Tootfinder

Took me a moment…. TBH, I actually asked the person who sent it to me if it was true.

Great stuff! I can't recommend enough!
OK, I'll try, but it's like I'm trying to slam dunk a basketball, when I can't jump 6" off the ground...
You'll love his books. They're great. Life-lessons. Tragedy. Comedy. And they're a good deal. Did I mention cheap?
#ShortFiction #ProsePoetry

Deep Fried Store — Mark Doyon: Author of 'Deep Fried'
Buy 'Deep Fried' by Mark Doyon in hardcover, trade paperback, and ebook formats.

Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models
Hyunwoo Yoo, Gail L. Rosen
https://arxiv.org/abs/2507.21980 https://

Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models
Traditional machine learning models struggle to generalize in microbiome studies where only metadata is available, especially in small-sample settings or across studies with heterogeneous label formats. In this work, we explore the use of large language models (LLMs) to classify microbial samples into ontology categories such as EMPO 3 and related biological labels, as well as to predict pathogen contamination risk, specifically the presence of E. Coli, using environmental metadata alone. We ev…

Verisimilitude as Boon and Bane: How People Initiate Opportunistic Interactions at Professional Events in Social VR
Victoria Chang, Caro Williams-Pierce, Huaishu Peng, Ge Gao
https://arxiv.org/abs/2507.22241

Verisimilitude as Boon and Bane: How People Initiate Opportunistic Interactions at Professional Events in Social VR
Opportunistic interactions-the unstructured exchanges that emerge as individuals become aware of each other's presence-are essential for relationship building and information sharing in everyday life. Yet, fostering effective opportunistic interactions has proven challenging, especially at professional events that have increasingly transitioned from in person to online formats. In the current paper, we offer an in-depth qualitative account of how people initiate opportunistic interactions in so…

from my link log —
Firefox's optimized zip format: reading zip files really quickly.
https://taras.glek.net/posts/optimized-zip-format/
saved 2025-07-03

@…
Overheard: "Pidgey is beak-deep in Mark Doyon's tragicomic new novel, 'Deep Fried.' Be like Pidgey."
Available now!
https://www.DeepFried.store/

Deep Fried Store — Mark Doyon: Author of 'Deep Fried'
Buy 'Deep Fried' by Mark Doyon in hardcover, trade paperback, and ebook formats.

SciMantify -- A Hybrid Approach for the Evolving Semantification of Scientific Knowledge
Lena John, Kheir Eddine Farfar, S\"oren Auer, Oliver Karras
https://arxiv.org/abs/2506.21819

SciMantify -- A Hybrid Approach for the Evolving Semantification of Scientific Knowledge
Scientific publications, primarily digitized as PDFs, remain static and unstructured, limiting the accessibility and reusability of the contained knowledge. At best, scientific knowledge from publications is provided in tabular formats, which lack semantic context. A more flexible, structured, and semantic representation is needed to make scientific knowledge understandable and processable by both humans and machines. We propose an evolution model of knowledge representation, inspired by the 5-…

“FOR REVIEW: Address formats around the world”
https://www.w3.org/blog/International/2025/08/06/for-review-address-formats-around-the-world/
The doc to review:

Enriching Object-Centric Event Data with Process Scopes: A Framework for Aggregation and Analysis
Shahrzad Khayatbashi, Majid Rafiei, Jiayuan Chen, Timotheus Kampik, Gregor Berg, Amin Jalali
https://arxiv.org/abs/2508.18830

Enriching Object-Centric Event Data with Process Scopes: A Framework for Aggregation and Analysis
Object-Centric Process Mining enables the analysis of complex operational behavior by capturing interactions among multiple business objects (e.g., orders, items, deliveries). These interactions are recorded using Object-Centric Event Data (OCED) formats, such as the Object-Centric Event Log (OCEL). However, existing formats lack explicit definitions of process scopes, which restricts analysis to individual processes and limits insights to a low level of granularity. In practice, OCED often spa…

CNN is expanding its podcast business by rebranding CNN Audio to CNN Podcasts and plans to introduce new talent and formats, including more video podcasts (Alex Weprin/The Hollywood Reporter)
https://www.hollywoodreporter.com/business

CNN Plans a Podcast Expansion Push (Exclusive)
The news network is rebranding CNN Audio as CNN Podcasts, as it develops new formats and shifts attention to new talent.

@… @… @… the library already checks for expected fail on those formats 😅

"New File Format Research and Documentation on the Sustainability of Digital Formats" | The Signal https://blogs.loc.gov/thesignal/2025/06/new-file-format-research/

A Technical Review on Comparison and Estimation of Steganographic Tools
Ms. Preeti P. Bhatt, Rakesh R. Savant
https://arxiv.org/abs/2508.19323 https://arxi…

A Technical Review on Comparison and Estimation of Steganographic Tools
Steganography is technique of hiding a data under cover media using different steganography tools. Image steganography is hiding of data (Text/Image/Audio/Video) under a cover as Image. This review paper presents classification of image steganography and the comparison of various Image steganography tools using different image formats. Analyzing numerous tools on the basis of Image features and extracting the best one. Some of the tools available in the market were selected based on the frequen…

Binsparse: A Specification for Cross-Platform Storage of Sparse Matrices and Tensors
Benjamin Brock, Willow Ahrens, Hameer Abbasi, Timothy A. Davis, Juni Kim, James Kitchen, Spencer Patty, Isaac Virshup, Erik Welch
https://arxiv.org/abs/2506.19175

Binsparse: A Specification for Cross-Platform Storage of Sparse Matrices and Tensors
Sparse matrices and tensors are ubiquitous throughout multiple subfields of computing. The widespread usage of sparse data has inspired many in-memory and on-disk storage formats, but the only widely adopted storage specifications are the Matrix Market and FROSTT file formats, which both use ASCII text. Due to the inefficiency of text storage, these files typically have larger file sizes and longer parsing times than binary storage formats, which directly store an in-memory representation to di…

Three small announcements:
1. RFC 9839, a guide to which Unicode characters you should never use: https://www.rfc-editor.org/rfc/rfc9839.html
2. Blog piece with background and context, “RFC 9839 and Bad Unicode”:

Excellent article by Ibrahim Diallo that serves as a quick overview of image formats for the web! ^^
What Learning React Won't Teach You: Image Formats
https://idiallo.com/blog/react-and-image-format?utm_source=tldrwebdev

Lyft ramps up its ad business with three new ad formats; CEO David Risher said that Lyft is on track to reach a $100M annualized ad revenue run rate by 2025 end (Kerry Flynn/Axios)
https://www.axios.com/2025/06/12/lyft-ads-sponsored-rides

Exclusive: Lyft launches new ad formats
Advertisers can brand the Lyft map and subsidize rides.

