arXiv subjects

Caio Gomes

Publications and source records attributed to Caio Gomes.

4 recordsLinked to original sources

arXiv2026

AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach

The explosive growth and complexity of product data within the dynamic Brazilian e-commerce landscape demand robust and specialized methods for structured information extraction. Traditional approaches to Product Attribute Value Extraction (PAVE) often struggle with the linguistic nuances and sheer diversity of product descriptions in Portuguese. To address this critical gap, this paper introduces two major contributions. First, we present AI-PAVEBr, a specialized system engineered with Large Language Models (LLMs) to perform high-accuracy PAVE specifically for Brazilian e-commerce catalogs. Second, to facilitate reproducible research and provide a definitive benchmark, we introduce and share the Golden Set, a new, meticulously curated, and manually annotated dataset for PAVE in Portuguese. We detail the creation process and structure (Entity, Category, Subcategories) of this high-quality reference set. Our experiments conclusively show that AI-PAVE-Br, leveraging targeted prompt engineering, dramatically outperforms conventional Named Entity Recognition (NER) baselines. This work not only delivers a superior, scalable solution for a major non-English market but also enriches the NLP community with a valuable, publicly available resource for future PAVE research.

cs.CL↗

arXiv2026

Your SaaS Is an Insurance Product: A Modeling Framework

Capped-usage SaaS products -- LLM subscriptions such as Claude Code and ChatGPT, cloud platforms such as Vercel and Cloudflare Workers, corporate benefit platforms, identity-verification services with liability transfer -- share a structural signature with insurance products: a fixed premium decoupled from realized consumption, stochastic per-user demand with heavy-tailed severity, a non-fungible cap that resets on a fixed schedule, and a portfolio-level exposure that requires reserve adequacy under tail risk. We argue that this is not an analogy. It is the same operational problem actuarial science has been tooled for decades to address, restated with new dependent variables (tokens, bandwidth bytes, function-invocations, gym check-ins) in place of medical claims. This paper proposes a modeling framework for capped-usage SaaS pricing built from frequency-severity decomposition, premium calculation principles, and Monte Carlo reserve adequacy. We map the framework to publicly observable subscription tiers in two domains (LLM services and cloud platforms), ground it in canonical health-insurance economics (Arrow 1963; Pauly 1968; Manning et al. 1987; Brot-Goldberg et al. 2017), and demonstrate divergence from traditional unit economics through a worked example. The contribution is operational rather than theoretical: not a new theorem, but vocabulary and tools currently absent from cs.LG/stat.ML practice.

cs.LG↗

arXiv2025

Equilibrium Points and Surface Dynamics About Comet 67P/Churyumov-Gerasimenko

Small bodies in our Solar System are considered remnants of their early formation. Studying their physical and dynamic properties can provide insights into their evolution, stability, and origin. ESA's Rosetta mission successfully landed and studied comet Churyumov-Gerasimenko (67P) for approximately two years. In this work, the aim is to analyze the surface and orbital dynamics of comet 67P in detail, using a suitable 3-D polyhedral shape model. We applied the polyhedron method to calculate dynamic surface characteristics, including geometric height, surface tilt, surface slopes, geopotential surface, acceleration surface, escape speed, equilibrium points, and zero-velocity curves. The results show that the gravitational potential is predominant on the comet's surface due to its slow rotation. The escape speed has the maximum value in the Hapi region (the comet's neck). The surface slopes were analyzed to predict possible regions of particle motion and accumulation. The results show that most regions of the comet's surface have low slopes. Furthermore, we analyzed the slopes under the effects of Third-Body gravitational and Solar Radiation Pressure perturbations. Our results showed that the effects of Third-Body perturbations do not significantly affect the global behavior of slopes. Meanwhile, the Solar Radiation Pressure does not significantly affect particles across the surface of comet 67P with sizes $>\sim10^{-3}$\,cm at apocenter and $>\sim10^{-1}$\,cm at pericenter. We also identified four equilibrium points around comet 67P and one equilibrium point inside the body, where points E$_2$ and E$_5$ are linearly stable. In addition, we approximated the shape of comet 67P using the simplified Dipole Segment Model to study its dynamics, employing parameters derived from its 3-D polyhedral shape model. We found 12 families of planar symmetric periodic orbits around the body.

astro-ph.EP↗

arXiv2018

Mediation Analysis in Online Experiments at Booking.com: Disentangling Direct and Indirect Effects

Online experimentation is at the core of Booking.com's customer-centric product development. While randomised controlled trials are a powerful tool for estimating the overall effects of product changes on business metrics, they often fall short in explaining the mechanism of change. This becomes problematic when decision-making depends on being able to distinguish between the direct effect of a treatment on some outcome variable and its indirect effect via a mediator variable. In this paper, we demonstrate the need for mediation analyses in online experimentation, and use simulated data to show how these methods help identify and estimate direct causal effect. Failing to take into account all confounders can lead to biased estimates, so we include sensitivity analyses to help gauge the robustness of estimates to missing causal factors.

cs.HC↗