Tootfinder

Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He
https://arxiv.org/abs/2506.02546

Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach the trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness p…

This https://arxiv.org/abs/2504.11711 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs
Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, traditional static analysis tools often generate excessive false positives due to simplified vulnerability modeling and overapproximation of path and data constraints. While large language models (LLMs) demonstrate promising code understanding capabilities, their direct application to program analysis remains unreliable due to…

This https://arxiv.org/abs/2305.11943 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

Public versus Less-Public News Engagement on Facebook: Patterns Across Bias and Reliability
The rapid growth of social media as a news platform has raised significant concerns about the influence and societal impact of biased and unreliable news on these platforms. While much research has explored user engagement with news on platforms like Facebook, most studies have focused on publicly shared posts. This focus leaves an important question unanswered: how representative is the public sphere of Facebook's entire ecosystem? Specifically, how much of the interactions occur in less-publi…

This https://arxiv.org/abs/2504.08756 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation
Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which capturing the complexity of reasoning based on hops and the distribution of supporting evidence. In this paper, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leve…

https://www.irishtimes.com/opinion/2025/06/29/mark-oconnell-i-love-wikipedia-so-much-i-hardly-even-minded-when-it-killed-me-off/

Mark O'Connell: I love Wikipedia so much, I hardly even minded when it killed me off
ChatGPT is so unreliable as to be effectively worse than useless. No-one would say that about Wikipedia

Leveraging In-Context Learning for Political Bias Testing of LLMs
Patrick Haller, Jannis Vamvas, Rico Sennrich, Lena A. J\"ager
https://arxiv.org/abs/2506.22232

Leveraging In-Context Learning for Political Bias Testing of LLMs
A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruct…

Dear #Apple Time Machine has become an unreliable POS. Jeez what the FICK are you guys doing!

Imagine if the media just stopped reporting on everything that #Trump says.. Since it's completely incoherent and unreliable anyway.. Wouldn't everyone just be happier? 🤔
#UsPol

Forecasting Geopolitical Events with a Sparse Temporal Fusion Transformer and Gaussian Process Hybrid: A Case Study in Middle Eastern and U.S. Conflict Dynamics
Hsin-Hsiung Huang, Hayden Hampton
https://arxiv.org/abs/2506.20935

Forecasting Geopolitical Events with a Sparse Temporal Fusion Transformer and Gaussian Process Hybrid: A Case Study in Middle Eastern and U.S. Conflict Dynamics
Forecasting geopolitical conflict from data sources like the Global Database of Events, Language, and Tone (GDELT) is a critical challenge for national security. The inherent sparsity, burstiness, and overdispersion of such data cause standard deep learning models, including the Temporal Fusion Transformer (TFT), to produce unreliable long-horizon predictions. We introduce STFT-VNNGP, a hybrid architecture that won the 2023 Algorithms for Threat Detection (ATD) competition by overcoming these l…

US and Iran were negotiating. Next round was scheduled for 15 June
13 June: Israel attacks Iran, out of the blue
Trump claims he knew beforehand.
Trump, 17 June: UNCONDITIONAL SURRENDER
Trump, today: "Iran should’ve agreed to a deal before Israel began its operation"
Incoherent and unreliable.

Experience converting a large mathematical software package written in C to C 20 modules
Wolfgang Bangerth
https://arxiv.org/abs/2506.21654 https://

Experience converting a large mathematical software package written in C++ to C++20 modules
Mathematical software has traditionally been built in the form of "packages" that build on each other. A substantial fraction of these packages is written in C++ and, as a consequence, the interface of a package is described in the form of header files that downstream packages and applications can then #include. C++ has inherited this approach towards exporting interfaces from C, but the approach is clunky, unreliable, and slow. As a consequence, C++20 has introduced a "module" system in which …

This https://arxiv.org/abs/2410.09516 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCE_…

Bridging the Gap Between Data-Driven And Theory-Driven Modelling - Leveraging Causal Machine Learning for Integrative Modelling of Dynamical Systems
Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by enhancing predictive robustness. However, constructing an initial causal graph manually using domain knowledge is time-consuming, particularly in complex time series with numerous variables. To address this, causal discovery algorithms can provide a preliminary ca…

Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
Zachary Ravichandran, Ignacio Hounie, Fernando Cladera, Alejandro Ribeiro, George J. Pappas, Vijay Kumar
https://arxiv.org/abs/2506.17486

Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-hosted models, limiting their usability in environments with unreliable communication infrastructure, such as outdoor or industrial settings. We present PRISM, a framework for distilling small language model (SLM)-enabled robot planners that run on-device with minimal human supervision. Starting from an existing LLM-ena…

Trans-dimensional Hamiltonian model selection and parameter estimation from sparse, noisy data
Abigail N. Poteshman, Jiwon Yun, Tim H. Taminiau, Giulia Galli
https://arxiv.org/abs/2506.18802

