Tootfinder

edit_wikinews: Wikipedia news edits (2010)
Two bipartite user-page networks extracted from Wikipedia, about news events. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 61822 nodes and 686017 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

If the "conspiracy" is so huge that only a minority believe it's a "hoax" who exactly is suffering from delusion or attempting to con the gullible? If it walks like a duck, what's the harm in seeing it?

Is Alaska still a State or did we give it back to Russia? (Or was Putin holding out to reclaim Washington state, Oregon, and California?)
Fort Ross California State Historical Park: A Russian Fort by the Sea
https://www.parks.ca.gov/?page_id=26334

Fort Ross SHP: A Russian Fort by the Sea
California State Parks

Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators
Pavel \v{S}indel\'a\v{r}, Ond\v{r}ej Bojar
https://arxiv.org/abs/2507.12143

Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators
ELOQUENT is a set of shared tasks that aims to create easily testable high-level criteria for evaluating generative language models. Sensemaking is one such shared task. In Sensemaking, we try to assess how well generative models ``make sense out of a given text'' in three steps inspired by exams in a classroom setting: (1) Teacher systems should prepare a set of questions, (2) Student systems should answer these questions, and (3) Evaluator systems should score these answers, all adhering ra…

Characterizing Phishing Pages by JavaScript Capabilities
Aleksandr Nahapetyan, Kanv Khare, Kevin Schwarz, Bradley Reaves, Alexandros Kapravelos
https://arxiv.org/abs/2509.13186 …

Characterizing Phishing Pages by JavaScript Capabilities
In 2024, the Anti-Phishing Work Group identified over one million phishing pages. Phishers achieve this scale by using phishing kits -- ready-to-deploy phishing websites -- to rapidly deploy phishing campaigns with specific data exfiltration, evasion, or mimicry techniques. In contrast, researchers and defenders continue to fight phishing on a page-by-page basis and rely on manual analysis to recognize static features for kit identification. This paper aims to aid researchers and analysts by …

Dressing Factors and Mirror Thermodynamic Bethe Ansatz for mixed-flux AdS3/CFT2
Sergey Frolov, Davide Polvara, Alessandro Sfondrini
https://arxiv.org/abs/2507.12191

Dressing Factors and Mirror Thermodynamic Bethe Ansatz for mixed-flux AdS3/CFT2
We complete the derivation of the dressing factors for the $AdS_3\times S^3\times T^4$ S matrix with mixed Ramond--Ramond and Neveu-Schwarz-Neveu-Schwarz flux, in the "string" and "mirror" kinematics. Using these, we propose the mirror Thermodynamic Bethe Ansatz equations which describe the spectrum of the model at any string tension.

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/7]:
- A Pressure-Based Diffusion Model for Influence Maximization on Social Networks
Curt Stutsman, Eliot W. Robson, Abhishek K. Umrawal

Crosslisted article(s) found for math.CT. https://arxiv.org/list/math.CT/new
[1/1]:
- The Classification of 3 1d Symmetry Enriched Topological Order
Thibault D. D\'ecoppet, Matthew Yu

ReCross: Efficient Embedding Reduction Scheme for In-Memory Computing using ReRAM-Based Crossbar
Yu-Hong Lai, Chieh-Lin Tsai, Wen Sheng Lim, Han-Wen Hu, Tei-Wei Kuo, Yuan-Hao Chang
https://arxiv.org/abs/2509.10627

ReCross: Efficient Embedding Reduction Scheme for In-Memory Computing using ReRAM-Based Crossbar
Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due to high memory access costs and irregular access patterns, leading to increased inference time and energy consumption. While resistive random access memory (ReRAM) based crossbars offer a fast and energy-efficient solution through in-memory embedding reductio…

Integration of $\text{Er}^{3 }$-emitters in silicon-on-insulator nanodisks metasurface
Joshua Bader, Hamed Arianfard, Vincenzo Ciavolino, Shin-ichiro Sato, Stefania Castelletto
https://arxiv.org/abs/2509.11592

Integration of $\text{Er}^{3+}$-emitters in silicon-on-insulator nanodisks metasurface
Erbium ($\text{Er}^{3+}$) emitters are relevant for optical applications due to their narrow emission line directly in the telecom C-band due to the ${}^\text{4}\text{I}_{\text{13/2}}$ $\rightarrow$ ${}^\text{4}\text{I}_{\text{15/2}}$ transition at 1.54 $μ$m. Additionally they are promising candidates for future quantum technologies when embedded in thin-film silicon-on-insulator (SOI) to achieve fabrication scalability and CMOS compatibility. In this paper we integrate $\text{Er}^{3+}$ emitte…

Collisional model with dissipative and dephasing baths: Nonadditive effects at strong coupling
Alessandro Prositto, Carlos Ramon-Escandell, Dvira Segal
https://arxiv.org/abs/2509.10988

Collisional model with dissipative and dephasing baths: Nonadditive effects at strong coupling
The repeated interaction model provides a framework for emulating and analyzing the dynamics of open quantum systems. We explore here the dynamics generated by this protocol in a system that is simultaneously coupled to two baths through noncommuting system operators. One bath is made to couple to nondiagonal elements of the system, thus it induces dissipative dynamics, while the other couples to diagonal elements, and by itself it generates pure dephasing. By solving the problem analytically e…

VH-Diffuser: Variable Horizon Diffusion Planner for Time-Aware Goal-Conditioned Trajectory Planning
Ruijia Liu, Ancheng Hou, Shaoyuan Li, Xiang Yin
https://arxiv.org/abs/2509.11930

VH-Diffuser: Variable Horizon Diffusion Planner for Time-Aware Goal-Conditioned Trajectory Planning
Diffusion-based planners have gained significant recent attention for their robustness and performance in long-horizon tasks. However, most existing planners rely on a fixed, pre-specified horizon during both training and inference. This rigidity often produces length-mismatch (trajectories that are too short or too long) and brittle performance across instances with varying geometric or dynamical difficulty. In this paper, we introduce the Variable Horizon Diffuser (VHD) framework, which treat…

EfficientUICoder: Efficient MLLM-based UI Code Generation via Input and Output Token Compression
Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan, Yintong Huo, Yang Liu, Michael R. Lyu
https://arxiv.org/abs/2509.12159

EfficientUICoder: Efficient MLLM-based UI Code Generation via Input and Output Token Compression
Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code generation due to the large number of input image tokens and extensive output code tokens required. Our comprehensive study identifies significant redundancies in both image and code tokens that exacerbate computational complexity and hinder focus on key UI…

