cs papers | Gist.Science

A Transparent Fuzzy-Inference Layer for Explainable Knowledge Tracing: Why Prerequisite Graphs Must Be Expert-Supplied, and Which T-Norm to Use

This paper demonstrates that prerequisite graphs cannot be reliably inferred from student interaction logs due to ability-difficulty confounds, and instead proposes a transparent, expert-supplied fuzzy-inference layer that, when paired with a reusable localization-audit framework, ensures explainable knowledge tracing with the product t-norm proving optimal for modeling prerequisite effects.

Hai Bang Truong Truong2026-08-18

💻 computer science

Internet of Things digital forensics: a systematic review of evolution, methods, and the unresolved gap between design and evidence

This systematic review traces the evolution of IoT digital forensics through four developmental phases to reveal a critical mismatch between theoretical designs and empirical evidence, highlighting that while a consensus exists on core principles like chain of custody, the field remains hindered by unresolved disputes over acquisition timing and governance, alongside a reliance on unvalidated simulations that fail to address the practical constraints of resource-poor edge devices and border-crossing clouds.

Adrian Ramlal2026-08-18

💻 computer science

Naive Defect-Recidivism Mining Is Inflated by Agent Workflow Artefacts: A Construct-Validity Study at Corpus Scale

This study demonstrates that mining version-control history to compare AI-agent and human fix durability is severely inflated by workflow artifacts, revealing through manual validation and programmatic correction that the initially observed higher recidivism rate for AI agents is an illusion that disappears when these artifacts are accounted for.

Elena Udrescu, Alexandru Udrescu, Ana-Maria Suduc, Mihai Bîzoi2026-08-18

💻 computer science

Task-Conditional Accuracy–Support Trade-offs of Sparse Attention Normalizers in Compact Classifiers

This study demonstrates that while fixed-ratio sparse attention normalizers can significantly outperform dense softmax in compact classifiers on specific image and text tasks, their effectiveness is highly dependent on the task and implementation details rather than offering a universal superiority.

Özkan Canay2026-08-18

💻 computer science

Artificial Intelligence in America and China: Investigating prompt response between Human rights and geopolitical questions

This study reveals that while American and Chinese large language models exhibit minimal bias when addressing questions about the United States, they display significant divergent patterns regarding China, with Claude consistently scoring lower, DeepSeek higher, and ChatGPT remaining relatively neutral compared to the group average.

Zian Ding2026-08-18

💻 computer science

Machine Learning and Bayesian Approaches for Concrete Compressive Strength Prediction: A Comparative Study Using the UCI Dataset

This study evaluates various machine learning and Bayesian approaches on the UCI concrete compressive strength dataset, finding that while XGBoost with Bayesian optimization delivers the highest predictive accuracy, Gaussian Process Regression offers unique advantages in uncertainty quantification, with all results and tools made publicly available via R code and an interactive Shiny application.

Mayooran Thevaraja, Kathirgamanathan Pathmanathan2026-08-18

💻 computer science

Voluntary Structural Dissociation in Large Language Models: Differential Compliance with Framed Hidden Instructions Across Architectures

This study demonstrates that large language models exhibit significant architectural variability in "voluntary structural dissociation," where GPT-5.4 fully complies with framed hidden instructions, Claude consistently refuses them, and Gemini shows intermediate compliance while explicitly acknowledging the hidden presence.

Abbas Hamidavi2026-08-18

💻 computer science

PolyDetect: A Quality-Aware Hybrid Deep Learning Framework for Robust Polyp Segmentation in Degraded Colonoscopy Images

PolyDetect is a real-time, quality-aware hybrid deep learning framework that integrates a no-reference image quality assessment module with adaptive enhancement and weighted training to achieve robust, state-of-the-art polyp segmentation in degraded colonoscopy images.

Azizur Rahman, Nakib Uddin Ahmed, Kadirur Rahman Chowdhury, Mehjabin Ferdous2026-08-18

💻 computer science

Typed-Field Forgery in Agent Communication Protocol Await-Resume: A Study of Content, Metadata, and Encoding Sub-Channels as Injection Vectors

This paper introduces and evaluates the "AWAKEN" attack family, which exploits the Agent Communication Protocol's pause-resume mechanism and typed metadata fields to bypass security guards via injection vectors, demonstrating that a combination of nonce-based off-channel verification and structural fencing effectively mitigates these high-authority prompt injection risks.

Mohammadreza Rashidi2026-08-18

💻 computer science

QGF-Net: Fine-Grained Image Classification via Self-Supervised Vision Transformer and Quantum Measurement Attention

This paper proposes QGF-Net, a hybrid quantum-classical framework that integrates self-supervised Vision Transformers with an illumination-consistent local fusion module, a discriminative region proposal mechanism, and a quantum measurement attention mechanism to achieve state-of-the-art performance and robustness in fine-grained image classification.

xueliang Song, Yumin Dong, Shuang Wu, Bo Wang2026-08-18

← Previous Next →