Trans-dimensional Hamiltonian model selection and parameter estimation from sparse, noisy data
High-throughput characterization often requires estimating parameters and model dimension from experimental data of limited quantity and quality. Such data may result in an ill-posed inverse problem, where multiple sets of parameters and model dimensions are consistent with available data. This ill-posed regime may render traditional machine learning and deterministic methods unreliable or intractable, particularly in high-dimensional, nonlinear, and mixed continuous and discrete parameter spac…

Age of Information in Unreliable Tandem Queues
Muthukrishnan Senthilkumar, Aresh Dadlani, Hina Tabassum
https://arxiv.org/abs/2506.09245 https://

Age of Information in Unreliable Tandem Queues
Stringent demands for timely information delivery, driven by the widespread adoption of real-time applications and the Internet of Things, have established the age of information (AoI) as a critical metric for quantifying data freshness. Existing AoI models often assume multi-hop communication networks with fully reliable nodes, which may not accurately capture scenarios involving node transmission failures. This paper presents an analytical framework for two configurations of tandem queue syst…

So farewell then Pinetime Watch 🪦.
It isn't showing any signs of charging. even after a completely-flat battery reset. Last hope gone.
Now nobody at all is running my custom software I think, and I have no way to fix the bugs.
Could replace it, but I'm not really paying any attention to the things it measures anyway. Heartrate is too unreliable to be useful and steps seems likely to be counting my leg-jiggles since I tend to hit 10,000 most days without trying or leaving the flat.
The software which tracks my time and mood is probably better running on the phone really. Easier to add notes and detail. Can't really input text from a watch. Location data can be added in ways the watch couldn't.
So back to not wearing a watch at all I think. Who needs it now we all carry pocket watches with internet and telephony.
#pineTime #smartWatch

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
Shoichi Koyama, Kenji Ishizuka
https://arxiv.org/abs/2506.16729 https://…

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
A learning-based method for estimating the magnitude distribution of sound fields from spatially sparse measurements is proposed. Estimating the magnitude distribution of acoustic transfer function (ATF) is useful when phase measurements are unreliable or inaccessible and has a wide range of applications related to spatial audio. We propose a neural-network-based method for the ATF magnitude estimation. The key feature of our network architecture is the input and output layers conditioned on so…

To which I say 'define "working class"'.
Andy Haldane - in my view a rather unreliable oracle, although some in the UK heteredox economics world like him.
"Farage is like a tribune for the working class"
https://12ft.io/proxy

Navigating High-Dimensional Backstage: A Guide for Exploring Literature for the Reliable Use of Dimensionality Reduction
Hyeon Jeon, Hyunwook Lee, Yun-Hsin Kuo, Taehyun Yang, Daniel Archambault, Sungahn Ko, Takanori Fujiwara, Kwan-Liu Ma, Jinwook Seo
https://arxiv.org/abs/2506.14820

Navigating High-Dimensional Backstage: A Guide for Exploring Literature for the Reliable Use of Dimensionality Reduction
Visual analytics using dimensionality reduction (DR) can easily be unreliable for various reasons, e.g., inherent distortions in representing the original data. The literature has thus proposed a wide range of methodologies to make DR-based visual analytics reliable. However, the diversity and extensiveness of the literature can leave novice analysts and researchers uncertain about where to begin and proceed. To address this problem, we propose a guide for reading papers for reliable visual ana…

"Electric buses don't like the cold, study finds"
#PublicTransport #Buses #EV #ElectricVehicles

Electric buses don't like the cold, study finds
In 2021, Tompkins Consolidated Area Transit (TCAT) in Ithaca received a grant to procure seven all-electric buses and began a pilot program that didn't go as they'd hoped. In addition to issues with the manufacturers, the buses struggled in Ithaca's hilly terrain and were unreliable, with reduced range, in cold weather.

Mixed-Mode In-Memory Computing: Towards High-Performance Logic Processing In A Memristive Crossbar Array
Nan Du, Ilia Polian, Christopher Bengel, Kefeng Li, Ziang Chen, Xianyue Zhao, Uwe Huebner, Li-Wei Chen, Feng Liu, Massimiliano Di Ventra, Stephan Menzel, Heidemarie Krueger
https://arxiv.org/abs/2506.19063

Mixed-Mode In-Memory Computing: Towards High-Performance Logic Processing In A Memristive Crossbar Array
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable device behavior, which affects data accuracy and efficiency. In this work, the authors present a new computing method that combines two types of operations,those based on electrical resistance and those based on voltage, within each memory cell. This design improv…

TRUST: Test-time Resource Utilization for Superior Trustworthiness
Haripriya Harikumar, Santu Rana
https://arxiv.org/abs/2506.06048 https://