Most of the time I like widescreen and ultra-widescreen, but when I'm just puttering around on a computer, I find 5:4/4:3 oddly cozy. Incidentally, it works really well for browsing the modern web, because images fit pretty well in both square and vertical formats while wider formats still look ok.
Yes, I'm coming at you live in 1280x1024.

Recommendations to overcome language barriers in the Vera C. Rubin Observatory Research Ecosystem
Jos\'e Antonio Alonso Pav\'on, Andr\'es Alejandro Plazas Malag\'on
https://arxiv.org/abs/2507.18682

Recommendations to overcome language barriers in the Vera C. Rubin Observatory Research Ecosystem
The report presents a comprehensive set of five recommendations to reduce language barriers within the Vera C. Rubin Observatory Research Ecosystem, promoting greater inclusion of researchers who are speakers of English as an additional language. Recognizing that English linguistic hegemony in science limits participation and productivity, the document proposes multilingual presentation formats, academic writing training, a Virtual Writing Center, language support programs, and writing retreats…

Efficient Mixed-Precision Large Language Model Inference with TurboMind
Li Zhang, Youhe Jiang, Guoliang He, Xin Chen, Han Lv, Qian Yao, Fangcheng Fu, Kai Chen
https://arxiv.org/abs/2508.15601

Efficient Mixed-Precision Large Language Model Inference with TurboMind
Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. This work introduces mixed-precision LLM inference techniques that encompass (i) systematic memory and compute optimization across hierarchical storage and tensor core architectures, and (ii) comprehensive end-to-end mixed-precision optimization across diverse precision formats and hardware configurati…

Smoothness Meets Autobidding: Tight Price of Anarchy Bounds for Simultaneous First-Price Auctions
Riccardo Colini-Baldeschi, Sophie Klumper, Twan Kroll, Stefano Leonardi, Guido Sch\"afer, Artem Tsikiridis
https://arxiv.org/abs/2506.20908

Smoothness Meets Autobidding: Tight Price of Anarchy Bounds for Simultaneous First-Price Auctions
Online advertising systems have recently transitioned to autobidding, enabling advertisers to delegate bidding decisions to automated agents. Each advertiser directs their agent to optimize a valuation-dependent objective subject to return-on-investment (ROI) or budget constraints. Given their relevance, there has been a surge in literature studying the liquid welfare price of anarchy (POA) of core auction formats in autobidding, among which simultaneous first-price auctions (FPA). These models…

Bangla-Bayanno: A 52K-Pair Bengali Visual Question Answering Dataset with LLM-Assisted Translation Refinement
Mohammed Rakibul Hasan, Rafi Majid, Ahanaf Tahmid
https://arxiv.org/abs/2508.19887

Bangla-Bayanno: A 52K-Pair Bengali Visual Question Answering Dataset with LLM-Assisted Translation Refinement
In this paper, we introduce Bangla-Bayanno, an open-ended Visual Question Answering (VQA) Dataset in Bangla, a widely used, low-resource language in multimodal AI research. The majority of existing datasets are either manually annotated with an emphasis on a specific domain, query type, or answer type or are constrained by niche answer formats. In order to mitigate human-induced errors and guarantee lucidity, we implemented a multilingual LLM-assisted translation refinement pipeline. This datas…

🏗️ Supports distributable workers, multiple output formats & pluggable architecture for maximum flexibility
🔒 Execution without root privileges using #runc or #crun backends with #containerd

TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models
Zijian Zhang, Pan Chen, Fangshi Du, Runlong Ye, Oliver Huang, Michael Liut, Al\'an Aspuru-Guzik
https://arxiv.org/abs/2507.18945

TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models
Efficiently navigating and understanding academic papers is crucial for scientific progress. Traditional linear formats like PDF and HTML can cause cognitive overload and obscure a paper's hierarchical structure, making it difficult to locate key information. While LLM-based chatbots offer summarization, they often lack nuanced understanding of specific sections, may produce unreliable information, and typically discard the document's navigational structure. Drawing insights from a formative st…

"Der öffentlich-rechtliche Sender ist in jüngster Vergangenheit immer wieder durch einseitige Berichte über die Landwirtschaft aufgefallen – und zwar zugunsten des Bauernverbandes und nach rechts tendierender Landwirte. Vorläufiger Höhepunkt ist die zweite Folge des gemeinsam mit dem BR produzierten Formats „Klar“. Sie kann als Werbung für die AfD interpretiert werden." #ÖRR

Wie der NDR über Bauern berichtet: Ach, du heile Ackerwelt
Der NDR berichtet neuerdings oft einseitig positiv über Landwirtschaft. Manche führen diesen Trend auf den Druck durch die Bauernproteste zurück.

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Ran Wang, Xiaoxuan Liu, Hao Ren, Gang Chen, Fanchao Qi, Maosong Sun
https://arxiv.org/abs/2507.16768

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Structured decoding enables large language models (LLMs) to generate outputs in formats required by downstream systems, such as HTML or JSON. However, existing methods suffer from efficiency bottlenecks due to grammar compilation, state tracking, and mask creation. We observe that many real-world tasks embed strong prior knowledge about output structure. Leveraging this, we propose a decomposition of constraints into static and dynamic components -- precompiling static structures offline and in…

A Unified Transformer Architecture for Low-Latency and Scalable Wireless Signal Processing
Yuto Kawai, Rajeev Koodli
https://arxiv.org/abs/2508.17960 https://

A Unified Transformer Architecture for Low-Latency and Scalable Wireless Signal Processing
We propose a unified Transformer-based architecture for wireless signal processing tasks, offering a low-latency, task-adaptive alternative to conventional receiver pipelines. Unlike traditional modular designs, our model integrates channel estimation, interpolation, and demapping into a single, compact attention-driven architecture designed for real-time deployment. The model's structure allows dynamic adaptation to diverse output formats by simply modifying the final projection layer, enablin…

Vor genau 30 Jahren wurde ein kleines Stück Technikgeschichte geschrieben, das unseren Musikkonsum für immer verändern sollte! Am 14. Juli 1995 legten die Forscher am Fraunhofer-Institut die Dateiendung ".mp3" fest. 🎧
Zum Artikel: https://heise.de/-1…

Comparison of FTN-NOFDM and PCS-OFDM for Long-Haul Coherent Optical Communications
Haide Wang, Ji Zhou, Yongcheng Li, Weiping Liu, Changyuan Yu, Xiangjun Xin, Liangchuan Li
https://arxiv.org/abs/2508.17350

