Tootfinder

Prompt Variability Effects On LLM Code Generation
Andrei Paleyes, Radzim Sendyka, Diana Robinson, Christian Cabrera, Neil D. Lawrence
https://arxiv.org/abs/2506.10204

Prompt Variability Effects On LLM Code Generation
Code generation is one of the most active areas of application of Large Language Models (LLMs). While LLMs lower barriers to writing code and accelerate development process, the overall quality of generated programs depends on the quality of given prompts. Specifically, functionality and quality of generated code can be sensitive to user's background and familiarity with software development. It is therefore important to quantify LLM's sensitivity to variations in the input. To this end we prop…

Water Detection in the Interstellar Object 3I/ATLAS
Zexi Xing, Shawn Oset, John Noonan, Dennis Bodewits
https://arxiv.org/abs/2508.04675 https://arxiv.org/…

Water Detection in the Interstellar Object 3I/ATLAS
We report the first detection of water activity in the third confirmed interstellar object, 3I/ATLAS, based on ultraviolet imaging with the \emph{Neil Gehrels-Swift Observatory}. Observations acquired with the Ultraviolet/Optical Telescope on 2025 July 31st - Aug 1st revealed OH (A$^2Σ$ -- X$^2Π$) emission near 3085~Å. The water production rate results highly depend on the reddening assumption. For a reddening of 38.6\% between 5437.8~Å and 3325.7~Å, the water production rate is $(1.35 \pm…