Tootfinder

Variable selection for minimum-variance portfolios
Guilherme V. Moura, Andr\'e P. Santos, Hudson S. Torrent
https://arxiv.org/abs/2508.14986 https://ar…

Variable selection for minimum-variance portfolios
Machine learning (ML) methods have been successfully employed in identifying variables that can predict the equity premium of individual stocks. In this paper, we investigate if ML can also be helpful in selecting variables relevant for optimal portfolio choice. To address this question, we parameterize minimum-variance portfolio weights as a function of a large pool of firm-level characteristics as well as their second-order and cross-product transformations, yielding a total of 4,610 predicto…

Generalizable Geometric Image Caption Synthesis
Yue Xin, Wenyuan Wang, Rui Pan, Ruida Wang, Howard Meng, Renjie Pi, Shizhe Diao, Tong Zhang
https://arxiv.org/abs/2509.15217 http…

Generalizable Geometric Image Caption Synthesis
Multimodal large language models have various practical applications that demand strong reasoning abilities. Despite recent advancements, these models still struggle to solve complex geometric problems. A key challenge stems from the lack of high-quality image-text pair datasets for understanding geometric images. Furthermore, most template-based data synthesis pipelines typically fail to generalize to questions beyond their predefined templates. In this paper, we bridge this gap by introducing…

And another question: Say I want to watch, comment and share videos from #Peertube (and nothing else like microblogging). Where should I create an account, which platform/software has @… in mind? It's not Peertube itself, right? Because that's for publishing…

Artist question: What’s the best media to set up an art portfolio for colleges?
#artist #question

#kde kmymoney also started to eat data. If Devs turn something from reliable and safe to unreliable and unsafe, the real question of liability comes into play. How can such a thing end in distribution?
Maybe we need to re-organize open source to have a reliable portfolio of applications, a kind of reliable #kde fr…

Toward Supporting Narrative-Driven Data Exploration: Barriers and Design Opportunities
Oliver Huang, Carolina Nobre
https://arxiv.org/abs/2508.04920 https://

Toward Supporting Narrative-Driven Data Exploration: Barriers and Design Opportunities
Analysts increasingly explore data through evolving, narrative-driven inquiries, moving beyond static dashboards and predefined metrics as their questions deepen and shift. As these explorations progress, insights often become dispersed across views, making it challenging to maintain context or clarify how conclusions arise. Through a formative study with 48 participants, we identify key barriers that hinder narrative-driven exploration, including difficulty maintaining context across views, tr…

Hedging Options on Asset Portfolios against Just One Underlying Asset in the Presence of Transaction Costs
Erina Nanyonga, Matt Davison
https://arxiv.org/abs/2509.07718 https://…

Hedging Options on Asset Portfolios against Just One Underlying Asset in the Presence of Transaction Costs
Options are contingent claims regarding the value of underlying assets. The Black-Scholes formula provides a road map for pricing these options in a risk-neutral setting, justified by a delta hedging argument in which countervailing positions of appropriate size are taken in the underlying asset. However, what if an underlying asset is expensive to trade? It might be better to hedge with a different, but related asset that is cheaper to trade. This study considers this question in a setting in …

JudgeAgent: Dynamically Evaluate LLMs with Agent-as-Interviewer
Zhichao Shi, Xuhui Jiang, Chengjin Xu, Cangli Yao, Zhenxin Huang, Shengjie Ma, Yinghan Shen, Yuanzhuo Wang
https://arxiv.org/abs/2509.02097

JudgeAgent: Dynamically Evaluate LLMs with Agent-as-Interviewer
Evaluating the capabilities of large language models (LLMs) is an essential step to ensure the successful application of LLMs across various domains. The current evaluation of LLMs is based on a paradigm that involves querying them with predefined question sets and assessing their outputs. This paradigm offers controllable processes and simplicity, but faces challenges such as limited interaction with targets, insufficient difficulty control, and difficulties in verifying the validity of evalua…

DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning
Shreyas Vinaya Sathyanarayana, Rahil Shah, Sharanabasava D. Hiremath, Rishikesh Panda, Rahul Jana, Riya Singh, Rida Irfan, Ashwin Murali, Bharath Ramsundar
https://arxiv.org/abs/2507.07060

DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning
Retrosynthesis, the identification of precursor molecules for a target compound, is pivotal for synthesizing complex molecules, but faces challenges in discovering novel pathways beyond predefined templates. Recent large language model (LLM) approaches to retrosynthesis have shown promise but effectively harnessing LLM reasoning capabilities for effective multi-step planning remains an open question. To address this challenge, we introduce DeepRetro, an open-source, iterative, hybrid LLM-based …

A 4% withdrawal rate for retirement spending, derived from a discrete-time model of stochastic returns on assets
Drew M. Thomas
https://arxiv.org/abs/2508.10273 https://

A 4% withdrawal rate for retirement spending, derived from a discrete-time model of stochastic returns on assets
What grounds the rule of thumb that a(n American) retiree can safely withdraw 4% of their initial retirement wealth in their first year of retirement, then increase that rate of consumption with inflation? I investigate that question with a discrete-time model of returns to a retirement portfolio consumed at a rate that grows by $s$ per period. The model hinges on the parameter $γ$, an $s$-adjusted rate of return to wealth, derived from the first 2-4 moments of the portfolio's probability dist…