Hurst Index of Gamma-Ray Burst Light Curves and Its Statistical Study
Ruo-Yu Guan, Feifei Wang, Yuan-Chuan Zou
https://arxiv.org/abs/2509.11631 https://arx…

Hurst Index of Gamma-Ray Burst Light Curves and Its Statistical Study
Gamma-ray bursts (GRBs) rank among the most powerful astrophysical phenomena, characterized by complex and highly variable prompt emission light curves that reflect the dynamics of their central engines. In this work, we analyze a sample of 163 long-duration GRBs detected by the Burst and Transient Source Experiment (BATSE), applying detrended fluctuation analysis (DFA) to derive the Hurst index as a quantitative descriptor of temporal correlations in the light curves. We further explore statis…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/1]:
- Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms
Keru Wu, Yuansi Chen, Wooseok Ha, Bin Yu

Commenotes: Synthesizing Organic Comments to Support Community-Based Fact-Checking
Shuning Zhang, Linzhi Wang, Dai Shi, Yuwei Chuai, Jingruo Chen, Yunyi Chen, Yifan Wang, Yating Wang, Xin Yi, Hewu Li
https://arxiv.org/abs/2509.11052

Commenotes: Synthesizing Organic Comments to Support Community-Based Fact-Checking
Community-based fact-checking is promising to reduce the spread of misleading posts at scale. However, its effectiveness can be undermined by the delays in fact-check delivery. Notably, user-initiated organic comments often contain debunking information and have the potential to help mitigate this limitation. Here, we investigate the feasibility of synthesizing comments to generate timely high-quality fact-checks. To this end, we analyze over 2.2 million replies on X and introduce Commenotes, a…

Brown Dwarf Formation Through Gravitational Collapse: Insights From 3D Numerical Simulations
Adnan Ali Ahmad, Beno\^it Commer\c{c}on, Gilles Chabrier, Antonin Borderies
https://arxiv.org/abs/2509.12336

Brown Dwarf Formation Through Gravitational Collapse: Insights From 3D Numerical Simulations
The formation mechanism of Brown Dwarfs (BDs), whether akin to stars or ejected planetary-mass objects, remains debated. We present the first 3D radiation-MHD simulations of magnetized, turbulent, gravitationally unstable low-mass cores ($0.05-0.1\ \mathrm{M_{\odot}}$) collapsing into proto-BDs. Using the {\ttfamily RAMSES} code with adaptive mesh refinement, we model the full dynamical range ($10^{5}~-10^{22}\ \mathrm{cm^{-3}}$), including radiative transfer (flux limited diffusion) and non-id…

Replaced article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[1/1]:
- Digital Discrimination in Dating Apps and the Dutch Breeze case
Tim de Jonge, Frederik Zuiderveen Borgesius

President Trump files a 40-page amended $15B defamation complaint against the NYT and others, after a judge initially dismissed it on Sept. 19 due to its length (The Guardian)
https://www.theguardian.com/us-news/2025/oct/16/trump-new-york-times-defam…

Replaced article(s) found for cond-mat.mtrl-sci. https://arxiv.org/list/cond-mat.mtrl-sci/new
[1/1]:
- Utilizing a machine-learned potential to explore enhanced radiation tolerance in the MoNbTaVW hig...
Jiahui Liu, Jesper Byggmastar, Zheyong Fan, Bing Bai, Pi…

Replaced article(s) found for math.LO. https://arxiv.org/list/math.LO/new
[1/1]:
- Analytic Hardy fields
Matthias Aschenbrenner, Lou van den Dries
https://

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Tomer Bitan, Tal Kadosh, Erel Kaplan, Shira Meiri, Le Chen, Peter Morales, Niranjan Hasabnis, Gal Oren
https://arxiv.org/abs/2509.12136

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Translating programs between various parallel programming languages is an important problem in the high-performance computing (HPC) community. Existing tools for this problem are either too narrow in scope and/or outdated. Recent explosive growth in the popularity of large language models (LLMs) and their ability to generate and translate code offers a potential alternative approach. Toward that end, we first need to systematically evaluate the ability of LLMs to translate between parallel lang…

Hanlon-Hicks-Lazarev resolution revisited
Lev Borisov, Zengrui Han
https://arxiv.org/abs/2509.11077 https://arxiv.org/pdf/2509.11077

Hanlon-Hicks-Lazarev resolution revisited
Hanlon, Hicks and Lazarev constructed resolutions of structure sheaves of toric substacks by certain line bundles on the ambient toric stacks. In this paper, we give a new and substantially simpler proof of their result.

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Payal Bhattad, Sai Manoj Pudukotai Dinakarrao, Anju Gupta
https://arxiv.org/abs/2507.12126

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Text data augmentation is a widely used strategy for mitigating data sparsity in natural language processing (NLP), particularly in low-resource settings where limited samples hinder effective semantic modeling. While augmentation can improve input diversity and downstream interpretability, existing techniques often lack mechanisms to ensure semantic preservation during large-scale or iterative generation, leading to redundancy and instability. This work introduces a principled evaluation frame…

"I didn't say what I said" -- Kash Patel
https://www.theguardian.com/us-news/live/2…

Quantum Storage of Qubits in an Array of Independently Controllable Solid-State Quantum Memories
Markus Teller, Susana Plascencia, Samuele Grandi, Hugues de Riedmatten
https://arxiv.org/abs/2509.11910 …

Quantum Storage of Qubits in an Array of Independently Controllable Solid-State Quantum Memories
Random-access quantum memories may offer computational advantages for quantum computers and networks. In this paper, we advance arrays of solid-state quantum memories towards their usage as random-access quantum memory. We perform quantum storage of path and time-bin qubits implemented with weak coherent states at the single-photon level, in an array of ten temporally-multiplexed memory cells with controllable addressing. The qubits can be stored in arbitrary combinations of memory cells, from …

Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
Travis Davies, Yiqi Huang, Yunxin Liu, Xiang Chen, Huxian Liu, Luhui Hu
https://arxiv.org/abs/2509.11865

Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
Scaling Transformer policies and diffusion models has advanced robotic manipulation, yet combining these techniques in lightweight, cross-embodiment learning settings remains challenging. We study design choices that most affect stability and performance for diffusion-transformer policies trained on heterogeneous, multimodal robot data, and introduce Tenma, a lightweight diffusion-transformer for bi-manual arm control. Tenma integrates multiview RGB, proprioception, and language via a cross-emb…

Findings of MEGA: Maths Explanation with LLMs using the Socratic Method for Active Learning
Tosin Adewumi, Foteini Simistira Liwicki, Marcus Liwicki, Viktor Gardelli, Lama Alkhaled, Hamam Mokayed
https://arxiv.org/abs/2507.12079

