translators. However, to facilitate the reasoning processes that LLMs now possess, their demand for computational power and the supporting hardware and resources has increased proportionally. Considering the impacts of this technology on the environment, energy resources, and its accessibility, my research explores the possibilities of smaller, highly …

Ai Failures In The Eyes Of The Downstream Developer: A First Look At Concerns, Practices, And Challenges, Haoyu Gao, Mansooreh Zahedi, Wenxin Jiang, Hong Yi Lin, James C. Davis, Christoph Treude

Research Collection School Of Computing and Information Systems

With the advancement of AI models, more software systems are adopting AI as a component to facilitate automation. Pre-trained models (PTMs) have become a cornerstone of AI-based software, allowing for rapid integration and development with lower training cost. However, their adoption also introduces failure modes such as data leakage and biased outputs, that may require careful handling by downstream developers. While previous research has proposed taxonomies of these technical concerns and various mitigation strategies, how downstream developers address these issues during the development of general AI-based software when reusing PTMs remains unexplored. Understanding downstream developers’ perspectives is essential because they …

Logupdater: Automated Detection And Repair Of Specific Defects In Logging Statements, Renyi Zhong, Yichen Li, Jinxi Kuang, Wenwei Gu, Yintong Huo, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Developers write logging statements to monitor software runtime behaviors and system state. However, poorly constructed or misleading log messages can inadvertently obfuscate actual program execution patterns, thereby impeding effective software maintenance. Existing research on analyzing issues within logging statements is limited, primarily focusing on detecting a singular type of defect and relying on manual intervention for fixes rather than automated solutions.To address the limitation, we initiate a systematic study that pinpoints four specific types of defects in logging statements (i.e., statement code inconsistency, static dynamic inconsistency, temporal relation inconsistency, and readability issues) through the analysis of real-world log-centric changes. We …

Long Range Battery-Free Wireless Power Transfer Testbed For Underground Mines Iot And Lpwan Devices, Anabi Hilary Kelechi, Samuel Frimpong, Sanjay Madria

Mining Engineering Faculty Research & Creative Works

Underground mines are susceptible to occasional roof falls and cave-ins, temporarily destroying the existing wireless communications and telemetry infrastructure. During this temporary outage, intermittent provision of electrical energy wirelessly to the already deployed low-power wireless area networks (LPWAN) and Internet of Things (IoT) devices assumes a fundamental requirement. In this article, we propose and design a long-range far-field radio frequency (RF) wireless power transfer (WPT) testbed to power LPWAN and IoT devices at 35 m in an underground mines facility. Class AB external power amplifier (PA) was introduced to achieve a long-distance RF WPT, in the 880 MHz band. Thus, …

Smart Medical System Integrating Clinical Workflows For Robust Skin Cancer Detection Across Heterogeneous Pathologies, Ahed Abugabah, Prashant Kumar Shukla, Suchi Mishra, Abhishek Dwivedi

All Works

Skin cancer is among the most prevalent and life-threatening dermatological diseases worldwide, with melanoma responsible for a substantial proportion of skin cancer–related deaths due to delayed and unreliable diagnosis. Conventional clinical screening based on visual inspection and expert interpretation is inherently subjective and often affected by inter-observer variability, lesion heterogeneity, and imaging artifacts, highlighting the need for accurate and generalizable automated diagnostic systems. This study proposes a novel hybrid deep learning architecture for skin cancer classification that integrates an attention-guided autoencoder with a transformer-inspired global context modeling module, forming a unified and robust representation learning framework. The encoder–decoder structure is …

A Deep Learning Ensemble Framework For Multi-Subtype Renal Tumor Classification Using Contrast-Enhanced Ct, Hisham Abdeltawab, Ahmed Alksas, Mohamed Ghazal, Ashraf Khalil, Norah Saleh Alghamdi, Rasha T. Abouelkheir, Ahmed Elmahdy, Mohamed Abou El-Ghar, Sohail Contractor, Ayman El–Baz

All Works

Renal cell carcinoma (RCC) is considered the most aggressive and common form of renal cancer. Therefore, early detection is crucial to ensure appropriate and effective treatment planning. In our study, we propose a novel computer-aided diagnostic (CAD) approach which incorporates a deep learning ensemble to differentiate between five renal tumor subtypes, utilising the modality of contrast-enhanced computed tomography (CE-CT). The addressed renal lesions are malignant tumors (chromophobe RCC (chRCC), papillary RCC (pRCC), and clear cell RCC (ccRCC)) and benign tumors (renal oncocytoma (RO) and angiomyolipoma (AML)). Our study includes 280 patients who underwent renal biopsy, 112 patients were diagnosed with …

