arXiv subjects

Ricardo Fitas

Publications and source records attributed to Ricardo Fitas.

7 recordsLinked to original sources

arXiv2026

The geometry of AI validation: From structural blindness to reusable audits

AI systems increasingly search among candidate answers and deploy the highest-scoring one. Increasing search changes which errors matter, so a precise evaluation at one computation budget can leave another budget unresolved. We connect this information gap to the cost of closing it. For independent best-of-n search, aggregate reliability measurements identify deployment only through the directions they observe; we derive an exact ambiguity frontier when only small search widths are audited. Retaining candidate ranks and truth labels enables a constructive alternative: one audit can estimate reliability across all widths up to N. With known score percentiles, the minimax worst-coordinate mean squared error scales as (1 + log N)/T + N/M, capped at a constant, for expected budgets of T truth labels and M candidate observations. Matching lower bounds allow adaptive label acquisition, establishing that the distinct label and candidate costs are intrinsic to this experiment. An explicit design attains this order; a complementary record-based procedure supplies simultaneous guarantees without a known score distribution. Retrospective mathematical-reasoning and code-generation analyses show why search-dependent validation matters. In held-out CodeRM pools, a shared audit reduces the 95th-percentile maximum error across 100 widths by 58% and 40% relative to uniform labeling. These results turn structural ambiguity into a quantitative prescription for reusable validation.

cs.LG↗

arXiv2025

The Author Is Sovereign: A Manifesto for Ethical Copyright in the Age of AI

In the age of AI, authorship is being quietly eroded by algorithmic content scraping, legal gray zones like "fair use," and platforms that profit from creative labor without consent or compensation. This short manifesto proposes a radical alternative: a system in which the author is sovereign of their intellectual domain. It presents seven ethical principles that challenge prevailing assumptions about open access, copyright ownership, and the public domain - arguing that voluntary, negotiated consent must replace coercive norms. The text exposes how weakened authorship fuels structural exploitation. In place of reactive solutions, it calls for a new ethic of authorship rooted in consent, dignity, and contractual fairness.

cs.CY↗

arXiv2025

Modeling the Effective Elastic Modulus and Thickness of Corrugated Boards Using Gaussian Process Regression and Expected Hypervolume Improvement

This work aims to model the hypersurface of the effective elastic modulus, $ E_{z, \text{eff}} $, and thickness, $ th_{\text{eff}} $, in corrugated boards. A Latin Hypercube Sampling (LHS) is followed by Gaussian Process Regression (GP), enhanced by EHVI as a multi-objective acquisition function. Accurate modeling of $ E_{z, \text{eff}} $ and $ th_{\text{eff}} $ is critical for optimizing the mechanical properties of corrugated materials in engineering applications. LHS provides an efficient and straightforward approach for an initial sampling of the input space; GP is expected to be able to adapt to the complexity of the response surfaces by incorporating both prediction and uncertainty. Therefore, the next points being generated and evaluated are based on the complexity of the hypersurfaces, and some points, especially those with higher variance, are more exploited and carry more importance. The performance of GP with EHVI is measured by Mean Squared Error (MSE). Prediction of GP resulted in $ \text{MSE}(E_{z, \text{eff}}) = 5.24 \, \text{kPa}^2 $ and $ \text{MSE}(th_{\text{eff}}) = 1 \, \text{mm}^2 $. GP possesses then improved accuracy and adaptability for future applications in structural optimization.

physics.app-ph↗

arXiv2025

On the Design of Corrugated Boards: A New FEM Modeling and Experimental Validation

This study presents a simplified FEM modeling approach suitable for large structures made of corrugated boards, such as customized packages, based on a homogenization method, which is combined with correction factors for internal mechanisms. The homogenization process reduces computational time by transforming flute geometries into equivalent elastic models. In large deformations and in the presence of contact for a given geometry, the effective elastic modulus in the thickness direction, as well as the effective thickness of the structure, are corrected by two statistical Weibull distributions representing the contact and buckling mechanisms in a corrugated board. The Weibull parameters are obtained via experimental analysis, and such a process is then validated. The results demonstrate that the statistical parameters ($β_1 = 0.14$, $β_2 = 1.31$) can be used for the simplistic representation of corrugated boards, being computationally efficient. This research contributes to the optimization of corrugated packaging design, specifically by simplifying FEM models for faster yet equally accurate simulations.

physics.app-ph↗

arXiv2025

Inclusive Education with AI: Supporting Special Needs and Tackling Language Barriers

Early childhood classrooms are becoming increasingly diverse, with students spanning a range of linguistic backgrounds and abilities. AI offers innovative tools to help educators create more inclusive learning environments by breaking down language barriers and providing tailored support for children with special needs. This chapter provides a comprehensive review of how AI technologies can facilitate inclusion in early education. It is discussed AI-driven language assistance tools that enable real-time translation and communication in multilingual classrooms, and it is explored assistive technologies powered by AI that personalize learning for students with disabilities. The implications of these technologies for teachers are examined, including shifts in educator roles and workloads. General outcomes observed with AI integration - such as improved student engagement and performance - as well as challenges related to equitable access and the need for ethical implementation are highlighted. Finally, practical recommendations for educators, policymakers, and developers are offered to collaboratively harness AI in a responsible manner, ensuring that its benefits reach all learners.

cs.CY↗

arXiv2024

A new simplified MOPSO based on Swarm Elitism and Swarm Memory: MO-ETPSO

This paper presents an algorithm based on Particle Swarm Optimization (PSO), adapted for multi-objective optimization problems: the Elitist PSO (MO-ETPSO). The proposed algorithm integrates core strategies from the well-established NSGA-II approach, such as the Crowding Distance Algorithm, while leveraging the advantages of Swarm Intelligence in terms of individual and social cognition. A novel aspect of the algorithm is the introduction of a swarm memory and swarm elitism, which may turn the adoption of NSGA-II strategies in PSO. These features enhance the algorithm's ability to retain and utilize high-quality solutions throughout optimization. Furthermore, all operators within the algorithm are intentionally designed for simplicity, ensuring ease of replication and implementation in various settings. Preliminary comparisons with the NSGA-II algorithm for the Green Vehicle Routing Problem, both in terms of solutions found and convergence, have yielded promising results in favor of MO-ETPSO.

cs.NE↗

arXiv2024

Optimal Design of Spur Gears using Particle Swarm Optimization

Optimizing the design of spur gears, regarding their mass or failure reduction, leads to reduced costs. The proposed work is aimed at using Particle Swarm Optimization (PSO) to solve single and multiple-objective optimization problems concerning spur gears. Pinion, number of teeth, the module, the face width, and the profile shift coefficients of both the pinion and wheel. Mass, gear loss factor, specific sliding, contact ratio, and safety factors are variables considered for the formulation of the objective function. The results show that those variables are reduced when compared to the results of the literature. Mass reduction, for instance, was possible to be achieved due to the reduction of the gear module and face width, increasing the number of teeth to achieve the required working center distance of the gear.

physics.comp-ph↗