Findings of MEGA: Maths Explanation with LLMs using the Socratic Method for Active Learning
This paper presents an intervention study on the effects of the combined methods of (1) the Socratic method, (2) Chain of Thought (CoT) reasoning, (3) simplified gamification and (4) formative feedback on university students' Maths learning driven by large language models (LLMs). We call our approach Mathematics Explanations through Games by AI LLMs (MEGA). Some students struggle with Maths and as a result avoid Math-related discipline or subjects despite the importance of Maths across many fie…

A New Benchmark for Evaluating Code Translation with Third-Party Libraries
Pengyu Xue, Kunwu Zheng, Zhen Yang, Yifei Pei, Linhao Wu, Jiahui Dong, Xiapu Luo, Yan Xiao, Fei Liu, Yuxuan Zhang, Xiran Lyu, Xianhang Li, Xuanyu Zhu, Chengyi Wang
https://arxiv.org/abs/2509.12087

A New Benchmark for Evaluating Code Translation with Third-Party Libraries
In recent years, Large Language Models (LLMs) have been widely studied in the code translation field on the method, class, and even repository levels. However, most of these benchmarks are limited in terms of Third-Party Library (TPL) categories and scales, making TPL-related errors hard to expose and hindering the development of targeted solutions. Considering the high dependence (over 90%) on TPLs in practical programming, demystifying and analyzing LLMs' code translation performance involvin…

Vocabuild: An Accessible Augmented Tangible Interface for Gamified Vocabulary Learning of Constructing Meaning
Siying Hu, Zhenhao Zhang
https://arxiv.org/abs/2509.11027 https://…

Vocabuild: An Accessible Augmented Tangible Interface for Gamified Vocabulary Learning of Constructing Meaning
Vocabulary acquisition in early education often relies on rote memorization and passive screen-based tools, which can fail to engage students kinesthetically and collaboratively. This paper introduces Vocabuild, an augmented tangible interface designed to transform vocabulary learning into an active, embodied, and playful experience. The system combines physical letter blocks with a projection-augmented surface. As children physically construct words with the blocks, the system provides real-ti…

Crosslisted article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[1/1]:
- V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Exams
Duong Q. Nguyen, Quy P. Nguyen, Nguyen Van Nhon, Quang-Thinh Bui, H. Nguyen-Xuan

Crosslisted article(s) found for math.LO. https://arxiv.org/list/math.LO/new
[1/1]:
- Amenability, Optimal Transport and Abstract Ergodic Theorems
Christian Rosendal

One of today's non-political headlines could accurately read:
"Robert Redford, former student of Van Nuys High School, dies aged 89"
(For those who don't know, Van Nuys High is where many of those who created the Internet went before moving on to UCLA and Stanford. I also went to Van Nuys High, but somebody keeps removing me from the school's Wikipedia page.)

Replaced article(s) found for hep-th. https://arxiv.org/list/hep-th/new
[2/2]:
- Spin Precession in magnetized Kerr spacetime
Karthik Iyer (MCNS, India), Chandrachur Chakraborty (MCNS, India)

BOOKCOREF: Coreference Resolution at Book Scale
Giuliano Martinelli, Tommaso Bonomo, Pere-Llu\'is Huguet Cabot, Roberto Navigli
https://arxiv.org/abs/2507.12075

BOOKCOREF: Coreference Resolution at Book Scale
Coreference Resolution systems are typically evaluated on benchmarks containing small- to medium-scale documents. When it comes to evaluating long texts, however, existing benchmarks, such as LitBank, remain limited in length and do not adequately assess system capabilities at the book scale, i.e., when co-referring mentions span hundreds of thousands of tokens. To fill this gap, we first put forward a novel automatic pipeline that produces high-quality Coreference Resolution annotations on ful…

Comment on "Properties and dynamics of generalized squeezed states"
Rub\'en Gordillo, Ricardo Puebla
https://arxiv.org/abs/2507.12250 https:/…

Comment on "Properties and dynamics of generalized squeezed states"
A recent article [S. Ashhab and M. Ayyash, New J. Phys. 27, 054104 (2025)] has reported unexpected oscillatory dynamics in generalized squeezed states of order higher than two as their squeezing parameter increases. This behaviour, observed through numerical simulations using truncated bosonic annihilation and creation operators, appeared in several properties of these states, including their average photon number. The authors argued that these oscillations reflect a genuine physical effect. He…

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[2/2]:
- On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles
Xingyu Zhao, Robab Aghazadeh-Chakherlou, Chih-Hong Cheng, Peter Popov, Lorenzo Strigini

Towards the Next Generation of Software: Insights from Grey Literature on AI-Native Applications
Lingli Cao, Shanshan Li, Ying Fan, Danyang Li, Chenxing Zhong
https://arxiv.org/abs/2509.13144

Towards the Next Generation of Software: Insights from Grey Literature on AI-Native Applications
Background: The rapid advancement of large language models (LLMs) has given rise to AI-native applications, a new paradigm in software engineering that fundamentally redefines how software is designed, developed, and evolved. Despite their growing prominence, AI-native applications still lack a unified engineering definition and architectural blueprint, leaving practitioners without systematic guidance for system design, quality assurance, and technology selection. Objective: This study seeks…

When Your Boss Is an AI Bot: Exploring Opportunities and Risks of Manager Clone Agents in the Future Workplace
Qing (Diane), Hu, Qing Xiao, Hancheng Cao, Hong Shen
https://arxiv.org/abs/2509.10993

When Your Boss Is an AI Bot: Exploring Opportunities and Risks of Manager Clone Agents in the Future Workplace
As Generative AI (GenAI) becomes increasingly embedded in the workplace, managers are beginning to create Manager Clone Agents - AI-powered digital surrogates that are trained on their work communications and decision patterns to perform managerial tasks on their behalf. To investigate this emerging phenomenon, we conducted six design fiction workshops (n = 23) with managers and workers, in which participants co-created speculative scenarios and discussed how Manager Clone Agents might transfor…

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy
Yukun Zhang, TianYang Zhang
https://arxiv.org/abs/2509.13265 https://

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy
This paper conceptualizes Large Language Models (LLMs) as a form of mixed public goods within digital infrastructure, analyzing their economic properties through a comprehensive theoretical framework. We develop mathematical models to quantify the non-rivalry characteristics, partial excludability, and positive externalities of LLMs. Through comparative analysis of open-source and closed-source development paths, we identify systematic differences in resource allocation efficiency, innovation t…

Splittings in varieties of logic
Brian A. Davey, Tomasz Kowalski, Christopher J. Taylor
https://arxiv.org/abs/2509.11623 https://arxiv.org/pdf/2509.11623…

