Tootfinder

Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities
Maria Levchenko
https://arxiv.org/abs/2510.06743 https://arx…

Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities
Digital humanities scholars increasingly use Large Language Models for historical document digitization, yet lack appropriate evaluation frameworks for LLM-based OCR. Traditional metrics fail to capture temporal biases and period-specific errors crucial for historical corpus creation. We present an evaluation methodology for LLM-based historical OCR, addressing contamination risks and systematic biases in diplomatic transcription. Using 18th-century Russian Civil font texts, we introduce novel …

"...using science-backed methodology and AI‑driven insights to support data‑informed hiring and talent management decisions."
(nonsense words I encountered during job search, describing an automated "assessment" I was given)
This is AI driven: https://www.youtube.com/watch?v=LMoONIKPmRw

interactome_stelzl: Stelzl human interactome (2005)
A network of human proteins and their binding interactions. Nodes represent proteins and an edge represents an interaction between two proteins, as inferred via high-throughput Y2H experiments using bait and prey methodology.
This network has 1706 nodes and 6207 edges.
Tags: Biological, Protein interactions, Unweighted

⇢ So, more and more research questions will be “answered” directly by chatbots, and for the rest, the results will be produced by code generated by chatbots processing data preprocessed by chatbots.
This is then complemented by a lot of speculation about the “meaning” of these results. □
#DigitalHumanities

Melkein 10000 ääntä kasassa!
Metaani: ilmaston vaiettu vihollinen. Vaadi rajoja liha- ja maitoteollisuudelle sekä niiden ylikulutukselle. Allekirjoita vetoomus! https://www.greenpeace.org/finland/toimi/metaani-ilmaston-vaiettu-vihollinen/

Metaani: ilmaston vaiettu vihollinen - Greenpeace Suomi
Metaani on voimakas kasvihuonekaasu, jota syntyy erityisesti maito- ja lihataloudessa. On aika vetää ilmastohätäjarrusta.

Tidy Modeling with R: #rstats #machinelearning

Tidy Modeling with R
The tidymodels framework is a collection of R packages for modeling and machine learning using tidyverse principles. This book provides a thorough introduction to how to use tidymodels, and an outline of good methodology and statistical practice for phases of the modeling process.

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See
https://arxiv.org/abs/2510.07172

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive explora…

interactome_stelzl: Stelzl human interactome (2005)
A network of human proteins and their binding interactions. Nodes represent proteins and an edge represents an interaction between two proteins, as inferred via high-throughput Y2H experiments using bait and prey methodology.
This network has 1706 nodes and 6207 edges.
Tags: Biological, Protein interactions, Unweighted

Foundations of LLM Knowledge Materialization: Termination, Reproducibility, Robustness
Luca Giordano, Simon Razniewski
https://arxiv.org/abs/2510.06780 https://

Foundations of LLM Knowledge Materialization: Termination, Reproducibility, Robustness
Large Language Models (LLMs) encode substantial factual knowledge, yet measuring and systematizing this knowledge remains challenging. Converting it into structured format, for example through recursive extraction approaches such as the GPTKB methodology (Hu et al., 2025b), is still underexplored. Key open questions include whether such extraction can terminate, whether its outputs are reproducible, and how robust they are to variations. We systematically study LLM knowledge materialization usi…

AIM 2025 Challenge on Real-World RAW Image Denoising
Feiran Li, Jiacheng Li, Marcos V. Conde, Beril Besbinar, Vlad Hosu, Daisuke Iso, Radu Timofte
https://arxiv.org/abs/2510.06601

AIM 2025 Challenge on Real-World RAW Image Denoising
We introduce the AIM 2025 Real-World RAW Image Denoising Challenge, aiming to advance efficient and effective denoising techniques grounded in data synthesis. The competition is built upon a newly established evaluation benchmark featuring challenging low-light noisy images captured in the wild using five different DSLR cameras. Participants are tasked with developing novel noise synthesis pipelines, network architectures, and training methodologies to achieve high performance across different …