cs papers | Gist.Science

Distinguishing Order Effects from Random Variation in Cleaning Pipelines for Tabular Data Classification

This paper introduces the Order Sensitivity Index and a permutation test to rigorously distinguish meaningful pipeline order effects from random variation in tabular data classification, revealing that while order impacts accuracy beyond chance in many cases, the specific sequence of balancing classes and correcting labels is critical to preventing minority-class label degradation.

Muhammad Idrees, Zaheer Ullah, Thanh Thi Nguyen, Muhammad Taimour Hamid2026-11-11

💻 computer science

A Trust-Aware Hybrid Q-AHA Energy-Efficient secure Clustering for Wireless Sensor Networks with a Mobile Sink Node

This paper proposes a Trust-Aware Hybrid Q-AHA clustering algorithm for Mobile Wireless Sensor Networks that integrates distributed Q-learning for local node evaluation with the Artificial Hummingbird Algorithm for global cluster head optimization, effectively balancing energy efficiency, security against malicious nodes, and network performance metrics like lifetime and throughput.

Keerthi K S, Jagadisha N2026-11-11

💻 computer science

SOFIA: Quantifying Sampling-Induced Explanation Instability in Graph Neural Networks

The paper introduces SOFIA, a framework demonstrating that training-time neighbor sampling in Graph Neural Networks causes significant, structure-dependent instability in post-hoc explanations, revealing that these outputs often reflect arbitrary hyperparameters rather than genuine structural node properties.

Prabu N P, Priyanga Subbiah, Daniel A2026-11-11

💻 computer science

CLEAR: Cross-Layer Extreme Activation Representation for Backdoor Sample Detection

This paper proposes CLEAR, a cross-layer framework that leverages batch normalization-aligned extreme activation representations and particle swarm optimization-driven layer weighting to detect backdoor samples with high accuracy and low false positives, even under low poisoning rates and without clean validation data.

Hui Li, Bingyan Li, Wanwei Huang, Lifeng Jin, Chunfeng Du, Yi Ding, Shilin Liang2026-11-11

💻 computer science

Characterising Mobile Money Phishing Attacks Using Imitation Learning Relying on Expert Demonstrations

This paper characterizes mobile money phishing attacks in Africa by modeling them as a four-state process and applying imitation learning algorithms, specifically Behavior Cloning and Generative Adversarial Imitation Learning, to learn attacker strategies directly from expert demonstrations rather than relying on hand-crafted reward functions.

Alima Nzeket Njoya, Claudette Nyinawumuntu, Franklin Tchakounté, Derrick Méthode Bagaza, Mismadji Sosthène Togbé2026-11-11

💻 computer science

Predictive Failure Risk Assessment Using Temporal Dependency Modeling in Distributed Computing Environments

This study evaluates the effectiveness of temporal feature-based predictive modeling using Logistic Regression and Random Forest across diverse distributed computing datasets, demonstrating that the optimal classifier and feature approach depend significantly on the specific prediction target and data characteristics rather than offering a universal solution for physical failure prediction.

Umma Habiba Sultana2026-11-11

💻 computer science

Artificial Intelligence and Misinformation Detection in Digital Media: An Explainable Machine Learning Framework

This study proposes an explainable machine learning framework for detecting political misinformation on social media that achieves superior predictive performance compared to baseline models while highlighting that the system's real-world reliability is ultimately constrained by low ground-truth label agreement and poor temporal generalizability rather than architectural limitations.

Muhammad Usman Aslam, Hafiz Aqib Sattar2026-11-11

💻 computer science

Integrating Knowledge Graphs with Adaptive Schema into Wikipedia-based Question Answering Systems

This paper proposes an adaptive-schema, graph-enhanced retrieval framework for Wikipedia-based multi-hop question answering that utilizes local GLiNER2-based schema-guided extraction and post-hoc triple injection to improve evidence coverage and retrieval performance over LLM-dependent baselines, achieving state-of-the-art F1 scores on MuSiQue, 2WikiMultihopQA, and HotpotQA datasets.

Cong Tran, Linh Nguyen-Thi-Dieu, Hai Van Pham2026-11-11

💻 computer science

A one-year measurement of quota-induced waste in private clouds

This paper analyzes a year of private cloud operational data to reveal that quota-based resource management, combined with user behavior of provisioning for peak demand and administrative overselling, leads to significant inefficiencies characterized by persistent quota exhaustion despite available capacity and prolonged VM idleness.

Paola Marques, Francesco Desimoni, Francisco Brasileiro, Massimo Canonico, Thiago Emmanuel Pereira2026-11-11

💻 computer science

Comparative Machine Learning Approaches for QSPR-Based Prediction of Thermochemical Properties in Rocket Fuel Candidate Screening

This study develops a multi-output Artificial Neural Network leveraging molecular descriptors and information-gain metrics to simultaneously predict key thermochemical properties of rocket fuel candidates, demonstrating competitive performance against ensemble and support vector regression models to accelerate computational screening.

Yashwin G Devadiga, Parth Sarathi Panigrahy, Swarna M Patra, Ganga Periyasamy, K. N. Subramanya2026-11-11

← Previous Next →