An Advanced Healthcare System With An Automated Vit Model For Dermoscopic Skin Cancer Identification, Ahed Abugabah, Prashant Kumar Shukla, Suchi Mishra, Abhishek Dwivedi

All Works

Early and reliable diagnosis of skin cancer from dermoscopic images remains challenging due to class imbalance, subtle inter-class variations, lesion boundary ambiguity, and illumination inconsistency, which can degrade the robustness of conventional convolutional neural networks (CNNs). To address these limitations, this study proposes an automated smart healthcare framework for dermoscopic skin cancer diagnosis using an Enhanced Vision Transformer (E-ViT) that improves global-context modeling through self-attention while strengthening fine-grained lesion representation learning. Unlike standard ViT configurations, the proposed architecture integrates multi-scale patch embedding and attention refinement to better capture border irregularities and color–texture heterogeneity that are critical for melanoma discrimination. Furthermore, …

Generative Ai Adoption And Solvers' Popularity On Supply-Driven Crowdsourcing Platforms: The Dual Role Of Price Signals, Zimeng Zhu, Carol Hsu, Fiona Fui-Hoon Nah, Na Liu

Research Collection School Of Computing and Information Systems

Purpose – We investigate the effect of solvers’ adoption of Generative AI (GenAI) on their popularity in a supply-driven crowdsourcing platform. We also examine the impact of price signals as well as their heterogeneous impact based on the solvers’ membership duration on the platform. Design/methodology/approach – Our analysis focuses on solvers who adopt GenAI for design-related gigs on the supply-driven crowdsourcing platform. By combining propensity score matching (PSM) with multi-period difference-in-differences (DID), we examine how GenAI adoption impacts solvers’ popularity and how price signals affect this main effect. Findings – Our findings reveal that solvers who adopt GenAI tend to …

Suicide Ideation Detection Using Social Media Data And Ensemble Machine Learning Model, Erol Kina, Jin Ghoo Choi, Abid Ishaq, Rahman Shafique, Monica Gracia Villar, Eduardo Silva Alvarado, Isabel De La Torre Diez, Imran Ashraf

Research outputs 2022 to 2026

Identifying the emotional state of individuals has useful applications, particularly to reduce the risk of suicide. Users’ thoughts on social media platforms can be used to find cues on the emotional state of individuals. Clinical approaches to suicide ideation detection primarily rely on evaluation by psychologists, medical experts, etc., which is time-consuming and requires medical expertise. Machine learning approaches have shown potential in automating suicide detection. In this regard, this study presents a soft voting ensemble model (SVEM) by leveraging random forest, logistic regression, and stochastic gradient descent classifiers using soft voting. In addition, for the robust training of SVEM, …

Machine Learning-Based Regression For Magnetic Field Prediction From Odmr Spectral Data, Jesse B. Hernandez

Electronic Theses, Projects, and Dissertations

Optically Detected Magnetic Resonance (ODMR) using nitrogen-vacancy (NV) centers in diamond enables sensitive, room-temperature magnetic field sensing, but real ODMR spectra are often noisy and difficult to analyze with traditional peak-fitting methods. This thesis investigates whether machine learning can reliably predict magnetic field strength directly from ODMR spectra, and compares four model families under a single regression task: a random forest, an artificial neural network (ANN), a one-dimensional convolutional neural network (1D-CNN), and a Transformer.

Training data were generated from an NV-ensemble simulation calibrated to real measurements provided by the Ulsan National Institute of Science and Technology (UNIST), spanning 0 …

A Systematic Review Of Audio Deepfake Detection Techniques For Digital Investigation, Mahra Alnaqbi, Richard Adeyemi Ikuesan

All Works

Deepfake technology has been driven by advanced machine learning and revolutionized multimedia creation by synthesizing hyper-realistic content. It includes images, videos, and audio. While its creative applications in entertainment and accessibility are significant, the technology also poses critical risks, especially in fraud, disinformation, and identity theft. Audio deepfakes are a subset of this phenomenon that replicate human voices with enhanced precision, mimicking tone, accent, and subtle vocal nuances. This has raised concerns in security-sensitive domains like voice authentication and forensic investigations. This systematic literature review (SLR) adopts PRISMA guidelines to explore the state-of-the-art in audio deepfake detection. It examines existing …

A Performance-Optimized V2v Task Offloading Framework For Real-Time Vehicular Communication, Tariq Qayyum, Asadullah Tariq, Ikbal Taleb, Mohamed Adel Serhani, Zouheir Trabelsi

