Tootfinder

Single Answer is Not Enough: On Generating Ranked Lists with Medical Reasoning Models
Pittawat Taveekitworachai, Natpatchara Pongjirapat, Krittaphas Chaisutyakorn, Piyalitt Ittichaiwong, Tossaporn Saengja, Kunat Pipatanakul
https://arxiv.org/abs/2509.20866

Single Answer is Not Enough: On Generating Ranked Lists with Medical Reasoning Models
This paper presents a systematic study on enabling medical reasoning models (MRMs) to generate ranked lists of answers for open-ended questions. Clinical decision-making rarely relies on a single answer but instead considers multiple options, reducing the risks of narrow perspectives. Yet current MRMs are typically trained to produce only one answer, even in open-ended settings. We propose an alternative format: ranked lists and investigate two approaches: prompting and fine-tuning. While promp…

Status of the MARS code
Igor Rakhno (Fermi National Accelerator Laboratory), Igor Tropint (Fermi National Accelerator Laboratory), Dali Georgobiani (Fermi National Accelerator Laboratory), Alajos Makovec (Fermi National Accelerator Laboratory)
https://arxiv.org/abs/2510.03008

Status of the MARS code
This report describes major features of the most recent version of the MARS code as well as ongoing developments. The list of features includes various options for geometry models, a beam line builder based on MADX code, import of geometry models in GDML format, use of structured and unstructured meshes for scoring purposes, an update to the recent TENDL library for a number of projectiles at low energies (up to 250 MeV), and a recently implemented method to calculate spatial distribution of re…

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 …