Tootfinder

AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
Lian Yan, Haotian Wang, Chen Tang, Haifeng Liu, Tianyang Sun, Liangliang Liu, Yi Guan, Jingchi Jiang
https://arxiv.org/abs/2507.21773

AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
In the agricultural domain, the deployment of large language models (LLMs) is hindered by the lack of training data and evaluation benchmarks. To mitigate this issue, we propose AgriEval, the first comprehensive Chinese agricultural benchmark with three main characteristics: (1) Comprehensive Capability Evaluation. AgriEval covers six major agriculture categories and 29 subcategories within agriculture, addressing four core cognitive scenarios: memorization, understanding, inference, and genera…

Physics of the gluon mass gap
Mauricio N. Ferreira, Joannis Papavassiliou, Jan M. Pawlowski, Nicolas Wink
https://arxiv.org/abs/2508.20568 https://arxiv.or…

Physics of the gluon mass gap
It has long been known that the gluon propagator in Landau-gauge QCD exhibits a mass gap; and its emergence has been ascribed to the action of the Schwinger mechanism in the gauge sector of QCD. In the present work, we relate this property to the physical mass gap of QCD by considering two observables associated with confinement and chiral symmetry breaking, namely the confinement-deconfinement transition temperature and the pion decay constant, respectively. It turns out that the first observa…

Sycophancy as compositions of Atomic Psychometric Traits
Shreyans Jain, Alexandra Yost, Amirali Abdullah
https://arxiv.org/abs/2508.19316 https://arxiv.org…

Sycophancy as compositions of Atomic Psychometric Traits
Sycophancy is a key behavioral risk in LLMs, yet is often treated as an isolated failure mode that occurs via a single causal mechanism. We instead propose modeling it as geometric and causal compositions of psychometric traits such as emotionality, openness, and agreeableness - similar to factor decomposition in psychometrics. Using Contrastive Activation Addition (CAA), we map activation directions to these factors and study how different combinations may give rise to sycophancy (e.g., high e…

Update on the Estlink-2 #subseacable cut last December:
"Finnish authorities [...] have charged the captain and two senior officers of a Russia-linked vessel that damaged undersea cables last year between Finland and Estonia."

Finland charges top officers of Russia-linked vessel that damaged undersea cables
Finnish authorities say they have charged the captain and two senior officers of a Russia-linked vessel that damaged undersea cables last year between Finland and Estonia. Monday's statement says they denied the allegations of aggravated criminal mischief and aggravated interference with communications. Authorities have said the vessel dragged its anchor to damage the Estlink-2 power cable and communication links between Finland and Estonia on Dec. 25. The Kremlin previously denied involvement …

Between Myth and History: von Neumann on Consciousness in Quantum Mechanics
Federico Laudisa
https://arxiv.org/abs/2508.15871 https://arxiv.org/pdf/2508.15…

Between Myth and History: von Neumann on Consciousness in Quantum Mechanics
The von Neumann attitude on such a deep interpretational question as the role of a human observer in order for the quantum description of measurement to be consistent has been long misrepresented. The large majority of the subsequent literature ascribed to von Neumann a radical view, according to which not only the collapse was in itself a truly physical process, but also the only way to accomodate it within a quantum description of a typical measurement was the introduction of human consciousn…

Credit risk for large portfolios of green and brown loans: extending the ASRF model
Alessandro Ramponi, Sergio Scarlatti
https://arxiv.org/abs/2506.12510 h…

Credit risk for large portfolios of green and brown loans: extending the ASRF model
We propose a credit risk model for portfolios composed of green and brown loans, extending the ASRF framework via a two-factor copula structure. Systematic risk is modeled using potentially skewed distributions, allowing for asymmetric creditworthiness effects, while idiosyncratic risk remains Gaussian. Under a non-uniform exposure setting, we establish convergence in quadratic mean of the portfolio loss to a limit reflecting the distinct characteristics of the two loan segments. Numerical resu…

Humanoid Robot Acrobatics Utilizing Complete Articulated Rigid Body Dynamics
Gerald Brantner
https://arxiv.org/abs/2508.08258 https://arxiv.org/pdf/2508.08…

Humanoid Robot Acrobatics Utilizing Complete Articulated Rigid Body Dynamics
Endowing humanoid robots with the ability to perform highly dynamic motions akin to human-level acrobatics has been a long-standing challenge. Successfully performing these maneuvers requires close consideration of the underlying physics in both trajectory optimization for planning and control during execution. This is particularly challenging due to humanoids' high degree-of-freedom count and associated exponentially scaling complexities, which makes planning on the explicit equations of motio…

Question-Answer Extraction from Scientific Articles Using Knowledge Graphs and Large Language Models
Hosein Azarbonyad, Zi Long Zhu, Georgios Cheirmpos, Zubair Afzal, Vikrant Yadav, Georgios Tsatsaronis
https://arxiv.org/abs/2507.13827

Question-Answer Extraction from Scientific Articles Using Knowledge Graphs and Large Language Models
When deciding to read an article or incorporate it into their research, scholars often seek to quickly identify and understand its main ideas. In this paper, we aim to extract these key concepts and contributions from scientific articles in the form of Question and Answer (QA) pairs. We propose two distinct approaches for generating QAs. The first approach involves selecting salient paragraphs, using a Large Language Model (LLM) to generate questions, ranking these questions by the likelihood o…

SPARE: Securing Progressive Web Applications Against Unauthorized Replications
Sajib Talukder, Nur Imtiazul Haque, Khandakar Ashrafi Akbar
https://arxiv.org/abs/2508.07053 https…

SPARE: Securing Progressive Web Applications Against Unauthorized Replications
WebView applications are widely used in mobile applications to display web content directly within the app, enhancing user engagement by eliminating the need to open an external browser and providing a seamless experience. Progressive Web Applications (PWAs) further improve usability by combining the accessibility of web apps with the speed, offline capabilities, and responsiveness of native applications. However, malicious developers can exploit this technology by duplicating PWA web links to …

Inductive Bias Extraction and Matching for LLM Prompts
Christian M. Angel, Francis Ferraro
https://arxiv.org/abs/2508.10295 https://arxiv.org/pdf/2508.1029…

Inductive Bias Extraction and Matching for LLM Prompts
The active research topic of prompt engineering makes it evident that LLMs are sensitive to small changes in prompt wording. A portion of this can be ascribed to the inductive bias that is present in the LLM. By using an LLM's output as a portion of its prompt, we can more easily create satisfactory wording for prompts. This has the effect of creating a prompt that matches the inductive bias in model. Empirically, we show that using this Inductive Bias Extraction and Matching strategy improves …