Splittings in varieties of logic
We study splittings, or lack of them, in lattices of subvarieties of some logic-related varieties. We present a general lemma, the Non-Splitting Lemma, which when combined with some variety-specific constructions, yields each of our negative results: the variety of commutative integral residuated lattices contains no splittings algebras, and in the varieties of double Heyting algebras, dually pseudocomplemented Heyting algebras and regular double p-algebras the only splitting algebras are the t…

Replaced article(s) found for hep-th. https://arxiv.org/list/hep-th/new
[1/2]:
- Line Defects in Fermionic CFTs
Simone Giombi, Elizabeth Helfenberger, Himanshu Khanchandani

Relations between parameters of the Hamiltonian and Neel-type states in the anisotropic Heisenberg model
Pavel Babaian, Gennady Koval
https://arxiv.org/abs/2507.12225

Relations between parameters of the Hamiltonian and Neel-type states in the anisotropic Heisenberg model
This article investigates Neel-type states in the anisotropic Heisenberg model with an external field. For arbitrary spin $s$ and arbitrary dimension of the space $d$ we find the expressions relating the angles which define the directions of spin polarisation to the parameters of the Hamiltonian.

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[1/2]:
- Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability throu...
Fern\'andez-Becerra, Gonz\'alez-Santamarta, Guerrero-Higueras, Rodr\'iguez-Lera, Olivera…

Optimizing Code Embeddings and ML Classifiers for Python Source Code Vulnerability Detection
Talaya Farasat, Joachim Posegga
https://arxiv.org/abs/2509.13134 https://

Optimizing Code Embeddings and ML Classifiers for Python Source Code Vulnerability Detection
In recent years, the growing complexity and scale of source code have rendered manual software vulnerability detection increasingly impractical. To address this challenge, automated approaches leveraging machine learning and code embeddings have gained substantial attention. This study investigates the optimal combination of code embedding techniques and machine learning classifiers for vulnerability detection in Python source code. We evaluate three embedding techniques, i.e., Word2Vec, CodeBE…

The Digital Landscape of God: Narrative, Visuals and Viewer Engagement of Religious Videos on YouTube
Rongyi Chen, Ziyan Xin, Qing Xiao, Ruiwei Xiao, Jingjia Xiao, Bingbing Zhang, Hong Shen, Zhicong Lu
https://arxiv.org/abs/2509.10957

The Digital Landscape of God: Narrative, Visuals and Viewer Engagement of Religious Videos on YouTube
The digital transformation of religious practice has reshaped how billions of people engage with spiritual content, with video-sharing platforms becoming central to contemporary religious communication. Yet HCI research lacks systematic understanding of how narrative and visual elements create meaningful spiritual experiences and foster viewer engagement. We present a mixed-methods study of religious videos on YouTube across major religions, developing taxonomies of narrative frameworks, visual…

Designing the Hybrid Cooperative: A Socio-Technical Architecture for Scalable, Global Coordination Using Blockchain
Henrik Axelsen, Jan Damsgaard
https://arxiv.org/abs/2509.13156

Designing the Hybrid Cooperative: A Socio-Technical Architecture for Scalable, Global Coordination Using Blockchain
Blockchain has been promoted as a remedy for coordination in fragmented, multi-stakeholder ecosystems, yet many projects stall at pilot stage. Using a design-science approach, we develop the Hybrid Cooperative (HC), a digitally native governance architecture that combines smart-contract coordination with a minimal, code-deferent legal interface and jurisdictional modules. This selective decentralization decentralizes rules where programmability lowers agency and verification costs, and centrali…

Kites and representations of pseudo MV-algebras
Michal Botur, Tomasz Kowalski
https://arxiv.org/abs/2509.11603 https://arxiv.org/pdf/2509.11603

Kites and representations of pseudo MV-algebras
We investigate the structure of perfect residuated lattices, focussing especially on perfect pseudo MV-algebras. We show that perfect pseudo MV-algebras can be represented as a generalised version of kites of Dvurečenskij and Kowalski, and that they are categorically equivalent to $\ell$-groups with a distinguished automorphism. We then characterise varieties generated by kites and describe the lattice of these varieties as a complete sublattice of the lattice of perfectly generated varieties …

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
Farideh Majidi, Ziaeddin Beheshtifard
https://arxiv.org/abs/2507.11634

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples o…

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[3/3]:
- UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction
Yunxuan Mao, Rong Xiong, Yue Wang, Yiyi Liao

AI Hasn't Fixed Teamwork, But It Shifted Collaborative Culture: A Longitudinal Study in a Project-Based Software Development Organization (2023-2025)
Qing Xiao, Xinlan Emily Hu, Mark E. Whiting, Arvind Karunakaran, Hong Shen, Hancheng Cao
https://arxiv.org/abs/2509.10956

AI Hasn't Fixed Teamwork, But It Shifted Collaborative Culture: A Longitudinal Study in a Project-Based Software Development Organization (2023-2025)
When AI entered the workplace, many believed it could reshape teamwork as profoundly as it boosted individual productivity. Would AI finally ease the longstanding challenges of team collaboration? Our findings suggested a more complicated reality. We conducted a longitudinal two-wave interview study (2023-2025) with members (N=15) of a project-based software development organization to examine the expectations and use of AI in teamwork. In early 2023, just after the release of ChatGPT, particip…

Introducing the A2AJ's Canadian Legal Data: An open-source alternative to CanLII for the era of computational law
Simon Wallace, Sean Rehaag
https://arxiv.org/abs/2509.13032

Introducing the A2AJ's Canadian Legal Data: An open-source alternative to CanLII for the era of computational law
The Access to Algorithmic Justice project (A2AJ) is an open-source alternative to the Canadian Legal Information Institute (CanLII). At a moment when technology promises to enable new ways of working with law, CanLII is becoming an impediment to the free access of law and access to justice movements because it restricts bulk and programmatic access to Canadian legal data. This means that Canada is staring down a digital divide: well-resourced actors have the best new technological tools and, be…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/3]:
- From Semantic Web and MAS to Agentic AI: A Unified Narrative of the Web of Agents
Tatiana Petrova, Boris Bliznioukov, Aleksandr Puzikov, Radu State

Some applications of finite BL-algebras
Cristina Flaut, Dana Piciu, Bianca Liana Bercea-Straton
https://arxiv.org/abs/2509.10915 https://arxiv.org/pdf/2509…

Some applications of finite BL-algebras
In this paper we present an encryption/decryption algorithm which use properties of finite MV-algebras, we proved that there are no commutative and unitary rings R such that Id (R) = L,where L is a finite BL-algebra which is not an MV-algebra and we give a method to generate BL-comets. Moreover, we give a final characterisation of finite BL-algebra and we proved that a finite BL-algebra is a comet or MV-algebras which are not chains.

