cs papers | Gist.Science

Humans Disengage, Reasoning Models Persist: An Item-Controlled Dissociation in Deliberation Allocation

This paper reveals a critical dissociation between humans and large reasoning models (LRMs) in deliberation allocation: while both spend more time on harder problems overall, humans invest less time on items they ultimately get wrong (abandoning difficult tasks), whereas LRMs paradoxically generate longer reasoning traces on problems they fail (persisting in uncertainty), highlighting a fundamental difference in stopping and control policies despite surface-level similarities.

Han-yu Wang2026-07-23

💻 computer science

Blockchain-focused Cyber Security for the Detection and Protection of Denial of Service (DoS) Attacks

This study proposes a blockchain-integrated cybersecurity framework that utilizes a Convolutional Neural Network (CNN) model to achieve 98.3% detection accuracy and 100% prevention capability against Denial of Service (DoS) attacks in AI-based network systems.

Eshetie Teka Mitiku, Tibebe Beshah, Habtamu Kassaw2026-07-23

💻 computer science

How AI-Generated Prompts Shape Emotional Expression in Digital Drawing: Effects on Visual Complexity, Creative Engagement, and Arousal

This study demonstrates that AI-assisted prompting enhances visual complexity and behavioral engagement in digital drawing while revealing that machine learning models can better predict broad affective categories than fine-grained emotions based on these drawing features.

Hong-Chun Shi2026-07-22

💻 computer science

DIT: A Decentralized Identity and Trust Protocol for Post-Quantum CA-Free Web Authentication

DIT is a decentralized, post-quantum secure authentication protocol that eliminates the traditional CA hierarchy by anchoring domain identities in DNSSEC-verified ML-DSA-65 keys and utilizing a hybrid X25519MLKEM768 handshake with Merkle transparency logs to provide efficient, revocable trust without centralized certificate authorities.

Debasish tripathy, Dayananda P2026-07-22

💻 computer science

Uncertainty-Guided Triple-Memory Fusion for Robust Multi-Object Tracking

This paper proposes an uncertainty-guided triple-memory fusion framework that leverages probabilistic Mamba to quantify motion uncertainty and dynamically fuse motion, appearance, and category memories, achieving state-of-the-art performance in robust multi-object tracking across complex dynamic scenes.

Weichao Guo, Leiming He, Han Li, Yi Sun, Yuchen Zhang, Chenguang Xing2026-07-22

💻 computer science

A Grayscale image encryption using cubic fractional transformation and logistic map

This paper proposes a grayscale image encryption scheme that combines a cubic fractional transformation-generated S-box with a logistic map to perform substitution, diffusion, and XOR-based scrambling, demonstrating robust security through comprehensive statistical and key sensitivity analyses.

Abdul Qadeer, Rashid Ali, Tahir Sajjad Ali2026-07-22

💻 computer science

Artificial Intelligence Framework for Audit-Ready Pharmaceutical Manufacturing Under Explainability, Fairness, and Regulatory Transparency Constraints

This study proposes a comprehensive AI framework for pharmaceutical manufacturing that integrates predictive modeling with explainability, fairness, calibration, drift monitoring, and regulatory traceability to ensure audit-ready, defensible quality-governance decisions.

Charles Onyeka Nwamekwe, Nkemakonam Chidiebube Igbokwe, Chukwuma Godfrey Ono2026-07-22

💻 computer science

Seeing quality through AI: YOLOv11 for automated grading of dried sea cucumber processing methods

This study demonstrates that a lightweight YOLO11n deep learning model can achieve near-perfect accuracy in automatically classifying dried sea cucumber processing methods (salting, smoking, and roasting) from dense-object images, offering a robust, non-destructive alternative to subjective manual inspection for quality grading.

Luther Alexander Latumakulita, Risnandar Risnandar, Hence Beedwel Lumentut, Silviani Esther Rumagit2026-07-22

💻 computer science

Semantic-Guided Multi-Scale Dual-Teacher Distillation Network for Medical and Industrial Anomaly Detection

This paper proposes SGMS-DTDNet, a semantic-guided multi-scale dual-teacher distillation network that integrates domain-specific semantics, structural priors, and adaptive feature selection to achieve state-of-the-art performance in unified medical and industrial anomaly detection by overcoming challenges like scarce abnormal samples and heterogeneous defect morphologies.

Pufan Guo2026-07-22

💻 computer science

Beyond full fine-tuning: enhancing generalizability in ECG foundation models' downstream adaptation

This study demonstrates that parameter-efficient fine-tuning (PEFT) strategies, such as partial fine-tuning and BitFit, outperform full fine-tuning in electrocardiogram foundation models by significantly enhancing generalizability and reducing overfitting, particularly on out-of-domain data and resource-constrained scenarios.

Giuliana Monachino, Beatrice Zanchi, Georgiy Farina, Francesca Dalia Faraci2026-07-22

← Previous Next →