cs papers | Gist.Science

Zero Trust for IT Governance and Risk Management: A Systematic Review and Conceptual Framework

This study employs a PRISMA 2020 systematic review of 73 peer-reviewed articles to bridge the gap between technical Zero Trust implementations and organizational governance, proposing a conceptual framework that links continuous verification and identity-centric controls to enhanced risk management and strategic IT objectives while highlighting critical gaps in SME adoption and AI-driven automation.

‪nabil almotawkel‬‏, Mohammed Alkohali, Sadeg Manaa, Osamah AL-Maamari, Ashraf Al-Godami, Shaima Alqahoom2026-07-21

💻 computer science

A Hybrid VGG16–PCA–Fuzzy Based Framework for the Classification of Morphologically Similar Maize Pests

This study proposes a hybrid VGG16–PCA–Fuzzy framework that integrates Gaussian membership-based uncertainty modeling to significantly improve the classification accuracy of morphologically similar maize pests, achieving a 97.17% accuracy rate that outperforms standalone VGG16 baselines.

Bonga G Baleni, Ayinde M Usman, Clement Nyirenda2026-07-21

💻 computer science

Chain-Hash Audit Framework with Trusted Anchoring for Tamper-Evident Evidence Lifecycle Management

This paper proposes the Chain-Hash Audit Framework (CHAF), a novel architecture that enhances traditional hash-chain logging by integrating authorization status, timestamps, and lifecycle properties with signed checkpoints and external anchoring to create a tamper-evident, verifiable evidence chain that significantly reduces audit reconstruction time for digital asset systems.

Jinyuan Li, Yulun Zhang, Yicheng Gu2026-07-21

💻 computer science

The Influence of Artificial Intelligence on Project Risk Identification and Mitigation

This study demonstrates that Artificial Intelligence significantly enhances project risk identification and mitigation through improved accuracy and data processing, while highlighting the critical need for human-AI collaboration frameworks to address challenges like information overload, algorithmic bias, and over-reliance.

Praise Adeleke2026-07-21

💻 computer science

An AI–BIM Integrated Framework for Rapid Early-Stage Energy Performance Prediction in Algerian Residential Buildings: A Machine Learning Approach Using Random Forest and XGBoost

This research presents an AI-BIM integrated framework utilizing Random Forest and XGBoost models to enable rapid, real-time energy performance prediction for Algerian residential buildings, thereby overcoming the limitations of traditional simulation tools during early-stage design.

BESSAI Hadjer2026-07-21

💻 computer science

Algorithmic Topological Resonance Theory: Realizing a Quantum Stateless AI Data Center Architecture via Zero-Payload I/O and Permanent O(1) Complexity

This paper proposes the Quantum Stateless AI Data Center (QS-AIDC) architecture, which utilizes Algorithmic Topological Resonance theory, Zero-Payload I/O, and Proof of Resonance consensus to achieve permanent O(1) complexity, eliminate data storage, and drastically reduce energy consumption by replacing traditional stateful computing with non-local, deterministic reconstruction.

Min Ho Jung2026-07-21

💻 computer science

From Requirements to Production: Governing AI-Assisted Software Delivery through a Canonical Requirements Model

This paper presents a design science study introducing a governance framework for AI-assisted software delivery that utilizes a canonical requirements model, a dual-vendor build-and-review loop, and executable documentation to achieve high traceability and compliance across two independent production systems while redefining the business analyst's role.

Mohamed Zahran2026-07-21

💻 computer science

Distributional Neurons: Making Uncertainty a Unit of Computation

The paper introduces EVE, a variational neuron that treats uncertainty as a computational primitive by propagating distributional latent states, demonstrating that this neuron-level approach improves uncertainty calibration and performance in both dense MLPs and Transformer architectures while maintaining competitive point accuracy.

YVES RUFFENACH2026-07-21

💻 computer science

Automated Scoring of Handwritten Mathematical Problem Posing Using Large Language Models

This study demonstrates that the large language model Gemini 3.5 Flash can achieve reliable automated scoring of handwritten middle school mathematical problem-posing tasks when using a zero-shot prompting approach with a structured rubric, particularly for whole number problems and when utilizing revised OCR text inputs.

Tuğrul Kar, Tarık Kışla, Muhammed Ali Kayici, Burak Aydın2026-07-21

💻 computer science

Behavioral Anomaly Detection and Malicious Service Identification in the Tor Network Using Deep Learning

This paper proposes MBRD-Tor, a three-stage deep learning framework that addresses the challenges of protocol homogenization, encryption noise, and extreme class imbalance in the Tor network by fusing multi-scale behavioral signatures, employing an ensemble-based quality estimation for adaptive weighting, and utilizing GAN-generated synthetic features to achieve superior malicious service detection performance.

Amirhossein Saviz2026-07-21

← Previous Next →