Can GenAI Move from Individual Use to Collaborative Work? Experiences, Challenges, and Opportunities of Integrating GenAI into Collaborative Newsroom Routines
Qing Xiao (Diane), Qing (Diane), Hu, Jingjia Xiao, Hancheng Cao, Hong Shen
https://arxiv.org/abs/2509.10950

Can GenAI Move from Individual Use to Collaborative Work? Experiences, Challenges, and Opportunities of Integrating GenAI into Collaborative Newsroom Routines
Generative AI (GenAI) is reshaping work, but adoption remains largely individual and experimental rather than integrated into collaborative routines. Whether GenAI can move from individual use to collaborative work is a critical question for future organizations. Journalism offers a compelling site to examine this shift: individual journalists have already been disrupted by GenAI tools; yet newswork is inherently collaborative relying on shared routines and coordinated workflows. We conducted 2…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
- Large Language Models Often Know When They Are Being Evaluated
Joe Needham, Giles Edkins, Govind Pimpale, Henning Bartsch, Marius Hobbhahn

An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
Elinor Poole-Dayan, Deb Roy, Jad Kabbara
https://arxiv.org/abs/2509.12577 https://

An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
In an era of increasing societal fragmentation, political polarization, and erosion of public trust in institutions, representative deliberative assemblies are emerging as a promising democratic forum for developing effective policy outcomes on complex global issues. Despite theoretical attention, there remains limited empirical work that systematically traces how specific ideas evolve, are prioritized, or are discarded during deliberation to form policy recommendations. Addressing these gaps, …

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/3]:
- RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
Jennifer Hsia, Afreen Shaikh, Zhiruo Wang, Graham Neubig

Crisis Messaging Journeys: Epistemic Struggles over CDC Guidance During COVID-19
Tawfiq Ammari
https://arxiv.org/abs/2509.10906 https://arxiv.org/pdf/2509.…

Crisis Messaging Journeys: Epistemic Struggles over CDC Guidance During COVID-19
This study investigates how the U.S. Centers for Disease Control and Prevention (CDC) communicated COVID-19 guidance on Twitter and how publics responded over two years of the pandemic. Drawing on 275,124 tweets mentioning or addressing @CDCgov, I combine BERTopic modeling, sentiment analysis (VADER), credibility checks (Iffy Index), change point detection (PELT), and survival analysis to trace three phases of discourse: (1) early hoax claims and testing debates, (2) lockdown and mask controver…

Qualitative Research in an Era of AI: A Pragmatic Approach to Data Analysis, Workflow, and Computation
Corey M. Abramson, Zhuofan Li, Tara Prendergast, Daniel Dohan
https://arxiv.org/abs/2509.12503

Qualitative Research in an Era of AI: A Pragmatic Approach to Data Analysis, Workflow, and Computation
Rapid computational developments - particularly the proliferation of artificial intelligence (AI) - increasingly shape social scientific research while raising new questions about in-depth qualitative methods such as ethnography and interviewing. Building on classic debates about using computers to analyze qualitative data, we revisit longstanding concerns and assess possibilities and dangers in an era of automation, AI chatbots, and 'big data.' We first historicize developments by revisiting c…

Language Models Improve When Pretraining Data Matches Target Tasks
David Mizrahi, Anders Boesen Lindbo Larsen, Jesse Allardice, Suzie Petryk, Yuri Gorokhov, Jeffrey Li, Alex Fang, Josh Gardner, Tom Gunter, Afshin Dehghan
https://arxiv.org/abs/2507.12466

Language Models Improve When Pretraining Data Matches Target Tasks
Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine accordingly. This raises a natural question: what happens when we make this optimization explicit? To explore this, we propose benchmark-targeted ranking (BETR), a simple method that selects pretraining documents based on similarity to benchmark training examp…

Tracer: A Forensic Framework for Detecting Fraudulent Speedruns from Game Replays
Jaeung Franciskus Yoo, Huy Kang Kim
https://arxiv.org/abs/2509.10848 https://

Tracer: A Forensic Framework for Detecting Fraudulent Speedruns from Game Replays
Speedrun, a practice of completing a game as quickly as possible, has fostered vibrant communities driven by creativity, competition, and mastery of game mechanics and motor skills. However, this contest also attracts malicious actors as financial incentives come into play. As media and software manipulation techniques advance - such as spliced footage, modified game software and live stream with staged setups - forged speedruns have become increasingly difficult to detect. Volunteer-driven com…

Funding AI for Good: A Call for Meaningful Engagement
Hongjin Lin, Anna Kawakami, Catherine D'Ignazio, Kenneth Holstein, Krzysztof Gajos
https://arxiv.org/abs/2509.12455 htt…

Funding AI for Good: A Call for Meaningful Engagement
Artificial Intelligence for Social Good (AI4SG) is a growing area exploring AI's potential to address social issues like public health. Yet prior work has shown limited evidence of its tangible benefits for intended communities, and projects frequently face inadequate community engagement and sustainability challenges. Funding agendas play a crucial role in framing AI4SG initiatives and shaping their approaches. Through a qualitative analysis of 35 funding documents -- representing about $410 m…

S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling
Suman Adhya, Debarshi Kumar Sanyal
https://arxiv.org/abs/2507.12451 https://

S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling
Modeling latent representations in a hyperspherical space has proven effective for capturing directional similarities in high-dimensional text data, benefiting topic modeling. Variational autoencoder-based neural topic models (VAE-NTMs) commonly adopt the von Mises-Fisher prior to encode hyperspherical structure. However, VAE-NTMs often suffer from posterior collapse, where the KL divergence term in the objective function highly diminishes, leading to ineffective latent representations. To miti…

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
Yike Shi (Diane), Qing Xiao (Diane), Qing (Diane), Hu, Hong Shen, Hua Shen
https://arxiv.org/abs/2509.10830

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
Large language models can influence users through conversation, creating new forms of dark patterns that differ from traditional UX dark patterns. We define LLM dark patterns as manipulative or deceptive behaviors enacted in dialogue. Drawing on prior work and AI incident reports, we outline a diverse set of categories with real-world examples. Using them, we conducted a scenario-based study where participants (N=34) compared manipulative and neutral LLM responses. Our results reveal that recog…

Prompt Commons: Collective Prompting as Governance for Urban AI
Rashid Mushkani
https://arxiv.org/abs/2509.12415 https://arxiv.org/pdf/2509.12415

