Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Digital Resilience and Communication Strategies in Underfunded Museums in Argentina and Spain (2020-2024)

  • Martí Testón, Ana|||0000-0002-5058-2868
  • Climent-Ferrer, Juan José|||0000-0003-4130-6439
  • Muñoz García, Adolfo|||0000-0003-2435-3348
  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Gracia Calandin, Luis Ignacio|||0000-0001-9258-9286
  • Lanusse, Lucía
[EN] Between 2020 and 2024, museums underwent accelerated digital transformation driven by the global health crisis and technological advances, exposing deep inequalities in access to technology and communication capabilities. Museums with limited resources had to rethink their digital strategies to sustain audience engagement and cultural relevance. This article presents a comparative study of museums in Argentina and Spain with restricted budgets, analyzing how they responded to challenges of uncertainty and scarcity. Using a mixed methodology¿surveys of 22 professionals, interviews with directors of four representative museums, and qualitative case studies¿this study examines the implemented solutions and their impacts. The findings highlight innovative practices grounded in creativity, strategic alliances, and intensive use of social media. Argentine museums excelled in tactical adaptation amid economic instability, while Spanish institutions showed stronger strategic planning. Private museums proved more flexible than their public counterparts, which faced greater bureaucratic constraints. This work contributes to debates on institutional resilience and offers a framework for sustainable digital communication in resource-limited contexts., This work received funding from the European Union's DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Crisis Disinformation and Verification Dynamics in the València 2024 DANA

  • Climent-Ferrer, Juan José|||0000-0003-4130-6439
  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Martí Testón, Ana|||0000-0002-5058-2868
  • Moriniello, Flavio|||0009-0006-0360-8822
  • Muñoz García, Adolfo|||0000-0003-2435-3348
  • Gracia Calandin, Luis Ignacio|||0000-0001-9258-9286
[EN] This study examines the circulation of disinformation during the 2024 València DANA (high-altitude isolated depression), which produced torrential rainfall across eastern and southern Spain between 29 and 31 October 2024. Using a quantitative content analysis, it analyzes the 100 most viral false or misleading claims, classifying them by typology, format, dissemination channel, and narrative strategy. Findings show an ecosystem dominated by conspiracy narratives about the causes of the disaster and by audiovisual content¿particularly short videos and images¿which achieved substantially greater reach than textual posts. Narrative mechanisms such as decontextualization, emotional appeal, and political polarization were recurrent and often combined. Verification efforts that matched the original format were associated with higher relative correction reach, although their observable diffusion remained lower than that of the false claims in the analyzed sample. Overall, the study highlights the cross-platform and multimodal dynamics of crisis disinformation and underscores the need for proactive, technologically supported communication strategies. These include automated monitoring, multimodal verification, and interoperable digital infrastructures for crisis communication., This work has received funding from the European Union s DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MICIU/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Geometry-Aware Conformal Temperature Calibration for Entropic Action Selection in Reinforcement Learning

  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Francés-Falip, Aitana
[EN] Entropy-based soft-min operators and Gibbs policies are widely used in reinforcement learning to smooth greedy decisions and regulate stochastic action selection. Their behavior depends critically on an inverse temperature parameter, which is often chosen through fixed values, annealing schedules, entropy targets, or worst-case bounds. These rules do not directly control the local error induced by soft action selection and do not account for the geometry of the action-value vector. This paper develops a geometry-aware conformal calibration framework for selecting inverse temperatures in discounted finite-action reinforcement learning. The analysis distinguishes the operator-level soft-min approximation error from decision-level Gibbs excess and shows how both quantities depend on local value gaps and a near-optimal action structure. A conformal order statistic rule is then used to obtain finite-sample marginal control of the selected local score under exchangeability. A geometry-conditional extension assigns different temperatures to different action-value geometries. The Bellman analysis clarifies that fixed temperature maps preserve contraction, while data-dependent conformal selectors are best interpreted as post-training action selection rules. A finite-MDP experiment empirically confirms the conformal coverage behavior and shows that calibration must be applied to a decision-relevant cost representation when value estimates contain optimistic value estimation traps. An Atari SpaceInvaders experiment with a frozen deep Q-network shows that the learned action-value geometry is heterogeneous, that decision-level calibration is less conservative than operator-level calibration, and that gated geometry-conditional selection preserves most of the greedy return while providing explicit marginal score control of randomized decision excess with low online overhead., This work has received funding from the European Union s DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Geometry-Aware Conformal Calibration of Entropic Soft-Min Operators for Machine Learning and Reinforcement Learning

  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Francés-Falip, Aitana
[EN] Entropic soft-min operators are widely used to obtain smooth approximations of minimum and argmin mechanisms in optimization, machine learning, and reinforcement learning. The quality of this approximation is controlled by an inverse temperature parameter that governs the trade-off between smoothness and fidelity, yet its selection is usually based on global heuristics or worst-case bounds that do not account for the geometry of the candidate cost vector. This study investigates the calibration of the inverse temperature parameter from a geometry-aware perspective, with explicit guarantees on the approximation error between the entropic soft-min and the exact minimum value. After establishing the structural properties of the relaxation error, including monotonicity with respect to the inverse temperature and its dependence on the geometry of the near-optimal set, we introduce a conformal calibration rule that selects the smallest inverse temperature, ensuring that a prescribed upper quantile of the approximation error remains below a target tolerance with distribution-free finite-sample validity. The resulting selector adapts to the geometry distribution represented in the calibration population and provides a principled alternative to mean-based and worst-case tuning rules. Numerical experiments, including geometry-controlled benchmarks and a contextual bandit setting illustrating the impact of geometry-aware calibration on decision-making under estimated action values, show that the proposed method accurately tracks oracle calibration temperatures, preserves the desired operator-level coverage, and makes explicit how geometric heterogeneity governs the effective sharpness required by the soft-min approximation. Additional shifted evaluations illustrate the role of exchangeability in the validity guarantee and the consequences of transferring temperatures across populations with different near-optimal geometries., This work has received funding from the European Union s DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Regime-Adaptive Conformal Calibration of Entropic Soft-Min Relaxations for Heterogeneous Optimization Problems

