Tootfinder

RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
Bhavik Agarwal, Hemant Sunil Jomraj, Simone Kaplunov, Jack Krolick, Viktoria Rojkova
https://arxiv.org/abs/2508.09893

RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
Regulatory compliance question answering (QA) requires precise, verifiable information, and domain-specific expertise, posing challenges for Large Language Models (LLMs). In this work, we present a novel multi-agent framework that integrates a Knowledge Graph (KG) of Regulatory triplets with Retrieval-Augmented Generation (RAG) to address these demands. First, agents build and maintain an ontology-free KG by extracting subject--predicate--object (SPO) triplets from regulatory documents and syst…

Large scale statistically validated comorbidity networks
Paride Crisafulli, Tobias Galla, Antti Karlsson, Salvatore Miccich\`e, Jyrki Piilo, Rosario N. Mantegna
https://arxiv.org/abs/2510.09737

Large scale statistically validated comorbidity networks
We obtain comorbidity networks starting from medical information stored in electronic health records collected by the Wellbeing Services County of Southwest Finland (Varha). Based on the data, we associate each patient to one or more diseases and construct complex comorbidity networks associated with large patient cohorts characterized by an age interval and sex. The information about diseases in electronic health records is coded using the highest granularity present in the international class…

Open PhD/Junior Researcher Position in Neurosymbolic AI and Information Extraction on historical documents at FIZ Karlsruhe - Knowledge-driven AI research group (former ISE research group), starting at Jan 1, 2026.
Application Deadline: Oct 31, 2025
https://www.fiz-karlsruhe.de/en/stellenan…

Support measures in fractal geometry
Goran Radunovi\'c (University of Zagreb), Steffen Winter (Karlsruhe Institute of Technology)
https://arxiv.org/abs/2508.08780 https://…

Support measures in fractal geometry
We introduce two novel families of geometric functionals-basic contents and support contents-for investigating the fractal properties of compact subsets in Euclidean space. These functionals are derived from the support measures arising in connection with the general Steiner formula due to Hug, Last, and Weil, and offer new tools for extracting geometric information beyond classical fractal dimensions. The basic contents are constructed from the support measures of the set itself, while the sup…

Last week, October sunshine in Freiburg at the anual #NFDIMatWerk planning & strategy meeting at Freiburg Innovation Center FRIZ. Usually, I don't complain about the food, but ... hey guys, there is room for improvement ;-)
Overall outcome: The MSE KnowledgeGraph will be THE central hub for all NFDIMatWerk resources

HET/HPF observations of Helium in warm, hot, and ultra-hot Jupiters
Jaume Orell-Miquel, Kyra Sampson, Caroline V. Morley, William D. Cochran, Girish M. Duvvuri, Daniel M. Krolikowski, Suvrath Mahadevan, Quang H. Tran
https://arxiv.org/abs/2509.06847

HET/HPF observations of Helium in warm, hot, and ultra-hot Jupiters
The near-infrared helium triplet line is a powerful tool for studying atmospheric escape processes of close-in exoplanets, especially irradiated gas giants. Line profile fitting provides direct insight into the mechanisms driving atmospheric mass loss of close-in, Jupiter-sized planets. We present high-resolution transmission spectroscopy results for the helium triplet line of sixteen gas giants ($R_{\rm p} > 0.5 R_{\rm Jup}$). These observations are part of an extensive helium survey conducted…

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Qianfeng Wen, Yifan Liu, Justin Cui, Joshua Zhang, Anton Korikov, George-Kirollos Saad, Scott Sanner
https://arxiv.org/abs/2510.02656

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Natural Language (NL) recommender systems aim to retrieve relevant items from free-form user queries and item descriptions. Existing systems often rely on dense retrieval (DR), which struggles to interpret challenging queries that express broad (e.g., "cities for youth friendly activities") or indirect (e.g., "cities for a high school graduation trip") user intents. While query reformulation (QR) has been widely adopted to improve such systems, existing QR methods tend to focus only on expandin…

MIRAC-5 on the MMT with MAPS: annular groove phase mask N-band coronagraphic upgrade
Alyssa L. Miller, Jarron Leisenring, Michael Meyer, Gilles Orban De Xivry, Olivier Absil, Rory Bowens, Christian Delacroix, Olivier Durney, Pontus Forsberg, Bill Hoffmann, Mikael Karlsson, John D. Monnier, Manny Montoya, Katie Morzinski, Eric Pantin, Samuel Ronayette, Taylor L. Tobin, Grant West

MIRAC-5 on the MMT with MAPS: annular groove phase mask N-band coronagraphic upgrade
We describe the coronagraphic upgrade underway for the Mid-Infrared Array Camera-5 (MIRAC-5) to be used with the 6.5-m MMT telescope utilizing the new MMT Adaptive optics exoPlanet characterization System (MAPS). Mid-IR ground-based coronagraphic adaptive-optics-assisted imaging can be a powerful tool for characterizing exoplanet atmospheres and studying protoplanets in formation within circumstellar disks around young stars. In addition to enabling ground-based observations of bright targets i…

The uniqueness of inverse scattering problems, reciprocity principles, and nonradiating sources related to low-signature structures
Johan Helsing, Anders Karlsson
https://arxiv.org/abs/2509.26304

The uniqueness of inverse scattering problems, reciprocity principles, and nonradiating sources related to low-signature structures
This paper is about perfectly electrically conducting structures designed to produce negligible scattered power when exposed to a time-harmonic plane electromagnetic wave. The structures feature cavities capable of concealing objects. Theoretical investigations of the properties of the structures combined with accurate numerical computations lead to three key findings: the first concerns the uniqueness of the solution to an inverse scattering problem, the second establishes a reciprocity relati…

Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations
Bla\v{z} \v{S}krlj, Beno\^it Guilleminot, Andra\v{z} Tori
https://arxiv.org/abs/2507.18993

Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations
Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in code generation, their application in data-centric research is still largely untapped. This paper presents Agent0, an LLM-driven, agent-based system designed to automate information extraction and feature construction from raw, unstructured text. Categorical f…