Prompt Commons: Collective Prompting as Governance for Urban AI
Large Language Models (LLMs) are entering urban governance, yet their outputs are highly sensitive to prompts that carry value judgments. We propose Prompt Commons - a versioned, community-maintained repository of prompts with governance metadata, licensing, and moderation - to steer model behaviour toward pluralism. Using a Montreal dataset (443 human prompts; 3,317 after augmentation), we pilot three governance states (open, curated, veto-enabled). On a contested policy benchmark, a single-au…

Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
Yik Siu Chan, Zheng-Xin Yong, Stephen H. Bach
https://arxiv.org/abs/2507.12428

Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
Open-weights reasoning language models generate long chains-of-thought (CoTs) before producing a final response, which improves performance but introduces additional alignment risks, with harmful content often appearing in both the CoTs and the final outputs. In this work, we investigate if we can use CoTs to predict final response misalignment. We evaluate a range of monitoring approaches, including humans, highly-capable large language models, and text classifiers, using either CoT text or ac…

"I thought it was my mistake, but it's really the design'': A Critical Examination of the Accessibility of User-Enacted Moderation Tools on Facebook and X
Sudhamshu Hosamane, Alyvia Walters, Yao Lyu, Shagun Jhaver
https://arxiv.org/abs/2509.10789

"I thought it was my mistake, but it's really the design'': A Critical Examination of the Accessibility of User-Enacted Moderation Tools on Facebook and X
As social media platforms increasingly promote the use of user-enacted moderation tools (e.g., reporting, blocking, content filters) to address online harms, it becomes crucially important that such controls are usable for everyone. We evaluate the accessibility of these moderation tools on two mainstream platforms -- Facebook and X -- through interviews and task-based walkthroughs with 15 individuals with vision impairments. Adapting the lens of \emph{administrative burden of safety work}, we …

Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data
Chandana Cheerla
https://arxiv.org/abs/2507.12425 https://

Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data
Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are limited by static pretraining, short context windows, and challenges in processing heterogeneous data formats. Conventional Retrieval-Augmented Generation (RAG) frameworks address some of these gaps but often struggle with structured and semi-structured data.…

Do Teachers Dream of GenAI Widening Educational (In)equality? Envisioning the Future of K-12 GenAI Education from Global Teachers' Perspectives
Ruiwei Xiao, Qing Xiao, Xinying Hou, Phenyo Phemelo Moletsane, Hanqi Jane Li, Hong Shen, John Stamper
https://arxiv.org/abs/2509.10782

Do Teachers Dream of GenAI Widening Educational (In)equality? Envisioning the Future of K-12 GenAI Education from Global Teachers' Perspectives
Generative artificial intelligence (GenAI) is rapidly entering K-12 classrooms worldwide, initiating urgent debates about its potential to either reduce or exacerbate educational inequalities. Drawing on interviews with 30 K-12 teachers across the United States, South Africa, and Taiwan, this study examines how teachers navigate this GenAI tension around educational equalities. We found teachers actively framed GenAI education as an equality-oriented practice: they used it to alleviate pre-exis…

Probing for Arithmetic Errors in Language Models
Yucheng Sun, Alessandro Stolfo, Mrinmaya Sachan
https://arxiv.org/abs/2507.12379 https://

Probing for Arithmetic Errors in Language Models
We investigate whether internal activations in language models can be used to detect arithmetic errors. Starting with a controlled setting of 3-digit addition, we show that simple probes can accurately decode both the model's predicted output and the correct answer from hidden states, regardless of whether the model's output is correct. Building on this, we train lightweight error detectors that predict model correctness with over 90% accuracy. We then extend our analysis to structured chain-of…

Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices
Ruiwei Xiao, Qing Xiao, Xinying Hou, Hanqi Jane Li, Phenyo Phemelo Moletsane, Hong Shen, John Stamper
https://arxiv.org/abs/2509.10780

Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices
Generative AI (GenAI) is rapidly entering K-12 classrooms, offering teachers new ways for teaching practices. Yet GenAI models are often trained on culturally uneven datasets, embedding a "default culture" that often misaligns with local classrooms. To understand how teachers navigate this gap, we defined the new concept Cultural Distance (the gap between GenAI's default cultural repertoire and the situated demands of teaching practice) and conducted in-depth interviews with 30 K-12 teachers, 1…

Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
Meysam Alizadeh, Fabrizio Gilardi, Zeynab Samei, Mohsen Mosleh
https://arxiv.org/abs/2507.12372

Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
Large language models (LLMs) have traditionally relied on static training data, limiting their knowledge to fixed snapshots. Recent advancements, however, have equipped LLMs with web browsing capabilities, enabling real time information retrieval and multi step reasoning over live web content. While prior studies have demonstrated LLMs ability to access and analyze websites, their capacity to directly retrieve and analyze social media data remains unexplored. Here, we evaluate whether web brows…

Bonsai: Intentional and Personalized Social Media Feeds
Omar El Malki, Marianne Aubin Le Qu\'er\'e, Andr\'es Monroy-Hern\'andez, Manoel Horta Ribeiro
https://arxiv.org/abs/2509.10776

Bonsai: Intentional and Personalized Social Media Feeds
Modern social media feeds use predictive models to maximize engagement, often misaligning how people consume content with how they wish to. We introduce Bonsai, a system that enables people to build personalized and intentional feeds. Bonsai implements a platform-agnostic framework comprising Planning, Sourcing, Curating, and Ranking modules. Altogether, this framework allows users to express their intent in natural language and exert fine-grained control over a procedurally transparent feed cr…

Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
Ana Davila, Jacinto Colan, Yasuhisa Hasegawa
https://arxiv.org/abs/2507.12370

Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llam…

Exploring Gender Bias in Alzheimer's Disease Detection: Insights from Mandarin and Greek Speech Perception
Liu He, Yuanchao Li, Rui Feng, XinRan Han, Yin-Long Liu, Yuwei Yang, Zude Zhu, Jiahong Yuan
https://arxiv.org/abs/2507.12356

Exploring Gender Bias in Alzheimer's Disease Detection: Insights from Mandarin and Greek Speech Perception
Gender bias has been widely observed in speech perception tasks, influenced by the fundamental voicing differences between genders. This study reveals a gender bias in the perception of Alzheimer's Disease (AD) speech. In a perception experiment involving 16 Chinese listeners evaluating both Chinese and Greek speech, we identified that male speech was more frequently identified as AD, with this bias being particularly pronounced in Chinese speech. Acoustic analysis showed that shimmer values in…