TRUST: Test-time Resource Utilization for Superior Trustworthiness
Standard uncertainty estimation techniques, such as dropout, often struggle to clearly distinguish reliable predictions from unreliable ones. We attribute this limitation to noisy classifier weights, which, while not impairing overall class-level predictions, render finer-level statistics less informative. To address this, we propose a novel test-time optimization method that accounts for the impact of such noise to produce more reliable confidence estimates. This score defines a monotonic subs…

Leakage-Resilient Extractors against Number-on-Forehead Protocols
Eshan Chattopadhyay, Jesse Goodman
https://arxiv.org/abs/2506.12595 https://

Leakage-Resilient Extractors against Number-on-Forehead Protocols
Given a sequence of $N$ independent sources $\mathbf{X}_1,\mathbf{X}_2,\dots,\mathbf{X}_N\sim\{0,1\}^n$, how many of them must be good (i.e., contain some min-entropy) in order to extract a uniformly random string? This question was first raised by Chattopadhyay, Goodman, Goyal and Li (STOC '20), motivated by applications in cryptography, distributed computing, and the unreliable nature of real-world sources of randomness. In their paper, they showed how to construct explicit low-error extracto…

Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks
Laksh Patel, Neel Shanbhag
https://arxiv.org/abs/2506.08024 https://

Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks
Distributed supply-chain optimization demands algorithms that can cope with unreliable communication, unbounded messaging delays, and geographically dispersed agents while still guaranteeing convergence with provable rates. In this work, we introduce DAPD-SCO (Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks), a fully asynchronous primal-dual scheme for network flow allocation over directed acyclic supply-chain graphs. Each edge agent independently updates its local f…

Robust copula estimation for one-shot devices with correlated failure modes
E. Castilla, P. J. Chocano
https://arxiv.org/abs/2506.10152 https://

Robust copula estimation for one-shot devices with correlated failure modes
This paper presents a robust method for estimating copula models to evaluate dependence between failure modes in one-shot devices-systems designed for single use and destroyed upon activation. Traditional approaches, such as maximum likelihood estimation (MLE), often produce unreliable results when faced with outliers or model misspecification. To overcome these limitations, we introduce a divergence-based estimation technique that enhances robustness and provides a more reliable characterizati…

Position: Simulating Society Requires Simulating Thought
Chance Jiajie Li, Jiayi Wu, Zhenze Mo, Ao Qu, Yuhan Tang, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Jinhua Zhao, Paul Liang, Luis Alonso, Kent Larson
https://arxiv.org/abs/2506.06958

Position: Simulating Society Requires Simulating Thought
Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior -- it demands cognitively grounded reasoning that is structured, revisable, and traceable. LLM-based agents are increasingly used to emulate individual and group behavior -- primarily through prompting and supervised fine-tuning. Yet they often lack internal coherence, causal reasoning, and belief traceability -- making them unreliable for analyzing how people reason, deliberate, or …

Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments
Zaiqiang Wu, I-Chao Shen, Takeo Igarashi
https://arxiv.org/abs/2506.12348

Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments
Per-garment virtual try-on methods collect garment-specific datasets and train networks tailored to each garment to achieve superior results. However, these approaches often struggle with loose-fitting garments due to two key limitations: (1) They rely on human body semantic maps to align garments with the body, but these maps become unreliable when body contours are obscured by loose-fitting garments, resulting in degraded outcomes; (2) They train garment synthesis networks on a per-frame basi…

Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions
Asghar Ghorbani, Hanieh Fattahi
https://arxiv.org/abs/2506.12403

Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions
Limited infrastructure, scarce educational resources, and unreliable internet access often hinder physics and photonics education in underdeveloped regions. These barriers create deep inequities in Science, Technology, Engineering, and Mathematics (STEM) education. This article explores how Small Language Models (SLMs)-compact, AI-powered tools that can run offline on low-power devices, offering a scalable solution. By acting as virtual tutors, enabling native-language instruction, and supporti…

On the Synthetic Channels in Polar Codes over Binary-Input Discrete Memoryless Channels
Yadong Jiao, Xiaoyan Cheng, Yuansheng Tang, Ming Xu
https://arxiv.org/abs/2506.04163

On the Synthetic Channels in Polar Codes over Binary-Input Discrete Memoryless Channels
Polar codes introduced by Arikan in 2009 are the first code family achieving the capacity of binary-input discrete memoryless channels (BIDMCs) with low-complexity encoding and decoding. Identifying unreliable synthetic channels in polar code construction is crucial. Currently, because of the large size of the output alphabets of synthetic channels, there is no effective approach to evaluate their reliability, except in the case that the underlying channels are binary erasure channels. This pap…

Packing3D: An Open-Source Analytical Framework for Computing Packing Density and Mixing Indices Using Partial Spherical Volumes
Freddie Barter, Christopher R. K. Windows-Yule
https://arxiv.org/abs/2506.08852