All Works

As vehicular applications become increasingly complex, their computational demands often exceed the capabilities of individual vehicles. Vehicular Edge Computing (VEC) alleviates this limitation by enabling task delegation to nearby edge resources; however, high mobility, dynamic topology, and fluctuating vehicle density make real-time offloading decisions challenging. To address these issues, we propose a performance-optimized Vehicle-to-Vehicle (V2V) task offloading framework for dense and dynamic Vehicular Ad-hoc Networks (VANETs). The framework follows a two-stage design: (i) context-aware edge-node selection based on live topology capture via periodic beaconing, and (ii) cumulative score-based dynamic priority queuing at the selected edge node. The priority score jointly …

Fig-Gan: Fundus Image Generation Via Deep Learning Based Generative Adversarial Network For Amd Disease Diagnosis, Kailasa Thrishul, Ahed Abugabah, Amina Salhi, Manel Ayadi, Mohamed M. Sithik, D. Jayaprakash, A. Ahilan

All Works

Globally, age-related macular degeneration (AMD) remains a main cause of irreversible vision loss. Recently, deep learning models have primarily focused on classifying fundus images for early detection of AMD progression. However, existing models rarely address the generation of future progression-aware fundus images, particularly when complete real longitudinal follow-up scans are unavailable. This limitation makes it difficult to track retinal changes over time and highlights the need for generative models capable of producing realistic drusen-level structural variations. To address these issues, a novel deep learning-based FIG-GAN model is to generate synthetic future fundus images from baseline inputs. Multi-Attention U-Net (MAU-Net) is …

Extending Geometric Acoustic Ray Tracing To Multi-Room Environments: A Case Study On Gunshot Sound Transmission Between Adjacent Rooms, Tyler Ton

Theses and Dissertations

Accurate localization of gunshots in multi-room building environments remains a challenging problem in acoustic forensics and public safety applications. Existing approaches model sound propagation within a single room, neglecting the transmission of acoustic energy through walls and other building materials. This thesis presents a study on modeling multi-room gunshot acoustic transmission, combining geometric ray tracing with structural acoustic transmission-loss modeling to generate impulse responses for two horizontally adjacent rooms separated by a shared wall, providing a foundation for future inter-room gunshot localization work. The proposed system uses GSound-SIR, a geometric acoustics engine, to simulate sound propagation in both of the …

Analyzing Developer Discussions On Eu And Us Privacy Legislation Compliance In Github Repositories, Georgia M. Kapitsaki, Maria Papoutsoglou, Christoph Treude, Ioanna Theophilou

Research Collection School Of Computing and Information Systems

Context: Privacy legislation has impacted the way software systems are developed, prompting practitioners to update their implementations. Specifically, the EU General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) have forced the community to focus on users’ data privacy. Objectives: Relying on the vast amount of data on developer issues available in GitHub repositories, our aim is to gather empirical evidence on the issues developers of Open Source Software discuss to comply with privacy legislation. Method: We examined such discussions by mining and analyzing 32,820 issues from GitHub repositories. We partially analyzed the dataset automatically to identify …

Semantic-Structural Decoupling: Disentangling Semantic Attention From Structural Bias In The Attention Manifold, Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disproportionate attention toward certain semantically uninformative visual tokens, a phenomenon termed "register" or "Visual Attention Sinks." While existing inference intervention methods attempt to identify these sink tokens and redistribute their attention weights, such approaches typically treat these tokens in isolation and suffer from computational inefficiency. Instead, we reframe this phenomenon as a generalized textual bias exerted over visual features that extends beyond isolated sink tokens. From this perspective, a pervasive structural bias leads to the dilution of the …

Spatialimaginer: Towards Adaptive Visual Imagination For Spatial Reasoning, Yian Li, Yang Jiao, Bin Zhu, Tianwen Qian, Shaoxiang Chen, Jingjing Chen, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs. Effective spatial reasoning requires low-level geometric structure to be faithfully preserved and updated throughout the reasoning process, whereas textual representations tend to abstract away precisely these critical details. …

Tiny Large Language Models For Iot Networks: Potentials And Challenges, Muhammed Golec, Suhib Bani Melhem, Yaser Khamayseh, Abdulmalik Alwarafy, Naofal Al-Dhahir

All Works

Large Language Models (LLM), which have gained great momentum in recent years, have revolutionized the field of Artificial Intelligence (AI); while their applicability for hardware-constrained Internet of Things (IoT) environments has begun to be questioned. This has led to the emergence of compact architecture and resource-efficient Tiny LLM models. This survey paper systematically examines Tiny LLMs for IoT networks and classifies existing approaches in five basic dimensions: model architectures, optimization strategies, transfer learning methods, deployment paradigms, and explainability-security integration. By applying the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method, 139 related studies published between 2020 and 2025 …

