Tootfinder

DeliverC: Teaching Pointers through GenAI-Powered Game-Based Learning
Wyatt Petula, Anushcka Joshi, Peggy Tu, Amrutha Somasundar, Suman Saha
https://arxiv.org/abs/2509.14496 htt…

DeliverC: Teaching Pointers through GenAI-Powered Game-Based Learning
While game-based learning is widely used in programming education, few tools offer adaptive, real-time support for complex topics, such as C pointers. We present DeliverC, a GenAI-enhanced game that integrates GPT-4-mini to provide personalized hints and generate pointer-related challenges on the fly. In a pilot study involving 25 undergraduate students, we investigated the impact of the system on learning through gameplay data and a 15-item survey that covered constructs such as motivation, se…

SkyNET-scape Room: An Escape Room to Explore Astroparticle Physics
Elisa Prandini, Sabine Hemmer, Michele Branca, Luca Campagnoni, Gabriella Cataldi, Marco Circella, Jean-Pierre Jonckheere, Emanuele Leonora, Ilaria Viale, Giuseppe Silvestri
https://arxiv.org/abs/2509.14190

SkyNET-scape Room: An Escape Room to Explore Astroparticle Physics
Innovative science communication is key to engaging the public with complex topics such as astroparticle physics. As part of the Italian PRIN 2022 funding initiative, we are developing SkyNET-scape Room, an interactive escape room designed to introduce participants to the main messengers of the high-energy universe, namely cosmic rays, gamma rays, and neutrinos. The experience is structured into three interactive stations, each focusing on a specific messenger and its detection method. Small …

Pseudo Empirical Likelihood Inference for Non-Probability Survey Samples
Yilin Chen, Pengfei Li, J. N. K. Rao, Changbao Wu
https://arxiv.org/abs/2508.09356 https://

Pseudo Empirical Likelihood Inference for Non-Probability Survey Samples
In this paper, the authors first provide an overview of two major developments on complex survey data analysis: the empirical likelihood methods and statistical inference with non-probability survey samples, and highlight the important research contributions to the field of survey sampling in general and the two topics in particular by Canadian survey statisticians. The authors then propose new inferential procedures on analyzing non-probability survey samples through the pseudo empirical likel…

Automating API Documentation with LLMs: A BERTopic Approach
AmirHossein Naghshzan
https://arxiv.org/abs/2509.05749 https://arxiv.org/pdf/2509.05749

Automating API Documentation with LLMs: A BERTopic Approach
Developers rely on API documentation, but official sources are often lengthy, complex, or incomplete. Many turn to community-driven forums like Stack Overflow for practical insights. We propose automating the summarization of informal sources, focusing on Android APIs. Using BERTopic, we extracted prevalent topics from 3.6 million Stack Overflow posts and applied extractive summarization techniques to generate concise summaries, including code snippets. A user study with 30 Android developers a…

First look at Vela X-1 with XRISM: A simultaneous campaign with XMM-Newton and NuSTAR
C. M. Diez, S. Dupourqu\'e, M. Zhou, E. Quintin, G. A. Matzeu, F. F\"urst, P. Kretschmar, R. Amato, C. Malacaria
https://arxiv.org/abs/2509.07258

First look at Vela X-1 with XRISM: A simultaneous campaign with XMM-Newton and NuSTAR
High-Mass X-ray Binaries (HMXBs) serve as useful laboratories for exploring the behaviour of accreted matter onto compact objects and for probing the complex wind environments of massive stars. These investigations are essential for understanding stellar life cycles and the dynamics of the Milky Way, and they are prominent topics in the science cases for XRISM and NewAthena. We report, for the first time, a XRISM observation of the HMXB Vela X-1, conducted during the first cycle of the XRISM ge…

Network-Level Prompt and Trait Leakage in Local Research Agents
Hyejun Jeong, Mohammadreze Teymoorianfard, Abhinav Kumar, Amir Houmansadr, Eugene Badasarian
https://arxiv.org/abs/2508.20282

Network-Level Prompt and Trait Leakage in Local Research Agents
We show that Web and Research Agents (WRAs) -- language model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive network adversaries such as ISPs. These agents could be deployed \emph{locally} by organizations and individuals for privacy, legal, or financial purposes. Unlike sporadic web browsing by humans, WRAs visit $70{-}140$ domains with distinguishable timing correlations, enabling unique fingerprinting attacks. Specifically, w…

Enhancing patent retrieval using automated patent summarization
Eleni Kamateri, Renukswamy Chikkamath, Michail Salampasis, Linda Andersson, Markus Endres
https://arxiv.org/abs/2507.16371

Enhancing patent retrieval using automated patent summarization
Effective query formulation is a key challenge in long-document Information Retrieval (IR). This challenge is particularly acute in domain-specific contexts like patent retrieval, where documents are lengthy, linguistically complex, and encompass multiple interrelated technical topics. In this work, we present the application of recent extractive and abstractive summarization methods for generating concise, purpose-specific summaries of patent documents. We further assess the utility of these a…