cs papers | Gist.Science

FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets

FinSheet-Bench introduces a synthetic benchmark modeled on real private equity fund structures to evaluate LLMs on financial spreadsheet tasks, revealing that even the best-performing models currently lack the accuracy required for unsupervised professional use, particularly on complex, large-scale documents, and suggesting that reliable extraction will require separating document understanding from deterministic computation.

Jan Ravnik, Matjaž Ličen, Felix Bührmann, Bithiah Yuan, Felix Stinson, Tanvi Singh2026-03-10💻 cs

A method for the automated generation of proof exercises with comparable levels of proving complexity

This paper presents a computational method for automatically generating mathematical proof exercises with comparable complexity levels by utilizing cut-based tableau proofs and a mechanizable rule extraction procedure to control difficulty for undergraduate discrete mathematics education.

João Mendes, João Marcos, Patrick Terrematte2026-03-10💻 cs

Echo: Graph-Enhanced Retrieval and Execution Feedback for Issue Reproduction Test Generation

Echo is an advanced agent that leverages code graphs, automatic query refinement, and execution feedback to generate single, high-quality issue reproduction test cases, achieving a new state-of-the-art success rate of 66.28% on the SWT-Bench Verified dataset.

Zhiwei Fei, Yue Pan, Federica Sarro, Jidong Ge, Marc Liu, Vincent Ng, He Ye2026-03-10💻 cs

Offer of a reward does not always promote trust in spatial games

This study demonstrates through numerical simulations of a spatial trust game that inter-role rewards do not linearly promote trust, as excessive rewards can trigger non-return strategies that suppress cooperation, while moderately costly rewards are most effective at consolidating trust clusters.

Haidong Zhang, Chaoqian Wang, Shuo Liu, Charo I. del Genio, Stefano Boccaletti, Xin Lu2026-03-10💻 cs

Self-Supervised Evolutionary Learning of Neurodynamic Progression and Identity Manifolds from EEG During Safety-Critical Decision Making

This paper proposes a self-supervised evolutionary learning framework that extracts individualized neurodynamic progressions and identity manifolds from unlabeled EEG data during safety-critical decision-making, enabling robust user authentication, anomaly detection, and improved generalization without relying on external labels or predefined cognitive models.

Xiaoshan Zhou, Carol C. Menassa, Vineet R. Kamat2026-03-10💻 cs

VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models

This paper introduces VisualScratchpad, an interactive inference-time analysis tool that leverages sparse autoencoders and attention mechanisms to visualize and debug vision language models by linking visual concepts to text tokens, thereby revealing previously underexplored failure modes such as limited cross-modal alignment and misleading visual concepts.

Hyesu Lim, Jinho Choi, Taekyung Kim, Byeongho Heo, Jaegul Choo, Dongyoon Han2026-03-10💻 cs

A Lightweight Digital-Twin-Based Framework for Edge-Assisted Vehicle Tracking and Collision Prediction

This paper proposes a lightweight, digital-twin-based framework for edge-assisted vehicle tracking and collision prediction that achieves approximately 88% accuracy by relying on object detection and K-D tree-indexed path maps instead of computationally intensive trajectory prediction models.

Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Aisha Syed, Matthew Andrews, Sean Kennedy2026-03-10💻 cs

Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

The paper introduces Agora, an AI-powered platform that leverages LLMs to simulate diverse human perspectives on policy issues, enabling users to practice consensus-building and demonstrating through a preliminary study that access to authentic voice explanations significantly enhances problem-solving skills and the quality of collective decisions compared to viewing aggregate data alone.

Suyash Fulay, Prerna Ravi, Emily Kubin, Shrestha Mohanty, Michiel Bakker, Deb Roy2026-03-10💻 cs

Uber's Failover Architecture: Reconciling Reliability and Efficiency in Hyperscale Microservice Infrastructure

Uber's Failover Architecture (UFA) replaces its costly uniform 2x capacity model with a differentiated, criticality-based approach that opportunistically shares resources and preempts non-critical services during peak failovers, thereby reducing steady-state provisioning from 2x to 1.3x and eliminating over one million CPU cores while maintaining 99.97% availability.

Mayank Bansal, Milind Chabbi, Kenneth Bogh, Srikanth Prodduturi, Kevin Xu, Amit Kumar, David Bell, Ranjib Dey, Yufei Ren, Sachin Sharma, Juan Marcano, Shriniket Kale, Subhav Pradhan, Ivan Beschastnikh, Miguel Covarrubias, Chien-Chih Liao, Sandeep Koushik Sheshadri, Wen Luo, Kai Song, Ashish Samant, Sahil Rihan, Nimish Sheth, Uday Kiran Medisetty2026-03-10💻 cs

Pre-Clinical Latency Characterization of VRxBioRelax: A Real-Time EMG Biofeedback System for Muscle Relaxation in Virtual Reality

This paper introduces VRxBioRelax, a real-time virtual reality biofeedback system that utilizes sEMG data to drive an immersive relaxation environment, demonstrating through extensive pre-clinical testing that its average end-to-end latency of 25.34 ms significantly meets both VR comfort and clinical benchmarks for effective muscle relaxation training.