LubDubDecoder: Bringing Micro-Mechanical Cardiac Monitoring to Hearables
Siqi Zhang, Xiyuxing Zhang, Duc Vu, Tao Qiang, Clara Palacios, Jiangyifei Zhu, Yuntao Wang, Mayank Goel, Justin Chan
https://arxiv.org/abs/2509.10764

LubDubDecoder: Bringing Micro-Mechanical Cardiac Monitoring to Hearables
We present LubDubDecoder, a system that enables fine-grained monitoring of micro-cardiac vibrations associated with the opening and closing of heart valves across a range of hearables. Our system transforms the built-in speaker, the only transducer common to all hearables, into an acoustic sensor that captures the coarse "lub-dub" heart sounds, leverages their shared temporal and spectral structure to reconstruct the subtle seismocardiography (SCG) and gyrocardiography (GCG) waveforms, and extr…

Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization
Prashanth Vijayaraghavan, Apoorva Nitsure, Charles Mackin, Luyao Shi, Stefano Ambrogio, Arvind Haran, Viresh Paruthi, Ali Elzein, Dan Coops, David Beymer, Tyler Baldwin, Ehsan Degan
https://arxiv.org/abs/2507.12308

Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization
Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains, demonstrating their adaptability and effectiveness. In the realm of Electronic Design Automation (EDA), LLMs show promise for tasks like Register-Transfer Level (RTL) code generation and summarization. However, despite the proliferation of LLMs for general code-related tasks, there's a dearth of research focused on evaluating and refining these models for hardware description languages (HDLs), notably VHD…

Unbounded: Object-Boundary Interactions in Mixed Reality
Zhuoyue Lyu, Per Ola Kristensson
https://arxiv.org/abs/2509.10750 https://arxiv.org/pdf/2509.10750…

Unbounded: Object-Boundary Interactions in Mixed Reality
Boundaries such as walls, windows, and doors are ubiquitous in the physical world, yet their potential in Mixed Reality (MR) remains underexplored. We present Unbounded, a Research through Design inquiry into Object-Boundary Interactions (OBIs). Building on prior work, we articulate a design space aimed at providing a shared language for OBIs. To demonstrate its potential, we design and implement eight examples across productivity and art exploration scenarios, showcasing how boundaries can enr…

Text-ADBench: Text Anomaly Detection Benchmark based on LLMs Embedding
Feng Xiao, Jicong Fan
https://arxiv.org/abs/2507.12295 https://

Text-ADBench: Text Anomaly Detection Benchmark based on LLMs Embedding
Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation identification, spam detection and content moderation, etc. Despite significant advances in large language models (LLMs) and anomaly detection algorithms, the absence of standardized and comprehensive benchmarks for evaluating the existing anomaly detection methods on text data limits rigorous comparison and development of innovative approaches. This work pe…

Remotely Seeing Is Believing: How Trust in Cyber-Physical Systems Evolves Through Virtual Observation
Zhi Hua Jin, Kurt Xiao, David Hyde
https://arxiv.org/abs/2509.10749 https:/…

Remotely Seeing Is Believing: How Trust in Cyber-Physical Systems Evolves Through Virtual Observation
In this paper, we develop a virtual laboratory for measuring human trust. Our laboratory, which is realized as a web application, enables researchers to show pre-recorded or live video feeds to groups of users in a synchronized fashion. Users are able to provide real-time feedback on these videos via affect buttons and a freeform chat interface. We evaluate our application via a quantitative user study ($N \approx 80$) involving videos of cyber-physical systems, such as autonomous vehicles, per…

Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
Johann Frei, Nils Feldhus, Lisa Raithel, Roland Roller, Alexander Meyer, Frank Kramer
https://arxiv.org/abs/2507.12261

Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
For clinical data integration and healthcare services, the HL7 FHIR standard has established itself as a desirable format for interoperability between complex health data. Previous attempts at automating the translation from free-form clinical notes into structured FHIR resources rely on modular, rule-based systems or LLMs with instruction tuning and constrained decoding. Since they frequently suffer from limited generalizability and structural inconformity, we propose an end-to-end framework p…

Emerging Patterns of GenAI Use in K-12 Science and Mathematics Education
Lief Esbenshade (Victor), Shawon Sarkar (Victor), Drew Nucci (Victor), Ann Edwards (Victor), Sarah Nielsen (Victor), Joshua M. Rosenberg (Victor), Alex Liu (Victor), Zewei (Victor), Tian, Min Sun, Zachary Zhang, Thomas Han, Yulia Lapicus, Kevin He
https://arxiv.org/…

Emerging Patterns of GenAI Use in K-12 Science and Mathematics Education
In this report, we share findings from a nationally representative survey of US public school math and science teachers, examining current generative AI (GenAI) use, perceptions, constraints, and institutional support. We show trends in math and science teacher adoption of GenAI, including frequency and purpose of use. We describe how teachers use GenAI with students and their beliefs about GenAI's impact on student learning. We share teachers' reporting on the school and district support they …

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu
https://arxiv.org/abs/2507.12260

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
In this paper, we propose the first quantitative measure for translationese -- the translationese-index (T-index) for graded and generalizable measurement of translationese, computed from the likelihood ratios of two contrastively fine-tuned language models (LMs). We use a synthesized dataset and a dataset with translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments. Our results show that T-index is both robust and effici…

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
Jingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang, Bingcan Guo, Ibrahim Khalilov, Simret Araya Gebreegziabher, Bingsheng Yao, Dakuo Wang, Yanfang Ye, Tianshi Li, Ziang Xiao, Yaxing Yao, Toby Jia-Jun Li
https://arxiv.org/abs/…

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenario…

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
Shilin Zhou, Zhenghua Li
https://arxiv.org/abs/2507.12252 https://

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities. Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of …

Vibe Coding for UX Design: Understanding UX Professionals' Perceptions of AI-Assisted Design and Development
Jie Li, Youyang Hou, Laura Lin, Ruihao Zhu, Hancheng Cao, Abdallah El Ali
https://arxiv.org/abs/2509.10652

Vibe Coding for UX Design: Understanding UX Professionals' Perceptions of AI-Assisted Design and Development
Generative AI is reshaping UX design practices through "vibe coding," where UX professionals express intent in natural language and AI translates it into functional prototypes and code. Despite rapid adoption, little research has examined how vibe coding reconfigures UX workflows and collaboration. Drawing on interviews with 20 UX professionals across enterprises, startups, and academia, we show how vibe coding follows a four-stage workflow of ideation, AI generation, debugging, and review. Thi…

Towards few-shot isolated word reading assessment
Reuben Smit, Retief Louw, Herman Kamper
https://arxiv.org/abs/2507.12217 https://ar…