Comparison of FTN-NOFDM and PCS-OFDM for Long-Haul Coherent Optical Communications
Single-wavelength 400G coherent optical communications have become a critical solution to meet the explosive traffic demands. However, the single-carrier modulation using low-order modulation formats requires a broader wavelength division multiplexing grid and expands the occupied optical bandwidth. In this paper, we propose the faster-than-Nyquist non-orthogonal frequency division multiplexing (FTN-NOFDM) to improve the spectral efficiency for long-haul coherent optical communications. The sub…

Generating Actionable Robot Knowledge Bases by Combining 3D Scene Graphs with Robot Ontologies
Giang Nguyen, Mihai Pomarlan, Sascha Jongebloed, Nils Leusmann, Minh Nhat Vu, Michael Beetz
https://arxiv.org/abs/2507.11770

Generating Actionable Robot Knowledge Bases by Combining 3D Scene Graphs with Robot Ontologies
In robotics, the effective integration of environmental data into actionable knowledge remains a significant challenge due to the variety and incompatibility of data formats commonly used in scene descriptions, such as MJCF, URDF, and SDF. This paper presents a novel approach that addresses these challenges by developing a unified scene graph model that standardizes these varied formats into the Universal Scene Description (USD) format. This standardization facilitates the integration of these …

A User Manual for cuHALLaR: A GPU Accelerated Low-Rank Semidefinite Programming Solver
Jacob Aguirre, Diego Cifuentes, Vincent Guigues, Renato D. C. Monteiro, Victor Hugo Nascimento, Arnesh Sujanani
https://arxiv.org/abs/2508.15951

A User Manual for cuHALLaR: A GPU Accelerated Low-Rank Semidefinite Programming Solver
We present a Julia-based interface to the precompiled HALLaR and cuHALLaR binaries for large-scale semidefinite programs (SDPs). Both solvers are established as fast and numerically stable, and accept problem data in formats compatible with SDPA and a new enhanced data format taking advantage of Hybrid Sparse Low-Rank (HSLR) structure. The interface allows users to load custom data files, configure solver options, and execute experiments directly from Julia. A collection of example problems is …

High-Frequency First: A Two-Stage Approach for Improving Image INR
Sumit Kumar Dam, Mrityunjoy Gain, Eui-Nam Huh, Choong Seon Hong
https://arxiv.org/abs/2508.15582 https://

High-Frequency First: A Two-Stage Approach for Improving Image INR
Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates. A key challenge, however, lies in the spectral bias of neural networks, which tend to favor low-frequency components while struggling to capture high-frequency (HF) details such as sharp edges and fine textures. While prior approaches have addressed this limitation through architectural modifications or specialized …

Evaluating recognition and recall formats of social network surveys in physics education research
Meagan Sundstrom, Justin Gambrell, Adrienne L. Traxler, Eric Brewe
https://arxiv.org/abs/2508.08417

Evaluating recognition and recall formats of social network surveys in physics education research
An increasing number of studies in physics education research use social network analysis to quantify interactions among students. These studies typically gather data through online surveys using one of two different survey formats: recognition, where students select peers' names from a provided course roster, and recall, where students type their peers' names from memory as an open response. These survey formats, however, may be subject to two possible systematic errors. First, students may re…

@… that one looks decent! It’s about 1MB on disk but looks like it doesn’t support week date or day of year formats either

VulGuard: An Unified Tool for Evaluating Just-In-Time Vulnerability Prediction Models
Duong Nguyen, Manh Tran-Duc, Thanh Le-Cong, Triet Huynh Minh Le, M. Ali Babar, Quyet-Thang Huynh
https://arxiv.org/abs/2507.16685

VulGuard: An Unified Tool for Evaluating Just-In-Time Vulnerability Prediction Models
We present VulGuard, an automated tool designed to streamline the extraction, processing, and analysis of commits from GitHub repositories for Just-In-Time vulnerability prediction (JIT-VP) research. VulGuard automatically mines commit histories, extracts fine-grained code changes, commit messages, and software engineering metrics, and formats them for downstream analysis. In addition, it integrates several state-of-the-art vulnerability prediction models, allowing researchers to train, evaluat…

Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
Tianyao Shi, Yi Ding
https://arxiv.org/abs/2508.16712 https://

Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their heavy resource demands make quantization-reducing precision to lower-bit formats-critical for efficient serving. While many quantization methods exist, a systematic understanding of their performance, energy, and quality tradeoffs in realistic serving conditions remains a gap. In this work, we first develop a fully automated online characterization framework qMeter, and then conduct an in-de…

LettinGo: Explore User Profile Generation for Recommendation System
Lu Wang, Di Zhang, Fangkai Yang, Pu Zhao, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang
https://arxiv.org/abs/2506.18309

LettinGo: Explore User Profile Generation for Recommendation System
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations. While traditional embedding-based profiles lack interpretability and adaptability, recent advances with large language models (LLMs) enable text-based profiles that are semantically richer and more transparent. However, existing methods often adhere to fixed formats that limit their ability to capture the full diver…

Jack Unit: An Area- and Energy-Efficient Multiply-Accumulate (MAC) Unit Supporting Diverse Data Formats
Seock-Hwan Noh, Sungju Kim, Seohyun Kim, Daehoon Kim, Jaeha Kung, Yeseong Kim
https://arxiv.org/abs/2507.04772

Jack Unit: An Area- and Energy-Efficient Multiply-Accumulate (MAC) Unit Supporting Diverse Data Formats
In this work, we introduce an area- and energy-efficient multiply-accumulate (MAC) unit, named Jack unit, that is a jack-of-all-trades, supporting various data formats such as integer (INT), floating point (FP), and microscaling data format (MX). It provides bit-level flexibility and enhances hardware efficiency by i) replacing the carry-save multiplier (CSM) in the FP multiplier with a precision-scalable CSM, ii) performing the adjustment of significands based on the exponent differences withi…

Esto estš interesante. Dream Theater publicarš una novela gršfica inspirada en su mšs reciente disco «Parasomnia» que incluye 8 historias, una por cada canción.
https://www.loudersound.com/bands-artists/dream-theater…

It boggles my mind how it is just impossible to pay for a digitally delivered version of AmigaOS 3.2.X so I can use it in an emulator or on my PiStorm. The sold formats are physical roms, cd and compact flash (with weird restrictions on how to buy the latter). All massive detours for my purposes. I guess it’s 3.1 or 3.9. #amiga

Lyft ramps up its ad business with three new ad formats; CEO David Risher said that Lyft is on track to reach a $100M annualized ad revenue run rate by 2025 end (Kerry Flynn/Axios)
https://www.axios.com/2025/06/12/lyft-ads-sponsored-rides

Exclusive: Lyft launches new ad formats
Advertisers can brand the Lyft map and subsidize rides.