Melanie Baumgartner, Raphael Weibel, Tobias Hoesli, Aydin Javadov, Rayna Ney, Helen Schwerdt, Florian von Wangenheim, Joseph Ollier2026-03-10💻 cs

Collaboration by Mandate: How Shared Data Infrastructure Shapes Coordination and Control in U.S. Homelessness Services

This study argues that while federally mandated shared data systems like HMIS facilitate coordination and accountability in U.S. homelessness services, they simultaneously reinforce power asymmetries by shifting resource-constrained providers toward compliance roles and concentrating decision-making authority.

Lingwei Cheng, Saerim Kim, Andrew Sullivan2026-03-10💻 cs

The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations

This paper demonstrates that environmental pressure in multi-agent LLM simulations follows a Yerkes-Dodson inverted-U relationship, where medium stress optimizes emergent cooperative trade while extreme pressure causes behavioral collapse, and suggests that calibrating such pressure serves as an effective curriculum design strategy for agent development.

Ivan Pasichnyk2026-03-10💻 cs

Neural Control and Learning of Simulated Hand Movements With an EMG-Based Closed-Loop Interface

This paper presents a novel in silico neuromechanical framework that integrates forward musculoskeletal simulation, reinforcement learning, and online EMG synthesis to create a flexible, closed-loop virtual participant capable of generating synchronized neural and kinematic data for evaluating neural controllers and augmenting training datasets.

Balint K. Hodossy, Dario Farina2026-03-10💻 cs

Task learning increases information redundancy of neural responses in macaque visual cortex

By tracking macaque V4 neural responses during visual discrimination learning, the study demonstrates that task learning increases information redundancy rather than reducing it, supporting a Bayesian generative inference model where redundancy enhances the information carried by individual neurons.

Shizhao Liu, Anton Pletenev, Ralf M. Haefner, Adam C. Snyder2026-03-10💻 cs

Scheduling Parallel Optical Circuit Switches for AI Training

This paper introduces Spectra, a three-step scheduling algorithm that efficiently manages time-varying AI traffic across parallel optical circuit switches by decomposing traffic matrices, assigning permutations load-awarely, and balancing loads through controlled splitting, thereby significantly reducing makespan compared to state-of-the-art baselines.

Kevin Liang, Litao Qiao, Isaac Keslassy, Bill Lin2026-03-10💻 cs

Multi-Agentic AI for Conflict-Aware rApp Policy Orchestration in Open RAN

This paper proposes a Multi-Agentic AI framework utilizing specialized LLM agents and retrieval-augmented generation to automate conflict-aware rApp policy orchestration in Open RAN, achieving significant improvements in deployment accuracy and cost reduction while enabling zero-shot generalization.

Haiyuan Li, Yulei Wu, Dimitra Simeonidou2026-03-10💻 cs

SoK: Evolution, Security, and Fundamental Properties of Transactional Systems

This paper presents a comprehensive systematization of transaction processing security across four evolutionary generations, introducing a new taxonomy, mapping vulnerabilities to CWE identifiers, and proposing the RANCID property set to address the insufficiencies of the classical ACID model in modern, real-time, multi-context systems.

Sky Pelletier Waterpeace, Nikolay Ivanov2026-03-10✓ Author reviewed ⓘ💻 cs

Enhancing OLAP Resilience at LinkedIn

This paper presents a holistic resiliency framework for Apache Pinot at LinkedIn, featuring Query Workload Isolation, Impact-Free Rebalancing, Maintenance Zone Awareness, and Adaptive Server Selection, which collectively ensure stable subsecond query latency and high availability for petabyte-scale OLAP workloads under failures and load spikes.

Praveen Chaganlal, Jia Guo, Vivek Vaidyanathan, Dino Occhialini, Sonam Mandal, Subbu Subramaniam, Siddharth Teotia, Tianqi Li, Xiaxuan Gao, Florence Zhang2026-03-10💻 cs

Approximating Tensor Network Contraction with Sketches

This paper introduces the first sketching method capable of approximating arbitrary tensor network contractions, including cyclic ones, and proposes a second method for acyclic networks that achieves polynomial time and space complexity, overcoming the exponential limitations of existing approaches.

Mike Heddes, Igor Nunes, Tony Givargis, Alex Nicolau2026-03-10💻 cs

Link Wars: The Semantic Crisis. Is the debate over or is it just beginning?

This paper argues that the current fragmentation in high-performance interconnects stems from a fundamental "semantic crisis" caused by implicit, vendor-specific assumptions about time and ordering, and proposes that adopting explicit, testable link semantics through the Open Atomic Ethernet (OAE) standard is essential to restore correctness and enable convergence.

Paul Borrill2026-03-10💻 cs

← Previous Next →