cs papers | Gist.Science

Persistence-Weighted Descriptors: A Topologically Stable Local Feature Representation for Deformation-Robust Image Matching

This paper introduces PW-Desc, a topologically stable local feature descriptor that prioritizes mathematically proven stability guarantees under perturbations and photometric transforms over raw matching accuracy, making it specifically suitable for safety-critical applications like medical registration and forensic analysis despite trailing state-of-the-art learned methods in benchmark performance.

Md Hasibuzzaman2026-08-20

💻 computer science

Bottleneck-aware explainable learning-to-dispatch improves simulated throughput in dynamic flexible manufacturing systems

The paper introduces Bottleneck-aware Explainable Learning-to-Dispatch (BA-XLD), an interpretable priority policy that significantly improves throughput, reduces tardiness, and minimizes setup times in dynamic flexible manufacturing systems by leveraging learned, additive feature contributions to adapt to stochastic disturbances.

Muhammad Rafay Ikram2026-08-20

💻 computer science

Service-preserving carbon- and water-aware resource allocation for geo-distributed AI inference

This paper proposes a trace-driven, two-stage lexicographic framework for geo-distributed AI inference that prioritizes service feasibility while optimizing carbon emissions under strict physical water constraints, demonstrating significant environmental trade-offs and providing a reproducible benchmark for sustainable resource allocation.

Qian Zhang, Shengyu Sheng, Tongna Liu2026-08-20

💻 computer science

Target-Adaptive Probability Calibration for Reliable Student Risk Prediction under Cross-Module Dataset Shift

This study demonstrates that using modest amounts of historical target-domain data for target-adaptive probability calibration significantly improves the reliability and interpretability of AI-based student risk predictions across courses experiencing dataset shifts, without compromising ranking performance.

Qiuying Li, Jianqiang Tan2026-08-20

💻 computer science

Mapping social determinants of health in NIH research funding with large language models

This study demonstrates that fine-tuned large language models, particularly ModernBERT-base, significantly outperform traditional keyword methods and zero-shot approaches in classifying social determinants of health within NIH grant narratives, while identifying threshold calibration as a critical strategy for addressing label imbalance.

Yuxin Zhao, Zhuo Chen2026-08-20

💻 computer science

Interventional Causal Structure Discovery for Domain-Invariant Operating-Condition Classification in Multimodal Robotic Manufacturing

This paper introduces the Interventional Causal Framework for Condition-Based Maintenance (IC-CBM), which leverages interventional causal discovery and structural residual normalization to overcome associative overfitting in multimodal robotic manufacturing, achieving robust, domain-invariant operating-condition classification with significantly improved out-of-distribution accuracy and precision compared to traditional correlational baselines.

Md Omar Al Javed, Matthew Taylor, Vivekanand Naikwadi, Ayantha Senanayaka2026-08-20

💻 computer science

Diagnosing Causal Credibility of Machine Learning Explanations: A Dual- SHAP Attribution Framework Applied to Social Survey Data

This paper introduces a dual-SHAP framework that distinguishes between correlational and causal relationships in machine learning explanations by comparing conditional and interventional attributions, demonstrating its effectiveness in diagnosing causal credibility across diverse social survey outcomes.

Shidong Li2026-08-20

💻 computer science

Novel Vision-Based Camera Distance Estimation for Indoor Positioning

This paper proposes a novel vision-based framework that combines human pose detection, monocular depth features, homography mapping, and a learned residual correction model to accurately estimate the distance between a fixed CCTV camera and a person in GPS-denied indoor environments, achieving an average absolute error of 0.159 meters.

Halgurd S. Maghdid2026-08-20

💻 computer science

Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular Example

This paper proposes and validates a reproducible, graph-centered evaluation framework that grounds healthcare LLMs in a causal knowledge graph, demonstrating through a cardiovascular pilot that integrating causal assertions into model context significantly improves reasoning about interventions, mechanisms, and evidence compared to ungrounded approaches.

Ummara Mumtaz, Aimen Noor, Awais Ahmed2026-08-20

💻 computer science

OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations

This paper introduces OmegaUse-SOP, a human-in-the-loop system that transforms expert demonstrations into reusable, domain-specific Standard Operating Procedure (SOP) skills for GUI agents, significantly improving their reliability in complex professional environments like photovoltaic simulation workflows.

Yixiong Xiao2026-08-20

← Previous Next →