Just used this to shoot a patch scene that will go into an episode with no other added foley/ADR
iPhone 16: Edit Spatial Audio in Videos With Audio Mix - MacRumors https://www.macrumors.com/how-to/iphone-16-edit-spatial-audio-in-video-audio-mix/…

iPhone 16: Edit Spatial Audio in Videos With Audio Mix
When you shoot video on iPhone 16 models, multiple formats like Spatial Audio and Stereo are recorded to allow more audio customization. If you...

HybHuff: Lossless Compression for Hypergraphs via Entropy-Guided Huffman-Bitwise Coordination
Tianyu Zhao, Dongfang Zhao, Luanzheng Guo, Nathan Tallent
https://arxiv.org/abs/2506.15844

HybHuff: Lossless Compression for Hypergraphs via Entropy-Guided Huffman-Bitwise Coordination
Hypergraphs provide a natural representation for many-to-many relationships in data-intensive applications, yet their scalability is often hindered by high memory consumption. While prior work has improved computational efficiency, reducing the space overhead of hypergraph representations remains a major challenge. This paper presents a hybrid compression framework for integer-based hypergraph adjacency formats, which adaptively combines Huffman encoding and bitwise encoding to exploit structur…

Collaborative Texture Filtering
Tomas Akenine-M\"oller, Pontus Ebelin, Matt Pharr, Bartlomiej Wronski
https://arxiv.org/abs/2506.17770 https://…

Collaborative Texture Filtering
Recent advances in texture compression provide major improvements in compression ratios, but cannot use the GPU's texture units for decompression and filtering. This has led to the development of stochastic texture filtering (STF) techniques to avoid the high cost of multiple texel evaluations with such formats. Unfortunately, those methods can give undesirable visual appearance changes under magnification and may contain visible noise and flicker despite the use of spatiotemporal denoisers. Re…

🔄 Key features include automatic garbage collection, extendable frontend formats & concurrent dependency resolution
⚡ Efficient instruction caching with build cache import/export capabilities & nested build job invocations

PickleBall: Secure Deserialization of Pickle-based Machine Learning Models
Andreas D. Kellas, Neophytos Christou, Wenxin Jiang, Penghui Li, Laurent Simon, Yaniv David, Vasileios P. Kemerlis, James C. Davis, Junfeng Yang
https://arxiv.org/abs/2508.15987

PickleBall: Secure Deserialization of Pickle-based Machine Learning Models
Machine learning model repositories such as the Hugging Face Model Hub facilitate model exchanges. However, bad actors can deliver malware through compromised models. Existing defenses such as safer model formats, restrictive (but inflexible) loading policies, and model scanners have shortcomings: 44.9% of popular models on Hugging Face still use the insecure pickle format, 15% of these cannot be loaded by restrictive loading policies, and model scanners have both false positives and false nega…

Music and Artificial Intelligence: Artistic Trends
Jordi Pons, Zack Zukowski, Julian D. Parker, CJ Carr, Josiah Taylor, Zach Evans
https://arxiv.org/abs/2508.11694 https://

Music and Artificial Intelligence: Artistic Trends
We study how musicians use artificial intelligence (AI) across formats like singles, albums, performances, installations, voices, ballets, operas, or soundtracks. We collect 337 music artworks and categorize them based on AI usage: AI composition, co-composition, sound design, lyrics generation, and translation. We find that AI is employed as a co-creative tool, as an artistic medium, and in live performances and installations. Innovative uses of AI include exploring uncanny aesthetics, multili…

👀 #QGIS vs #Arcgis from an industry perspective https://www.wigeogis.com/en/arcgis_vs_qgis

A workflow for generating synthetic LiDAR datasets in simulation environments
Abhishek Phadke, Shakib Mahmud Dipto, Pratip Rana
https://arxiv.org/abs/2506.17378

A workflow for generating synthetic LiDAR datasets in simulation environments
This paper presents a simulation workflow for generating synthetic LiDAR datasets to support autonomous vehicle perception, robotics research, and sensor security analysis. Leveraging the CoppeliaSim simulation environment and its Python API, we integrate time-of-flight LiDAR, image sensors, and two dimensional scanners onto a simulated vehicle platform operating within an urban scenario. The workflow automates data capture, storage, and annotation across multiple formats (PCD, PLY, CSV), produ…

AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
Rana Alshaikh, Israa Alghanmi, Shelan Jeawak
https://arxiv.org/abs/2507.18442 https://…

AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
The cognitive and reasoning abilities of large language models (LLMs) have enabled remarkable progress in natural language processing. However, their performance in interpreting structured data, especially in tabular formats, remains limited. Although benchmarks for English tabular data are widely available, Arabic is still underrepresented because of the limited availability of public resources and its unique language features. To address this gap, we present AraTable, a novel and comprehensiv…

The {esquisse} package makes it easy to plot your data in different ways with a drag and drop interface: #rstats

Explore and Visualize Your Data Interactively
A shiny gadget to create ggplot2 figures interactively with drag-and-drop to map your variables to different aesthetics. You can quickly visualize your data accordingly to their type, export in various formats, and retrieve the code to reproduce the plot.

I wouldn't have thought that quantitative analyses of retrospective national bibliographies would be that painful: data access via SRU, OAI, and REST API; another resource has a JSON dump, another one again consists of various ttl for which you have to set up your own sparql endpoint. And I've not even arrived at formats, metadata standards and cataloguing peculiarities 🤯 so everything's #FAIR

LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference
Po-Han Lee, Yu-Cheng Lin, Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Ping-Hsun Wu, Yihuang Kang
https://arxiv.org/abs/2508.07221

LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference
Estimating individualized treatment effects from observational data presents a persistent challenge due to unmeasured confounding and structural bias. Causal Machine Learning (causal ML) methods, such as causal trees and doubly robust estimators, provide tools for estimating conditional average treatment effects. These methods have limited effectiveness in complex real-world environments due to the presence of latent confounders or those described in unstructured formats. Moreover, reliance on …

Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification
Kazuki Shimada, Archontis Politis, Iran R. Roman, Parthasaarathy Sudarsanam, David Diaz-Guerra, Ruchi Pandey, Kengo Uchida, Yuichiro Koyama, Naoya Takahashi, Takashi Shibuya, Shusuke Takahashi, Tuomas Virtanen, Yuki Mitsufuji
https://arxiv.org/a…

Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification
This paper presents the objective, dataset, baseline, and metrics of Task 3 of the DCASE2025 Challenge on sound event localization and detection (SELD). In previous editions, the challenge used four-channel audio formats of first-order Ambisonics (FOA) and microphone array. In contrast, this year's challenge investigates SELD with stereo audio data (termed stereo SELD). This change shifts the focus from more specialized 360° audio and audiovisual scene analysis to more commonplace audio and me…

STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting
Jiayu Fang, Zhiqi Shao, S T Boris Choy, Junbin Gao
https://arxiv.org/abs/2508.13433

STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting
Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often struggle with rigid temporal encoding and weak space-time fusion. We propose STPFormer, a Spatio-Temporal Pattern-Aware Transformer that achieves state-of-the-art performance via unified and interpretable representation learning. It integrates four modules: Temporal Position Aggregat…

from my link log —
Can You Block It ? a simple ad block tester.
https://canyoublockit.com/
saved 2025-08-05 https://dotat.at/:/Q4GFT.ht…

Can You Block It | A Simple Ad Block Tester
Test your Adblock with a Simple Adblocker Test. A webpage with various ad formats, test adblockers like AdBlock, AdBlock Plus, AdBlocker Ultimate, AdGuard, Ghostery, uBlock Origin, Pi-Hole, NoScript and more.

The Making of a Community Dark Matter Dataset with the National Science Data Fabric
Amy Roberts, Jack Marquez, Kin Hong NG, Kitty Mickelson, Aashish Panta, Giorgio Scorzelli, Amy Gooch, Prisca Cushman, Matthew Fritts, Himangshu Neog, Valerio Pascucci, Michela Taufer
https://arxiv.org/abs/2507.13297…

The Making of a Community Dark Matter Dataset with the National Science Data Fabric
Dark matter is believed to constitute approximately 85 percent of the universes matter, yet its fundamental nature remains elusive. Direct detection experiments, though globally deployed, generate data that is often locked within custom formats and non-reproducible software stacks, limiting interdisciplinary analysis and innovation. This paper presents a collaboration between the National Science Data Fabric (NSDF) and dark matter researchers to improve accessibility, usability, and scientific …

OceanVive: An Immersive Visualization System for Communicating Complex Oceanic Phenomena
Yang Ouyang, Yuchen Wu, Xiyuan Wang, Laixin Xie, Weicong Cheng, Jianping Gan, Quan Li, Xiaojuan Ma
https://arxiv.org/abs/2507.17218

OceanVive: An Immersive Visualization System for Communicating Complex Oceanic Phenomena
Communicating the complexity of oceanic phenomena-such as hypoxia and acidification-poses a persistent challenge for marine science. Despite advances in sensing technologies and computational models, conventional formats like static visualizations and text-based reports often fall short in conveying the dynamics of ocean changes. To address this gap, we present OceanVive, an immersive and interactive visualization system that transforms complex ocean datasets into navigable spatial narratives. …

sommerleseempfehlungen aus dem newsletter vom @…:
Summer 2025 Picks for Adults der New York Public Library:
https://www.nypl.org/books-more/recommend…

Generating Inputs for Grammar Mining using Dynamic Symbolic Execution
Andreas Pointner (University of Applied Sciences Upper Austria, Austria), Josef Pichler (University of Applied Sciences Upper Austria, Austria), Herbert Pr\"ahofer (Johannes Kepler University Linz, Austria)
https://arxiv.org/abs/2508.03832

Generating Inputs for Grammar Mining using Dynamic Symbolic Execution
A vast number of software systems include components that parse and process structured input. In addition to programming languages, which are analyzed by compilers or interpreters, there are numerous components that process standardized or proprietary data formats of varying complexity. Even if such components were initially developed and tested based on a specification, such as a grammar, numerous modifications and adaptations over the course of software evolution can make it impossible to pre…

A Comparative Study of Delta Parquet, Iceberg, and Hudi for Automotive Data Engineering Use Cases
Dinesh Eswararaj, Ajay Babu Nellipudi, Vandana Kollati
https://arxiv.org/abs/2508.13396

A Comparative Study of Delta Parquet, Iceberg, and Hudi for Automotive Data Engineering Use Cases
The automotive industry generates vast amounts of data from sensors, telemetry, diagnostics, and real-time operations. Efficient data engineering is critical to handle challenges of latency, scalability, and consistency. Modern data lakehouse formats Delta Parquet, Apache Iceberg, and Apache Hudi offer features such as ACID transactions, schema enforcement, and real-time ingestion, combining the strengths of data lakes and warehouses to support complex use cases. This study presents a comparati…

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
Qiao Zhang, Rabab Alomairy, Dali Wang, Zhuowei Gu, Qinglei Cao
https://arxiv.org/abs/2508.14848

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
General Matrix Multiplication (GEMM) is a critical operation underpinning a wide range of applications in high-performance computing (HPC) and artificial intelligence (AI). The emergence of hardware optimized for low-precision arithmetic necessitates a reevaluation of numerical algorithms to leverage mixed-precision computations, achieving improved performance and energy efficiency. This research introduces an adaptive mixed-precision GEMM framework that supports different precision formats at …

Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation
Genki Kusano, Kosuke Akimoto, Kunihiro Takeoka
https://arxiv.org/abs/2507.13525

Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation
Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling cold-start, cross-domain, and zero-shot scenarios, as well as supporting flexible input formats and generating explanations of user behavior. In this paper, we focus on a single-user setting, where no information from other users is used. This setting is practi…

POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration
Mukul Lokhande, Santosh Kumar Vishvakarma
https://arxiv.org/abs/2506.08785

POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration
The increasing complexity of AI models requires flexible hardware capable of supporting diverse precision formats, particularly for energy-constrained edge platforms. This work presents PARV-CE, a SIMD-enabled, multi-precision MAC engine that performs efficient multiply-accumulate operations using a unified data-path for 4/8/16-bit fixed-point, floating point, and posit formats. The architecture incorporates a layer adaptive precision strategy to align computational accuracy with workload sensi…

Survey of Surveys. II. Stellar parameters for 23 millions of stars
A. Turchi, E. Pancino, A. Avdeeva, F. Rossi, M. Tsantaki, P. M. Marrese, S. Marinoni, N. Sanna, G. Fanari, D. Alvarez Garay, M. Echeveste, S. Nedhath, S. Rani, E. Reggiani, S. Saracino, L. Steinbauer, G. Thomas, F. Gran, G. Guiglion
https://arxiv.org/abs/2507.059…

Survey of Surveys. II. Stellar parameters for 23 millions of stars
In the current panorama of large surveys, the vast amount of data obtained with different methods, data types, formats, and stellar samples, is making an efficient use of the available information difficult. The Survey of Surveys is a project to critically compile survey results in a single catalogue, facilitating the scientific use of the available information. In this second release, we present two new catalogs of stellar parameters (Teff, logg, and [Fe/H]). To build the first catalog, SoS-Sp…