  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Francés-Falip, Aitana
[EN] Entropic soft-min relaxations are widely used to obtain smooth approximations of minimum operators in optimization, machine learning, and control. The accuracy of this approximation is governed by an inverse temperature (or sharpness) parameter that controls the trade-off between smoothness and fidelity, yet its principled selection is typically heuristic. This work studies the data-driven calibration of the inverse temperature parameter governing the entropic soft-min relaxation, with explicit guarantees on the relaxation error between the soft-min operator and the infimum of the cost function. After establishing monotonicity properties and approximation bounds for the relaxation error, we introduce a conformal calibration rule that selects the smallest inverse temperature ensuring that the approximation error satisfies a prescribed tolerance with distribution-free finite-sample validity. The resulting selector adapts to the distribution of candidate cost-vector geometries represented in the calibration sample, enabling regime-specific inverse temperature selection in heterogeneous settings. Numerical experiments, including an adaptive cruise control application with safety filtering, show that the proposed method accurately tracks oracle calibration inverse temperatures and achieves near-target coverage in the exchangeable setting covered by the theory, while an additional shifted evaluation illustrates the role of this assumption., This work has received funding from the European Union's DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Explainable Early-Warning of High-Amplification Crisis-Related Disinformation in Social Media Streams

  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Climent-Ferrer, Juan José|||0000-0003-4130-6439
  • Moriniello, Flavio|||0009-0006-0360-8822
  • Martí Testón, Ana|||0000-0002-5058-2868
  • Muñoz García, Adolfo|||0000-0003-2435-3348
  • Gracia Calandin, Luis Ignacio|||0000-0001-9258-9286
[EN] Rumors, misleading claims, and other factually risky information units may gain visibility during crises before verification processes are complete. Existing detection systems often address factual status or diffusion separately, whereas operational monitoring requires identifying units that are both factually risky and highly amplified by a forecast horizon. This paper proposes the Disinformation Diffusion Virality Risk Index (DDVRI), an explainable early-warning framework for estimating this joint risk from evidence observed during a prespecified early window. The formulation defines early histories, adjudicated factual labels, fold-specific amplification thresholds estimated without test outcomes, optional absolute amplification floors, block-structured early representations, calibrated risk scores, and capacity-constrained alerting rules. The proposed framework is evaluated using two open datasets, one focused on crisis rumors and another focused on COVID-19 health misinformation with social engagement information. The results support DDVRI as a probabilistic early-warning and prioritization methodology for rare cases that combine factual risk and high-amplification, rather than as a general fake-news classifier or an automatic moderation system., This work has received funding from the European Union's DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT), from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033), and from the Generalitat Valenciana under Grant CIGE/2024/195.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Domain-Transportable Latent Summaries for RobustMultimodal Autism Phenotyping Under Missing Modality Blocks

  • Solanes, J. Ernesto|||0000-0001-5011-4872
  • Francés-Falip, Aitana
  • Linares-Pellicer, Jordi
[EN] Autism spectrum disorder is heterogeneous across clinical presentation, cognition, development, and biological profile. This heterogeneity complicates multimodal phenotyping when measurements are grouped in different modality blocks: Some blocks are missing, and deployment sites differ from training sites. We introduce a hierarchical latent-summary framework for multimodal autism phenotyping under incomplete observation and domain shift. The model separates a shared global latent summary from block-specific latent summaries. It makes block configurations, missingness patterns, and domain labels explicit. Under compactness, continuity, coupling observability, and inverse-stability assumptions, recovered summaries are well defined, and the error in the global summary can be bounded. This error control propagates to block-specific summaries under Lipschitz coupling maps. Domain variation is handled through a Wasserstein risk envelope in recovered latentsummary space. The guarantee is conditional on the deployment distribution lying inside the prescribed Wasserstein ball. Empirical evaluation has two complementary roles. Two synthetic studies test the structural mechanisms predicted by the theory: The first shows the asymmetric block value, nonuniform missing-block degradation, and a near tie between the full block set and a stable reduced configuration; the second separates practical train-only radius calibration from a certified transport construction. A real-data clinical illustration using the Autism Brain Imaging Data Exchange (ABIDE) phenotypic and preprocessed imaging-derived variables then examines whether the cross-sectional surrogate exposes analogous block-structured phenomena in a multisite autism cohort after excluding direct diagnostic symptom instruments. This illustration shows modest site-held-out diagnostic signals, clear block asymmetry, substantial site-level instability, and limited degradation under moderate additional block removal. These findings support a block-structured view of multimodal autism phenotyping in which prediction, missingness, latent recovery, and transportability must be evaluated jointly., This work received funding from the European Union s DIGITAL Europe Programme under Grant Agreement No. 101226207 (project AI-SECRETT); from the Spanish Government under Grant PID2024-156583OB-I00 (funded by MCIN/AEI/10.13039/501100011033); and from the Generalitat Valenciana under Grant CIGE/2024/195.