Towards few-shot isolated word reading assessment
We explore an ASR-free method for isolated word reading assessment in low-resource settings. Our few-shot approach compares input child speech to a small set of adult-provided reference templates. Inputs and templates are encoded using intermediate layers from large self-supervised learned (SSL) models. Using an Afrikaans child speech benchmark, we investigate design options such as discretising SSL features and barycentre averaging of the templates. Idealised experiments show reasonable perfor…

Toward a Behavioural Translation Style Space: Simulating the Temporal Dynamics of Affect, Behaviour, and Cognition in Human Translation Production
Michael Carl, Takanori Mizowaki, Aishvarya Ray, Masaru Yamada, Devi Sri Bandaru, Xinyue Ren
https://arxiv.org/abs/2507.12208

Toward a Behavioural Translation Style Space: Simulating the Temporal Dynamics of Affect, Behaviour, and Cognition in Human Translation Production
The paper introduces a Behavioural Translation Style Space (BTSS) that describes possible behavioural translation patterns. The suggested BTSS is organized as a hierarchical structure that entails various embedded processing layers. We posit that observable translation behaviour - i.e., eye and finger movements - is fundamental when executing the physical act of translation but it is caused and shaped by higher-order cognitive processes and affective translation states. We analyse records of ke…

LLMs Homogenize Values in Constructive Arguments on Value-Laden Topics
Farhana Shahid, Stella Zhang, Aditya Vashistha
https://arxiv.org/abs/2509.10637 https://

LLMs Homogenize Values in Constructive Arguments on Value-Laden Topics
Large language models (LLMs) are increasingly used to promote prosocial and constructive discourse online. Yet little is known about how they negotiate and shape underlying values when reframing people's arguments on value-laden topics. We conducted experiments with 347 participants from India and the United States, who wrote constructive comments on homophobic and Islamophobic threads, and reviewed human-written and LLM-rewritten versions of these comments. Our analysis shows that LLM systemat…

StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features
Jeremi K. Ochab, Mateusz Matias, Tymoteusz Boba, Tomasz Walkowiak
https://arxiv.org/abs/2507.12064

StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features
This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generat…

[2025-09-16 Tue (UTC), 50 new articles found for cs.HC Human-Computer Interaction]
toXiv_bot_toot

Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited
Anthony G Cohn, Robert E Blackwell
https://arxiv.org/abs/2507.12059

Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited
We investigate the abilities of 28 Large language Models (LLMs) to reason about cardinal directions (CDs) using a benchmark generated from a set of templates, extensively testing an LLM's ability to determine the correct CD given a particular scenario. The templates allow for a number of degrees of variation such as means of locomotion of the agent involved, and whether set in the first, second or third person. Even the newer Large Reasoning Models are unable to reliably determine the correct C…

Living with Data: Exploring Physicalization Approaches to Sedentary Behavior Intervention for the Elderly
Siying Hu, Zhenhao Zhang
https://arxiv.org/abs/2509.11059 https://

Living with Data: Exploring Physicalization Approaches to Sedentary Behavior Intervention for the Elderly
Sedentary behavior is a critical health risk for older adults. While digital interventions exist, they often rely on screen-based notifications that feel clinical and are easily ignored. This paper presents a Research through Design inquiry into data physicalization as a humane alternative. We designed and deployed tangible artifacts that ambiently represent sedentary patterns in older adults' homes. These artifacts transform abstract data into aesthetic, evolving forms, becoming part of the do…

A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans
Anca Dinu, Andra-Maria Florescu, Alina Resceanu
https://arxiv.org/abs/2507.12039

A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans
The following paper introduces a general linguistic creativity test for humans and Large Language Models (LLMs). The test consists of various tasks aimed at assessing their ability to generate new original words and phrases based on word formation processes (derivation and compounding) and on metaphorical language use. We administered the test to 24 humans and to an equal number of LLMs, and we automatically evaluated their answers using OCSAI tool for three criteria: Originality, Elaboration, …

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis
Josip Juki\'c
https://arxiv.org/abs/2507.12004 https://…

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis
This thesis addresses challenges related to data and parameter efficiency in neural language models, with a focus on representation analysis and the introduction of new optimization techniques. The first part examines the properties and dynamics of language representations within neural models, emphasizing their significance in enhancing robustness and generalization. It proposes innovative approaches based on representation smoothness, including regularization strategies that utilize Jacobian …

Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
Lukas Ellinger, Miriam Ansch\"utz, Georg Groh
https://arxiv.org/abs/2507.11981

Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
Large Language Models (LLMs) can provide accurate word definitions and explanations for any context. However, the scope of the definition changes for different target groups, like children or language learners. This is especially relevant for homonyms, words with multiple meanings, where oversimplification might risk information loss by omitting key senses, potentially misleading users who trust LLM outputs. We investigate how simplification impacts homonym definition quality across three targe…

Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
Yuki Sakamoto, Takahisa Uchida, Hiroshi Ishiguro
https://arxiv.org/abs/2507.11979

Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
Large language models (LLMs) have emerged as powerful tools for simulating complex social phenomena using human-like agents with specific traits. In human societies, value similarity is important for building trust and close relationships; however, it remains unexplored whether this principle holds true in artificial societies comprising LLM agents. Therefore, this study investigates the influence of value similarity on relationship-building among LLM agents through two experiments. First, in a…

Graph Representations for Reading Comprehension Analysis using Large Language Model and Eye-Tracking Biomarker
Yuhong Zhang, Jialu Li, Shilai Yang, Yuchen Xu, Gert Cauwenberghs, Tzyy-Ping Jung
https://arxiv.org/abs/2507.11972

Graph Representations for Reading Comprehension Analysis using Large Language Model and Eye-Tracking Biomarker
Reading comprehension is a fundamental skill in human cognitive development. With the advancement of Large Language Models (LLMs), there is a growing need to compare how humans and LLMs understand language across different contexts and apply this understanding to functional tasks such as inference, emotion interpretation, and information retrieval. Our previous work used LLMs and human biomarkers to study the reading comprehension process. The results showed that the biomarkers corresponding to…

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
Ziyu Ge, Gabriel Chua, Leanne Tan, Roy Ka-Wei Lee
https://arxiv.org/abs/2507.11966 …

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
As online communication increasingly incorporates under-represented languages and colloquial dialects, standard translation systems often fail to preserve local slang, code-mixing, and culturally embedded markers of harmful speech. Translating toxic content between low-resource language pairs poses additional challenges due to scarce parallel data and safety filters that sanitize offensive expressions. In this work, we propose a reproducible, two-stage framework for toxicity-preserving translat…