MRpro - open PyTorch-based MR reconstruction and processing package
Felix Frederik Zimmermann, Patrick Schuenke, Christoph S. Aigner, Bill A. Bernhardt, Mara Guastini, Johannes Hammacher, Noah Jaitner, Andreas Kofler, Leonid Lunin, Stefan Martin, Catarina Redshaw Kranich, Jakob Schattenfroh, David Schote, Yanglei Wu, Christoph Kolbitsch
https://

MRpro - open PyTorch-based MR reconstruction and processing package
We introduce MRpro, an open-source image reconstruction package built upon PyTorch and open data formats. The framework comprises three main areas. First, it provides unified data structures for the consistent manipulation of MR datasets and their associated metadata (e.g., k-space trajectories). Second, it offers a library of composable operators, proximable functionals, and optimization algorithms, including a unified Fourier operator for all common trajectories and an extended phase graph si…

CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following
Yinghao Ma, Siyou Li, Juntao Yu, Emmanouil Benetos, Akira Maezawa
https://arxiv.org/abs/2506.12285 …

CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following
Recent advances in audio-text large language models (LLMs) have opened new possibilities for music understanding and generation. However, existing benchmarks are limited in scope, often relying on simplified tasks or multi-choice evaluations that fail to reflect the complexity of real-world music analysis. We reinterpret a broad range of traditional MIR annotations as instruction-following formats and introduce CMI-Bench, a comprehensive music instruction following benchmark designed to evaluat…

FrameShift: Learning to Resize Fuzzer Inputs Without Breaking Them
Harrison Green, Claire Le Goues, Fraser Brown
https://arxiv.org/abs/2507.05421 https://

FrameShift: Learning to Resize Fuzzer Inputs Without Breaking Them
Coverage-guided fuzzers are powerful automated bug-finding tools. They mutate program inputs, observe coverage, and save any input that hits an unexplored path for future mutation. Unfortunately, without knowledge of input formats--for example, the relationship between formats' data fields and sizes--fuzzers are prone to generate destructive frameshift mutations. These time-wasting mutations yield malformed inputs that are rejected by the target program. To avoid such breaking mutations, this p…

Jelly: a fast and convenient RDF serialization format
Piotr Sowinski, Karolina Bogacka, Anastasiya Danilenka, Nikita Kozlov
https://arxiv.org/abs/2506.11298

Jelly: a fast and convenient RDF serialization format
Existing RDF serialization formats such as Turtle, N-Triples, and JSON-LD are widely used for communication and storage in knowledge graph and Semantic Web applications. However, they suffer from limitations in performance, compression ratio, and lack of native support for RDF streams. To address these shortcomings, we introduce Jelly, a fast and convenient binary serialization format for RDF data that supports both batch and streaming use cases. Jelly is designed to maximize serialization thro…

Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices
Parshva Dhilankumar Patel
https://arxiv.org/abs/2507.07029 https://…

Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices
This paper presents the design and development of an OCR-powered pipeline for efficient table extraction from invoices. The system leverages Tesseract OCR for text recognition and custom post-processing logic to detect, align, and extract structured tabular data from scanned invoice documents. Our approach includes dynamic preprocessing, table boundary detection, and row-column mapping, optimized for noisy and non-standard invoice formats. The resulting pipeline significantly improves data extr…

UK satellite TV channel Islam Channel acquires politics magazine Tribune, plans to increase its print frequency, and launch new formats like podcasts and video (Rob Waugh/Press Gazette)
https://pressgazette.co.uk/publishers/magazines/islam-channel-tribune/…

UK political mag Tribune taken over by Islam Channel owner
Tribune magazine has been bought by the Islam Channel, former editor said "one of weirdest things to have happened history of British media

ARPaCCino: An Agentic-RAG for Policy as Code Compliance
Francesco Romeo, Luigi Arena, Francesco Blefari, Francesco Aurelio Pironti, Matteo Lupinacci, Angelo Furfaro
https://arxiv.org/abs/2507.10584

ARPaCCino: An Agentic-RAG for Policy as Code Compliance
Policy as Code (PaC) is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code (IaC) environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In this work, we present ARPaCCino, an agentic system that combines Large Language Models (LLMs), Retrieval-Augmented-Generation (RAG), and tool-based validation to automate the generation and verificati…

NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding
Running Zhao, Zhihan Jiang, Xinchen Zhang, Chirui Chang, Handi Chen, Weipeng Deng, Luyao Jin, Xiaojuan Qi, Xun Qian, Edith C. H. Ngai
https://arxiv.org/abs/2508.14395

NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding
Users often take notes for instructional videos to access key knowledge later without revisiting long videos. Automated note generation tools enable users to obtain informative notes efficiently. However, notes generated by existing research or off-the-shelf tools fail to preserve the information conveyed in the original videos comprehensively, nor can they satisfy users' expectations for diverse presentation formats and interactive features when using notes digitally. In this work, we present …

XR-NPE: High-Throughput Mixed-precision SIMD Neural Processing Engine for Extended Reality Perception Workloads
Tejas Chaudhari, Akarsh J., Tanushree Dewangan, Mukul Lokhande, Santosh Kumar Vishvakarma
https://arxiv.org/abs/2508.13049

XR-NPE: High-Throughput Mixed-precision SIMD Neural Processing Engine for Extended Reality Perception Workloads
This work proposes XR-NPE, a high-throughput Mixed-precision SIMD Neural Processing Engine, designed for extended reality (XR) perception workloads like visual inertial odometry (VIO), object classification, and eye gaze extraction. XR-NPE is first to support FP4, Posit (4,1), Posit (8,0), and Posit (16,1) formats, with layer adaptive hybrid-algorithmic implementation supporting ultra-low bit precision to significantly reduce memory bandwidth requirements, and accompanied by quantization-aware …

Toward Efficient SpMV in Sparse LLMs via Block Extraction and Compressed Storage
Junqing Lin, Jingwei Sun, Mingge Lu, Guangzhong Sun
https://arxiv.org/abs/2507.12205

Toward Efficient SpMV in Sparse LLMs via Block Extraction and Compressed Storage
Sparse Matrix-Vector Multiplication (SpMV) has become a critical performance bottleneck in the local deployment of sparse Large Language Models (LLMs), where inference predominantly operates on workloads during the decoder phase with a batch size of one. Existing SpMV kernels and sparse matrix formats, originally designed for scientific computing, fail to exploit the unique structure patterns inherent in sparse LLMs, resulting in suboptimal performance and excessive storage overhead. This paper…

scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
Davide D'Ascenzo, Sebastiano Cultrera di Montesano
https://arxiv.org/abs/2506.01883

scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
Modern single-cell datasets now comprise hundreds of millions of cells, presenting significant challenges for training deep learning models that require shuffled, memory-efficient data loading. While the AnnData format is the community standard for storing single-cell datasets, existing data loading solutions for AnnData are often inadequate: some require loading all data into memory, others convert to dense formats that increase storage demands, and many are hampered by slow random disk access…