Climate Transition Stress Testing For Corporate Credit Risk: A Replicable Data-Mining Pipeline Using Esg Risk Scores, Huynh Long Hung Nguyen, Alan @ Ali Madjelisi Megargel, Rajesh Krishna Balan, Paul Robert Griffin

Research Collection School Of Computing and Information Systems

We present a replicable data-mining pipeline for illustrative, scenario-conditioned corporate distress analysis under feature decoupling. The pipeline links Compustat financial statements with Sustainalytics ESG Risk Rating records for 2,144 U.S. non-financial public firms, constructs a standardized Transition Risk Index (TRI), estimates a contemporaneous accounting-distress classifier, and applies transparent transition-cost sensitivities. Distress is defined as annual operating income insufficient to cover annual interest expense; interest coverage itself is excluded from the predictors. The resulting model is not a forward default forecast or a regulatory probability-of-default model. On a held-out cross-sectional test set, the logistic specification obtains AUC 0.909, PR-AUC 0.822, and …

Stewards Of Data: A Practical Handbook For Undergraduate Researchers In Engineering And Applied Sciences, Şenay Purzer, Wei Zakharov, Carla B. Zoltowski

Purdue University Press Books

Filled with actionable guides and real-world examples, Stewards of Data: A Practical Handbook for Undergraduate Researchers in Engineering and Applied Sciences allows readers to utilize the provided templates and guides almost immediately. In today’s world, data is ubiquitous and AI is growing exponentially. Practicing ethical data management is, therefore, crucial. Ensuring that data is findable, accessible, interoperable, and reusable is essential. This book is an interdisciplinary effort aimed at embedding ethical data life-cycle management education into undergraduate research. The authors present a Data Steward Framework, which serves as a guide for undergraduate researchers, the graduate students who mentor them, postdocs, …

Specification And Internal Assessment Of A Self Reported Protective Application Use Composite Among Computer Science Undergraduates In Enugu State Nigeria, Adesegun Nurudeen Osijirin, Leonard C. Anigbo, Oliver Okechukwu

Journal of Cybersecurity Education, Research and Practice

This study specifies a Protective Application Use Composite restricted to self-reported protective application use. A cross-sectional survey provided 364 complete records from Computer Science undergraduates at four universities in Enugu State, Nigeria, from 393 distributed questionnaires. The score is the equal-weight average of five questionnaire categories: antivirus, firewall, encryption, multi-factor authentication, and virtual private network use. Reanalysis of the author-supplied item records yielded category means from 2.097 to 2.376 and internal-consistency coefficients from 0.958 to 0.971. The composite mean was 2.170, with a standard deviation of 0.469. The first component of the category-score correlation matrix explained 50.98 percent of variance. …

A Narrative-Driven, Socratic Instructional Framework For Teaching Adversarial Cognition In Cybersecurity, Joshua K. Goossen

Journal of Cybersecurity Education, Research and Practice

The Socratic method has demonstrated, in studies across law, medicine, and nursing, that dialectic structured questioning improves expert reasoning. Cybersecurity currently teaches tools and techniques but lacks Socratic dialogic leaving graduates underprepared for novel scenarios requiring cross-domain reasoning. Because law, medicine and nursing cultivate similar reasoning as security there is principled reason to expect reasoning benefits could transfer to security students. This paper argues that the correspondence warrants investigation. Investigation requires a named, teachable reasoning target analogous to clinical reasoning and we specify that target as adversarial cognition, a framework integrating adversary features, system architecture, implementation logic, governance structure, human …

Ai-Generated Phishing Attacks: Emerging Threats And Detection Strategies For Security Operations Centers, Bahzad Khalid

Journal of Cybersecurity Education, Research and Practice

Artificial intelligence (AI) is transforming cybersecurity by strengthening defensive capabilities while simultaneously enabling more sophisticated phishing attacks. AI generated phishing emails increasingly evade traditional detection methods through improved grammar, contextual relevance and realistic communication styles creating significant challenges for Security Operations Centers (SOCs). This study investigates the effectiveness of current email security systems in detecting AI generated phishing emails compared with traditional phishing emails. A mixed method experimental approach was employed using controlled Gmail and Outlook environments to evaluate the detection and classification of multiple phishing scenarios. The results demonstrate that several AI generated phishing emails successfully bypassed initial security …

Integrating Gis With Interim Payment Valuation In Road Construction Projects: A Conceptual Framework, Abdulrahman I. Iro, Juma M. Matindana, Julian Ijumulana

Tanzania Journal of Engineering and Technology (TJET)

