Accurate yet interpretable prediction of Global Warming Potential (GWP) is essential for the sustainable design of novel molecules, chemical processes and materials. This capability is valuable in the early-stage screening of compounds with potential relevance to carbon management and emerging CCUS applications. However, conventional models often face a trade-off between predictive accuracy and interpretability. In this study, we propose an AI-based GWP prediction framework that integrates both molecular and process-level features to improve accuracy while employing white-box modeling techniques to enhance interpretability. First, by incorporating molecular descriptors (MACCS keys, Mordred descriptors) and process-level information (process title, description, location), the Deep Neural Network (DNN) model achieved an R² of 86% on the test data, representing a 25% improvement over the most comparable benchmark reported in prior studies. XAI analysis further highlights the crucial role of process-related features, particularly process title embeddings, in enhancing model predictions. Second, to address the need for model transparency, we employed a Kolmogorov–Arnold Network (KAN) model to develop a symbolic, white-box GWP prediction model. While achieving a lower R² of 64%, this model provides explicit mathematical representations of GWP relationships, enabling interpretable decision-making in sustainable chemical and process design. Our findings demonstrate that integrating molecular and process-level features improves both predictive accuracy and interpretability in GWP modelling. The resulting framework can support early-stage environmental assessment of novel compounds, offering a useful tool to inform the sustainable design of chemicals, including those with potential applications in CCUS.

Accurate yet interpretable prediction of Global Warming Potential (GWP) is essential for the sustainable design of novel molecules, chemical processes and materials. This capability is valuable in the early-stage screening of compounds with potential relevance to carbon management and emerging CCUS applications. However, conventional models often face a trade-off between predictive accuracy and interpretability. In this study, we propose an AI-based GWP prediction framework that integrates both molecular and process-level features to improve accuracy while employing white-box modeling techniques to enhance interpretability. First, by incorporating molecular descriptors (MACCS keys, Mordred descriptors) and process-level information (process title, description, location), the Deep Neural Network (DNN) model achieved an R² of 86% on the test data, representing a 25% improvement over the most comparable benchmark reported in prior studies. XAI analysis further highlights the crucial role of process-related features, particularly process title embeddings, in enhancing model predictions. Second, to address the need for model transparency, we employed a Kolmogorov–Arnold Network (KAN) model to develop a symbolic, white-box GWP prediction model. While achieving a lower R² of 64%, this model provides explicit mathematical representations of GWP relationships, enabling interpretable decision-making in sustainable chemical and process design. Our findings demonstrate that integrating molecular and process-level features improves both predictive accuracy and interpretability in GWP modelling. The resulting framework can support early-stage environmental assessment of novel compounds, offering a useful tool to inform the sustainable design of chemicals, including those with potential applications in CCUS.

Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation over Transformation (EOT) attack. We investigate the effect of the adversarial attacks using proxy gradients on randomized neural networks and demonstrate that it highly relies on the directional distribution of the loss gradients of the randomized neural network. We show in particular that proxy gradients are less effective when the gradients are more scattered. To this end, we propose Gradient Diversity (GradDiv) regularizations that minimize the concentration of the gradients to build a robust randomized neural network. Our experiments on MNIST, CIFAR10, and STL10 show that our proposed GradDiv regularizations improve the adversarial robustness of randomized neural networks against a variety of state-of-the-art attack methods. Moreover, our method efficiently reduces the transferability among sample models of randomized neural networks.

Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to complex structural tasks like web design. As lay creators increasingly turn to LLMs to 'vibe-code' websites -- prompting for aesthetic and functional goals rather than writing code -- they may inadvertently narrow the diversity of their designs, and limit creative expression throughout the internet. In this paper, we interrogate the possibility of design homogenization in web vibe coding. We first characterize the vibe coding lifecycle, pinpointing stages where homogenization risks may arise. We then conduct a sociotechnical risk analysis unpacking the potential harms of web vibe coding and their interaction with design homogenization. We identify that the push for frictionless generation can exacerbate homogenization and its harms. Finally, we propose a mitigation framework centered on the idea of productive friction. Through case studies at the micro, meso, and macro levels, we show how centering productive friction can empower creators to challenge default outputs and preserve diverse expression in AI-mediated web design.

Abstract Accurate forecasting of precious metal prices is increasingly critical in modern financial markets, as these metals function as industrial commodities and as strategic financial instruments for portfolio diversification and risk management. Although recent advances in financial technology have produced a range of forecasting approaches from traditional econometric methods to sophisticated deep learning models—the complex dynamics of metal prices continue to challenge existing methodologies. This paper introduces a significant innovation in financial forecasting by revealing and leveraging previously unrecognized pattern relationships in decomposed time series data. Our comprehensive analysis of metal price dynamics reveals distinct grouped patterns in decomposed time series components, challenging the conventional assumption of independence in current forecasting methods. Based on these insights, we propose the pattern-guided forecasting framework (PGFF), which enhances forecasting accuracy by leveraging cross-dimensional pattern relationships in decomposed time series. Our framework employs a novel two-stage approach: first, categorizing decomposed time series based on their temporal characteristics and autocorrelation patterns; then, implementing cross-dimensional forecasting to capture complex market dynamics. Empirical analysis of four major precious metals demonstrates that PGFF consistently outperforms existing forecasting frameworks, offering significant implications for investment decision-making and portfolio management in modern financial markets.

This study comprehensively explores whether there actually exist "emotion neurons" within large language models (LLMs) that selectively process and express certain emotions, and what functional role they play.Drawing on the representative emotion theory of the six basic emotions, we focus on six core emotions.Using synthetic dialogue data labeled with emotions, we identified sets of neurons that exhibit consistent activation patterns for each emotion.As a result, we confirmed that principal neurons handling emotion information do indeed exist within the model, forming distinct groups for each emotion, and that their distribution varies with model size and architectural depth.We then validated the functional significance of these emotion neurons by analyzing whether the prediction accuracy for a specific emotion significantly decreases when those neurons are artificially removed.We observed that in some emotions, the accuracy drops sharply upon neuron removal, while in others, the model's performance largely remains intact or even improves, presumably due to overlapping and complementary mechanisms among neurons.Furthermore, by examining how prediction accuracy changes depending on which layer range and at what proportion the emotion neurons are masked, we revealed that emotion information is processed in a multilayered and complex manner within the model.

On March 13, 2024, Ethereum implemented EIP-4844, an upgrade designed to enhance its role as a data availability layer. While this upgrade reduces data posting costs for rollups, it also raises concerns about its impact on consensus security due to the increased volume of propagated data. Moreover, the broader effects on rollup dynamics and the Ethereum ecosystem remain largely unexplored. In this paper, we conduct an empirical analysis of EIP-4844's impact on consensus security, Ethereum usage, rollup transaction dynamics, and the blob gas fee market. We investigate changes in slot sync time, provide quantitative assessments of rollup and user behaviors, and evaluate the efficiency of the blob gas fee market. Our findings reveal that EIP-4844 has successfully increased rollups' usage of Ethereum while lowering rollup transaction fees. However, we also observe a slight rise in the fork rate, though our analysis suggests that this increase is not attributed to blob propagation waiting time. Additionally, some rollup users experience delayed transaction inclusion in Ethereum blocks, which appears to be influenced by cost-minimizing batching strategies. These results demonstrate both the benefits and trade-offs of the upgrade, suggesting future directions for further research on Ethereum's scalability and consensus stability.