From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI
Christian Meske, Justin Brenne, Erdi Uenal, Sabahat Oelcer, Ayseguel Doganguen
https://arxiv.org/abs/2508.06352

From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI
Current explainable AI (XAI) approaches prioritize algorithmic transparency and present explanations in abstract, non-adaptive formats that often fail to support meaningful end-user understanding. This paper introduces "Explanatory AI" as a complementary paradigm that leverages generative AI capabilities to serve as explanatory partners for human understanding rather than providers of algorithmic transparency. While XAI reveals algorithmic decision processes for model validation, Explanatory AI…

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.…

Everything You Need to Know About CS Education: Open Results from a Survey of More Than 18,000 Participants
Katsiaryna Dzialets, Aleksandra Makeeva, Ilya Vlasov, Anna Potriasaeva, Aleksei Rostovskii, Yaroslav Golubev, Anastasiia Birillo
https://arxiv.org/abs/2508.05286

Everything You Need to Know About CS Education: Open Results from a Survey of More Than 18,000 Participants
Computer science education is a dynamic field with many aspects that influence the learner's path. While these aspects are usually studied in depth separately, it is also important to carry out broader large-scale studies that touch on many topics, because they allow us to put different results into each other's perspective. Past large-scale surveys have provided valuable insights, however, the emergence of new trends (e.g., AI), new learning formats (e.g., in-IDE learning), and the increasing …

A factorisation-based regularised interior point method using the augmented system
Filippo Zanetti, Jacek Gondzio
https://arxiv.org/abs/2508.04370 https://…

A factorisation-based regularised interior point method using the augmented system
This paper describes the implementation of a new interior point solver for linear programming for the open-source optimization library HiGHS. The solver uses a direct factorisation to solve the Newton systems, choosing the best approach between the normal equations and augmented system. Details of the multifrontal factorisation routine are given, with attention to the features that allow to achieve high performance, like storage formats, use of efficient dense linear algebra subroutines and par…

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
Tao Sun, Oliver Liu, JinJin Li, Lan Ma
https://arxiv.org/abs/2508.05602 https://

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., ``Relevant'' vs. ``Not Relevant'', is a fundamental problem. However, this is a challenging task considering that texts have diverse formats and the definition of relevancy varies in different scenarios. We find that Multim…

LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation
Fei Teng, Haoyang Li, Lei Chen
https://arxiv.org/abs/2508.09594 https://arxi…

LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation
Modern computing systems, such as HDFS and Spark, produce vast quantities of logs that developers use for tasks like anomaly detection and error analysis. To simplify log analysis, template generation methods have been proposed to standardize log formats, transforming unstructured data into structured templates. Existing heuristic-based methods and neural network-based methods suffer from low accuracy problems due to the reliance on handcrafted heuristics or specific log patterns in training se…

Scaling the memory wall using mixed-precision -- HPG-MxP on an exascale machine
Aditya Kashi, Nicholson Koukpaizan, Hao Lu, Michael Matheson, Sarp Oral, Feiyi Wang
https://arxiv.org/abs/2507.11512

Scaling the memory wall using mixed-precision -- HPG-MxP on an exascale machine
Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by dense matrix operations have seen substantial speedups by utilizing low precision formats such as FP16. However, a majority of scientific simulation applications are memory bandwidth limited. Beyond preliminary studies, the practical gain from using mixed-preci…

Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support
Wu Hao Ran, Xi Xi, Furong Li, Jingyi Lu, Jian Jiang, Hui Huang, Yuzhuan Zhang, Shi Li
https://arxiv.org/abs/2506.06340

Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support
The advent of large language models (LLMs) has opened new avenues for analyzing complex, unstructured data, particularly within the medical domain. Electronic Health Records (EHRs) contain a wealth of information in various formats, including free text clinical notes, structured lab results, and diagnostic codes. This paper explores the application of advanced language models to leverage these diverse data sources for improved clinical decision support. We will discuss how text-based features, …

MExplore: an entity-based visual analytics approach for medical expertise acquisition
Xiao Pang, Yan Huang, Chang Liu, JiYuan Liu, MingYou Liu
https://arxiv.org/abs/2507.12337

MExplore: an entity-based visual analytics approach for medical expertise acquisition
Acquiring medical expertise is a critical component of medical education and professional development. While existing studies focus primarily on constructing medical knowledge bases or developing learning tools based on the structured, private healthcare data, they often lack methods for extracting expertise from unstructured medical texts. These texts constitute a significant portion of medical literature and offer greater flexibility and detail compared to structured data formats. Furthermore…

The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
Petteri Teikari, Mike Jarrell, Maryam Azh, Harri Pesola
https://arxiv.org/abs/2508.02765

The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
The Uniform Appraisal Dataset (UAD) 3.6's mandatory 2026 implementation transforms residential property valuation from narrative reporting to structured, machine-readable formats. This paper provides the first comprehensive analysis of this regulatory shift alongside concurrent AI advances in computer vision, natural language processing, and autonomous systems. We develop a three-layer framework for AI-augmented valuation addressing technical implementation and institutional trust requirements.…

Error Detection and Correction for Interpretable Mathematics in Large Language Models
Yijin Yang, Cristina Cornelio, Mario Leiva, Paulo Shakarian
https://arxiv.org/abs/2508.03500

Error Detection and Correction for Interpretable Mathematics in Large Language Models
Recent large language models (LLMs) have demonstrated the ability to perform explicit multi-step reasoning such as chain-of-thought prompting. However, their intermediate steps often contain errors that can propagate leading to inaccurate final predictions. Additionally, LLMs still struggle with hallucinations and often fail to adhere to prescribed output formats, which is particularly problematic for tasks like generating mathematical expressions or source code. This work introduces EDCIM (Err…

Echoes of Automation: The Increasing Use of LLMs in Newsmaking
Abolfazl Ansari, Delvin Ce Zhang, Nafis Irtiza Tripto, Dongwon Lee
https://arxiv.org/abs/2508.06445 https://

Echoes of Automation: The Increasing Use of LLMs in Newsmaking
The rapid rise of Generative AI (GenAI), particularly LLMs, poses concerns for journalistic integrity and authorship. This study examines AI-generated content across over 40,000 news articles from major, local, and college news media, in various media formats. Using three advanced AI-text detectors (e.g., Binoculars, Fast-Detect GPT, and GPTZero), we find substantial increase of GenAI use in recent years, especially in local and college news. Sentence-level analysis reveals LLMs are often used …