Abstract

Interim Payment Valuation is a critical process in road construction contract administration, yet conventional valuation practices remain heavily dependent on manual measurements, fragmented documentation, spreadsheets, and professional judgement. These limitations can affect measurement accuracy, transparency, traceability, and the timeliness of payment certification. Although Geographic Information Systems have increasingly been applied to construction planning, quantity measurement, progress monitoring, infrastructure management, and decision support, their integration with contractual and financial processes for interim payment valuation remains insufficiently explored. This study therefore develops a conceptual framework for integrating GIS with Interim Payment Valuation in road construction projects. A PRISMA-guided structured literature review …

Navigating Text-To-Speech (Tts): Ethical Leadership In The Use Of Generative Ai For Extension, Xue A Dong, Paul A Hill

Journal of Extension

Text-to-speech (TTS) AI technology transforms written content into natural-sounding speech, offering a useful tool to enhance accessibility and inclusivity in Extension work. This article examines the role of TTS AI in bridging communication gaps, particularly for diverse and multilingual communities, and demonstrates the importance of ethical leadership in its adoption. By prioritizing diversity, equity, and inclusion, Extension professionals can leverage TTS AI to foster greater connection and engagement. Practical applications and examples are provided to guide the integration of TTS AI into programs. The article also offers recommendations for experimenting with innovative technologies to improve educational outcomes and increase the …

Interrater Reliability Of Software Optimized Movement Assessment With Traditional Methods And Video-Based Functional Movement Screen Scoring And Compensatory Movement Identification, Joshua Paul Verdillo, Nj Ermina, Tanya Mariel Capilla, Russel James Balane, Evriel Prince Apura, Daryl Reymon Apla-On, Ressyl Love Salvador

Philippine Journal of Physical Therapy

Introduction: The Functional Movement Screen (FMS) is a seven-part movement assessment used to identify injury risks caused by faulty biomechanics. There are three barriers in traditional FMS assessments that could affect the tool’s validity: the subjectivity of human scores that could cause bias, the need for in-person evaluations which limit access for remote patients, and the requirement of specialized training to use the tool, which makes it less accessible. This study investigates the effectiveness of SOMA, an AI-based web application that uses the MediaPipe framework to automatically assess (FMS) performances.

Methods: This study employs a quantitative, cross-sectional, comparative design to …

Voltage-Related Power Quality Issues And Impacts On Distribution Networks With Sensitive Loads - A Review, Godwin Elinazi Mnkeni, Jackson Justo, Aviti Thadei Mushi, Bakari M. M. Mwinyiwiwa

Tanzania Journal of Engineering and Technology (TJET)

Voltage disturbances are the most important power quality (PQ) complications that customers and power utilities face in this smart era. The growing adoption of sophisticated electronic equipment and integration of renewable energy sources (RES) into power grids has increased the susceptibility of power distribution networks (PDNs) to voltage sags, swells, interruptions, flicker, and voltage imbalance. These disturbances, mainly caused by upstream faults, switching operations, and RES integration, compromise voltage PQ and system reliability. Consequently, they accelerate equipment degradation, increase electronic waste (e-waste), raise reactive power demand and maintenance costs, increase power losses, and impose substantial economic losses on customers and …

Mutation-Based Multi-Agent Test Case Update, Dawei Tian, Jiakun Liu, Yun Peng, Yichen Zhang, Jianlei Chi, Jun Sun, Xiaohong Su

Research Collection School Of Computing and Information Systems

Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, causing pipeline disruptions, reduced productivity, and compromised quality. Recent automatic test update approaches leverage LLMs to refine test cases via execution feedback and exact-matching context retrieval, prioritizing executability and line coverage but suffering three limitations: (1) neglecting test assertion adequacy, weakening fault detection; (2) relying on coarse line coverage instead of specific uncovered lines/branches; (3) using exact-matching retrieval, which fails for LLM hallucinated queries. To address these, we propose MuMuTestUp, a mutation-guided multi-agent framework with three …

Ddor: Delta Debugging For Explainable Overrefusal Testing And Repair, Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang, Dongxia Wang

Research Collection School Of Computing and Information Systems

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (Delta Debugging for OverRefusal), a fully automated and explainable framework for overrefusal testing and repair in a black-box setting, where only model inputs and outputs are accessible and internal safety mechanisms remain opaque. DDOR applies delta debugging to localize minimal refusal-triggering fragments (mRTFs) that provide phrase-level, explainable evidence for why a refusal occurs. Conditioned on these mRTFs, DDOR generates diverse, context-rich prompts and performs multi-oracle validation to filter intrinsically …