Packing3D: An Open-Source Analytical Framework for Computing Packing Density and Mixing Indices Using Partial Spherical Volumes
Accurate quantification of local packing density and mixing in simulations of particulate systems is essential for many industrial applications. Traditional methods which simply count the number of particle centres within a given volume of space (cell) introduce discontinuities at cell boundaries, leading to unreliable measurement of packing density. We introduce Packing3D.jl, an open-source Julia package providing analytic, partial-volume calculations for spheres intersecting Cartesian and cyl…

What Really is a Member? Discrediting Membership Inference via Poisoning
Neal Mangaokar, Ashish Hooda, Zhuohang Li, Bradley A. Malin, Kassem Fawaz, Somesh Jha, Atul Prakash, Amrita Roy Chowdhury
https://arxiv.org/abs/2506.06003

What Really is a Member? Discrediting Membership Inference via Poisoning
Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often fail under the strict definition of membership based on exact matching, and have suggested relaxing this definition to include semantic neighbors as members as well. In this work, we show that membership inference tests are still unreliable under this relaxation - it is possible to poison the training dataset in a way…

This https://arxiv.org/abs/2506.05339 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on features like length, structure, and style, leading to issues like reward hacking and unreliable evaluations. Evidence suggests these biases originate in artifacts in human training data. In this work, we systematically investigate the relationship between tra…

Replaced article(s) found for cs.SI. https://arxiv.org/list/cs.SI/new
[1/1]:
Bridging Social Media and Search Engines: Dredge Words and the Detection of Unreliable Domains

This https://arxiv.org/abs/2406.02436 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Safe, Out-of-Distribution-Adaptive MPC with Conformalized Neural Network Ensembles
We present SODA-MPC, a Safe, Out-of-Distribution-Adaptive Model Predictive Control algorithm, which uses an ensemble of learned models for prediction, with a runtime monitor to flag unreliable out-of-distribution (OOD) predictions. When an OOD situation is detected, SODA-MPC triggers a safe fallback control strategy based on reachability, yielding a control framework that achieves the high performance of learning-based models while preserving the safety of reachability-based control. We demonst…

ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification
Yiyang Jin, Kunzhao Xu, Hang Li, Xueting Han, Yanmin Zhou, Cheng Li, Jing Bai
https://arxiv.org/abs/2506.11442

ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification
Recent advances in reinforcement learning (RL) with verifiable outcome rewards have significantly improved the reasoning capabilities of large language models (LLMs), especially when combined with multi-turn tool interactions. However, existing methods lack both meaningful verification signals from realistic environments and explicit optimization for verification, leading to unreliable self-verification. To address these limitations, we propose ReVeal, a multi-turn reinforcement learning framew…

Identifiability in epidemic models with prior immunity and under-reporting
Fanny Bergstr\"om, Martina Favero, Tom Britton
https://arxiv.org/abs/2506.07825

Identifiability in epidemic models with prior immunity and under-reporting
Identifiability is the property in mathematical modelling that determines if model parameters can be uniquely estimated from data. For infectious disease models, failure to ensure identifiability can lead to misleading parameter estimates and unreliable policy recommendations. We examine the identifiability of a modified SIR model that accounts for under-reporting and pre-existing immunity in the population. We provide a mathematical proof of the unidentifiability of jointly estimating three pa…

From Tea Leaves to System Maps: Context-awareness in Monitoring Operational Machine Learning Models
Joran Leest, Claudia Raibulet, Patricia Lago, Ilias Gerostathopoulos
https://arxiv.org/abs/2506.10770

From Tea Leaves to System Maps: Context-awareness in Monitoring Operational Machine Learning Models
Machine learning (ML) models in production do not fail due to statistical anomalies in their input data; they fail due to contextual misalignment -- when their environment deviates from training assumptions, leading to unreliable predictions. Effective ML monitoring requires rich contextual information to move beyond detecting statistical shifts toward meaningful alerts and systematic root-cause analysis. Yet, surprisingly, despite extensive research in ML monitoring and related disciplines (dr…

#WritersCoffeeClub
June 10: Where is the line between homage and theft?
Oh, that one's simple. Homage is when I do it.
Jokes aside, it's about motivation and scope, however subjective and unreliable that may be. Treating characters and stories with respect is homage. Indicating that borrowed things are, in fact, borrowed and referring the source is homage. Eventually…

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Yuansheng Ni, Ping Nie, Kai Zou, Xiang Yue, Wenhu Chen
https://arxiv.org/abs/2506.03930

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded supervision and offer limited support for iterative code correction, resulting in fragile and unreliable plot generation. We present VisCode-200K, a large-scale instruction tuning dataset for Python-based visualization and self-correction. It contains over 200K exampl…