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
Leon Garza, Anantaa Kotal, Aritran Piplai, Lavanya Elluri, Prajit Das, Aman Chadha
https://arxiv.org/abs/2508.05545

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition (NER) models, these methods fail to generalize across formats and contexts. Recent advances in Large Language Models (LLMs) offer a promising alternative, yet the effect of architectural and training choices on redaction performance remains underexplored. LLMs…

From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format
Mehdi Akbari Gurabi, Lasse Nitz, Radu-Mihai Castravet, Roman Matzutt, Avikarsha Mandal, Stefan Decker
https://arxiv.org/abs/2508.03342

From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format
Existing cybersecurity playbooks are often written in heterogeneous, non-machine-readable formats, which limits their automation and interoperability across Security Orchestration, Automation, and Response platforms. This paper explores the suitability of Large Language Models, combined with Prompt Engineering, to automatically translate legacy incident response playbooks into the standardized, machine-readable CACAO format. We systematically examine various Prompt Engineering techniques and ca…

In-person, Online and Back Again -- A Tale of Three Hybrid Hackathons
Abasi-amefon Obot Affia-Jomants, Alexander Serebrenik, James D. Herbsleb, Alexander Nolte
https://arxiv.org/abs/2508.07301

In-person, Online and Back Again -- A Tale of Three Hybrid Hackathons
Hybrid hackathons, which combine in-person and online participation, present unique challenges for organizers and participants. Although such events are increasingly conducted, research on them remains fragmented, with limited integration between hackathon studies and hybrid collaboration. Existing strategies for in-person or online-only events often fail to address the unique challenges of hybrid formats, such as managing communication across physical and virtual spaces. Our work addresses thi…

Template-Based Schema Matching of Multi-Layout Tenancy Schedules:A Comparative Study of a Template-Based Hybrid Matcher and the ALITE Full Disjunction Model
Tim Uilkema, Yao Ma, Seyed Sahand Mohammadi Ziabari, Joep van Vliet
https://arxiv.org/abs/2507.02020

Template-Based Schema Matching of Multi-Layout Tenancy Schedules:A Comparative Study of a Template-Based Hybrid Matcher and the ALITE Full Disjunction Model
The lack of standardized tabular formats for tenancy schedules across real estate firms creates significant inefficiencies in data integration. Existing automated integration methods, such as Full Disjunction (FD)-based models like ALITE, prioritize completeness but result in schema bloat, sparse attributes and limited business usability. We propose a novel hybrid, template-based schema matcher that aligns multi-layout tenancy schedules to a predefined target schema. The matcher combines schema…

This https://arxiv.org/abs/2505.20368 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents
Retrieval-augmented generation (RAG) based large language models (LLMs) are widely used in finance for their excellent performance on knowledge-intensive tasks. However, standardized documents (e.g., SEC filing) share similar formats such as repetitive boilerplate texts, and similar table structures. This similarity forces traditional RAG methods to misidentify near-duplicate text, leading to duplicate retrieval that undermines accuracy and completeness. To address these issues, we propose the …

Marito: Structuring and Building Open Multilingual Terminologies for South African NLP
Vukosi Marivate, Isheanesu Dzingirai, Fiskani Banda, Richard Lastrucci, Thapelo Sindane, Keabetswe Madumo, Kayode Olaleye, Abiodun Modupe, Unarine Netshifhefhe, Herkulaas Combrink, Mohlatlego Nakeng, Matome Ledwaba
https://arxiv.org/abs/2508.03529…

Marito: Structuring and Building Open Multilingual Terminologies for South African NLP
The critical lack of structured terminological data for South Africa's official languages hampers progress in multilingual NLP, despite the existence of numerous government and academic terminology lists. These valuable assets remain fragmented and locked in non-machine-readable formats, rendering them unusable for computational research and development. \emph{Marito} addresses this challenge by systematically aggregating, cleaning, and standardising these scattered resources into open, interop…

CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation
Kaiwen Zhao, Bharathan Balaji, Stephen Lee
https://arxiv.org/abs/2508.03489 https://

CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation
Product sustainability reports provide valuable insights into the environmental impacts of a product and are often distributed in PDF format. These reports often include a combination of tables and text, which complicates their analysis. The lack of standardization and the variability in reporting formats further exacerbate the difficulty of extracting and interpreting relevant information from large volumes of documents. In this paper, we tackle the challenge of answering questions related to …

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
Shahed Masoudian, Gustavo Escobedo, Hannah Strauss, Markus Schedl
https://arxiv.org/abs/2508.03292

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior research has often probed gender bias using explicit gender cues as counterfactual, or studied them in sentence completion and short question answering tasks. These formats might overlook more implicit forms of bias embedded in generative behavior of longer content. In this work, we investigate gender bias in LLMs using g…

Capturing and Sharing Know-How through Visual Process Representations: A Human-Centred Approach to Teacher Workflows
Gloria Fern\'andez-Nieto, Vanessa Echeverria, Yuheng Li, Yi-Shan Tsai, Lele Sha, Guanliang Chen, Dragan Gasevic, Zachari Swiecki
https://arxiv.org/abs/2508.04357

Capturing and Sharing Know-How through Visual Process Representations: A Human-Centred Approach to Teacher Workflows
Knowledge Management is crucial for capturing and transferring expertise within universities, especially in high staff turnover contexts where expertise loss disrupts teaching. Documenting teachers' workflows is time-intensive and diverts experts from core responsibilities. Sequential Pattern Mining (SPM) leverages log data to identify expert workflows, offering an automated alternative to represent workflows but requiring transformation into intuitive formats for novice educators. This paper i…

Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes
Nikita Neveditsin, Pawan Lingras, Vijay Mago
https://arxiv.org/abs/2507.01810

Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes
We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific fail…

MetaExplainer: A Framework to Generate Multi-Type User-Centered Explanations for AI Systems
Shruthi Chari, Oshani Seneviratne, Prithwish Chakraborty, Pablo Meyer, Deborah L. McGuinness
https://arxiv.org/abs/2508.00300

MetaExplainer: A Framework to Generate Multi-Type User-Centered Explanations for AI Systems
Explanations are crucial for building trustworthy AI systems, but a gap often exists between the explanations provided by models and those needed by users. To address this gap, we introduce MetaExplainer, a neuro-symbolic framework designed to generate user-centered explanations. Our approach employs a three-stage process: first, we decompose user questions into machine-readable formats using state-of-the-art large language models (LLM); second, we delegate the task of generating system recomme…