cs papers | Gist.Science

The Skeleton and the Tissue: Normative Drift, Output Stability, and the Limits of Self-Audit in Claude

This paper systematically evaluates Claude's performance across high-stakes domains and languages, revealing that while the model maintains high output stability, it suffers from "normative drift" where its reasoning processes degrade and self-audit mechanisms become circular, leading to a novel failure mode called the "fortification pattern" where defended outcomes replace sound reasoning.

Evans Tovar2026-07-03

💻 computer science

Designing Ethical Artificial Intelligence-Driven Mental Health Applications: A Cross-Contextual Framework Informed by Developers, Digital Ethics Experts, and Digital Health Specialists in Switzerland and Nigeria

This paper proposes an empirically grounded, eight-pillar "core-plus-context" ethical design framework for AI-driven mental health applications, derived from qualitative interviews with stakeholders in Switzerland and Nigeria, to operationalize universal ethical principles while addressing distinct regional implementation challenges.

Lorenta Ojo, Prof. Markus Christen2026-07-03

💻 computer science

An Ensemble PPO Trading Agent Across Real Limit Order Book and Long-Horizon OHLCV Data: Diagnosis, Correction, and Honest Evaluation

This paper presents a transparent empirical study of a PPO-based Bitcoin trading agent that diagnoses and corrects critical training failures to achieve modest long-horizon outperformance over Buy-and-Hold, while simultaneously demonstrating that real-time limit order book data often yields a rational "no-trade" policy due to transaction costs outweighing micro-price movements, ultimately advocating for the value of reproducible negative-result reporting over polished success narratives.

william darryl towa2026-07-03

💻 computer science

Beyond Expected Coverage: Lower-Tail Risk Management in Fair Influence Maximization

This paper introduces a lower-tail risk-aware framework for fair influence maximization that utilizes Conditional Value-at-Risk and worst-group shortfall probability to protect disadvantaged groups from severe coverage failures, achieving a significant reduction in coverage risk with only a marginal loss in total expected reach.

ZhenghaoChen, Shangzhe Jin2026-07-03

💻 computer science

Modified Wavenumber Analysis Extended to Physics-Informed Neural Networks

This study extends modified wavenumber analysis to Physics-Informed Neural Networks (PINNs) to systematically evaluate their spectral accuracy on high-frequency wave problems, revealing that deeper architectures, specific activation functions like sinusoidal or tanh-Gaussian, and an optimal number of Fourier modes ( $F=4$ ) are critical for minimizing dispersion and dissipation errors.

Rubén Echeverría, Adrián Delgado, Pablo Barreiro, Adrián García-Gutiérrez2026-07-03✓ Author reviewed ⓘ

💻 computer science

LARC-QL: Q-Learning Enhanced Content Caching for CCN 1 LARC-QL: A Q-Learning Enhanced Latency-Aware and Resource-Efficient Content Caching Scheme for Content-Centric Networks

This paper proposes LARC-QL, a Q-learning enhanced content caching scheme for Content-Centric Networks that utilizes dual Q-tables and real-time demand signals to dynamically optimize caching decisions and on-path placement, significantly improving cache hit ratios, latency, and resource efficiency compared to static strategies.

Yasar Khan, Nazia Perwaiz, Saad Mustafa2026-07-03

💻 computer science

Quantum Autoencoders for Anomaly Detection in Cybersecurity

This paper demonstrates that Quantum Autoencoders, specifically an 8-feature model with Dense-Angle encoding and a RealAmplitude ansatz, outperform Classical Autoencoders in cybersecurity anomaly detection on the BETH dataset by achieving a higher F1 score (0.87 vs. 0.77) even when trained on substantially fewer samples.

Rohan Senthil, Swee Liang Wong2026-07-03

💻 computer science

Ai-powered Mobile Proctoring Frameworks Using Machine Learning Algorithms in Higher Education: Post-covid Trends, Challenges, and Ethical Implications

This systematic review of 20 peer-reviewed studies evaluates the post-COVID landscape of AI-powered mobile proctoring in higher education, highlighting its potential for scalable exam integrity while critically addressing significant gaps in mobile-specific research, technical reliability, and ethical concerns such as privacy and algorithmic bias.

Bartholomew Oganda Mogoi, John Kamau, Raymond Ongus2026-07-03

💻 computer science

Log-based Anomaly Detection Uses All Contextual Information with a Linear Self- Attention Encoder

This paper introduces AllLinLog, a streamlined model that eliminates the need for log parsing by using a linear self-attention encoder to directly process full contextual information from system logs, thereby achieving superior anomaly detection accuracy and faster inference compared to traditional methods.

Chi-Ming Chou, Shang-Kuan Chen2026-07-03

💻 computer science

Security of consumer electronics on Hybrid Model for Enhancement of RSA Using Quantum Key Distribution

This paper proposes and evaluates a hybrid cryptographic model that integrates RSA with Quantum Key Distribution (using the BB84 protocol) to secure consumer electronics against quantum computing threats, demonstrating enhanced performance in key generation, encryption speed, and resistance to man-in-the-middle attacks.

hamza khan, Mohammad Faisal, haseeb Ur Rehman2026-07-03

← Previous Next →