cs papers | Gist.Science

Comparative Performance of Frontier Large Language Models for Extracting High-Risk Pathologic Features from Unstructured Gastrointestinal Oncology Reports: A Systematic Benchmarking Study with Human and Traditional NLP Baselines

This systematic benchmarking study demonstrates that frontier large multimodal models, particularly Gemini 2.5 Pro and GPT-4o, significantly outperform both time-pressured human experts and traditional NLP baselines in extracting critical perineural invasion status from unstructured gastrointestinal pathology reports, while a novel failure mode taxonomy provides actionable guidance for model selection based on specific error signatures.

Seher Siddiqui2026-07-21✓ Author reviewed ⓘ

💻 computer science

Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approach

This paper proposes a hedonic potential-game framework for stable and budget-feasible coalition formation in clustered federated learning, proving the existence of Nash-stable partitions and deriving welfare efficiency guarantees that are empirically validated to outperform equal-surplus sharing on CIFAR-10 datasets.

Cengis Hasan2026-07-21

💻 computer science

When Verification Is Late: Delay Floors and Placement Flips in Corrected Multi-Agent Systems

This paper establishes that in delayed multi-agent correction systems, verification latency imposes an inescapable accuracy floor determined by the Dottie number, creates a budget ceiling for performance gains, and reverses the optimal strategy from concentrating to spreading correction resources beyond a specific threshold.

Igor Itkin2026-07-21

💻 computer science

A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic

This paper proposes a resilient hybrid defense mechanism combining Adversarial Training and Gaussian Data Augmentation to significantly restore the accuracy of Network Intrusion Detection Systems against Fast Gradient Sign Method and Carlini & Wagner adversarial attacks, improving post-attack performance from as low as 26.49% to 96.57%.

Khushnaseeb Roshan2026-07-21

💻 computer science

Beyond Appearance: Intelligent Spatiotemporal Vision for Material-Aware Object Detection

This paper introduces a spatiotemporal fusion framework that integrates multispectral RGB intensity maps with direct time-of-flight photon histograms to achieve material-aware object detection, demonstrating high accuracy in localization, classification, and spoofing resistance through a dual-module pipeline validated on household objects.

Deborah A. Minka2026-07-21

💻 computer science

Fixed-Point Integer Approximations for Square Root and Division on ESP32:A Benchmark-Driven Analysis

This paper benchmarks fixed-point Q16 integer approximations for square root and division on the ESP32-S3, demonstrating that a lookup table with interpolation significantly outperforms native hardware floating-point implementations in speed while maintaining high accuracy for resource-constrained embedded applications.

Lucas Lima Freitag2026-07-21

💻 computer science

Advances in Factoring and Primality Testing: From Classical to Quantum Algorithms

This paper provides a comprehensive review and comparative performance analysis of classical and quantum algorithms for factoring and primality testing, concluding that while quantum methods like Shor's algorithm offer significant advantages for factoring, they do not provide comparable benefits for primality testing.

Anas A. Abudaqa, Nujud Alyami, Mostefa Kara, Farid Binbeshr, Muhammad Imam2026-07-21

💻 computer science

Evaluation of clustering methods for segmentation of hyperspectral remote sensing data

This paper empirically evaluates various clustering methods on hyperspectral remote sensing data, finding that computationally efficient centroid-based algorithms like K-Means consistently offer the best balance of quality, robustness, and speed compared to more complex alternatives when combined with effective dimensionality reduction.

Ehsan Farahbakhsh, Pulkit Sharma, Aman Agrawal, Rohitash Chandra2026-07-21

💻 computer science

The Scaffold Jump Pattern: Progressive, Evidence-Gated Fading of Human Roles in Artificial Intelligence Systems

This paper introduces the "Scaffold Jump" design pattern, an operational framework that enables organizations to systematically and safely transition AI systems from full human oversight to autonomy by defining four distinct phases linked by evidence-gated transitions that ensure performance thresholds are met while maintaining accountability and ethical constraints.

Michael Sadowski2026-07-21

💻 computer science

Face Recognition Utilizing Generative Adversarial Networks and Fuzzy Logicfor Angle Classification

This paper proposes an adaptive Fuzzy-GAN system that utilizes Generative Adversarial Networks and fuzzy logic to classify face orientations into low, medium, and high angles (including clockwise and anti-clockwise variations) to enhance pose-invariant face recognition for law enforcement applications.

Deepti Chepuri, Naga Venkata Jagan Mohan Remani2026-07-21

← Previous Next →