Court judgments reveal how legal rules have been interpreted and applied to facts, providing a foundation for understanding structured legal reasoning. However, existing automated approaches for capturing legal reasoning, including large language models, often fail to identify the relevant legal context, do not accurately trace how facts relate to legal norms, and may misrepresent the layered structure of judicial reasoning. These limitations hinder the ability to capture how courts apply the law to facts in practice. In this paper, we address these challenges by constructing a legal knowledge graph from 648 Japanese administrative court decisions. Our method extracts components of legal reasoning using prompt-based large language models, normalizes references to legal provisions, and links facts, norms, and legal applications through an ontology of legal inference. The resulting graph captures the full structure of legal reasoning as it appears in real court decisions, making implicit reasoning explicit and machine-readable. We evaluate our system using expert annotated data, and find that it achieves more accurate retrieval of relevant legal provisions from facts than large language model baselines and retrieval-augmented methods.

Large language models (LLMs) have demonstrated promising performance in various financial applications, though their potential in complex investment strategies remains underexplored. To address this gap, we investigate how LLMs can predict price movements in stock and bond portfolios using economic indicators, enabling portfolio adjustments akin to those employed by institutional investors. Additionally, we explore the impact of incorporating different personas within LLMs, using an ensemble approach to leverage their diverse predictions. Our findings show that LLM-based strategies, especially when combined with the mode ensemble, outperform the buy-and-hold strategy in terms of Sharpe ratio during periods of rising consumer price index (CPI). However, traditional strategies are more effective during declining CPI trends or sharp market downturns. These results suggest that while LLMs can enhance portfolio management, they may require complementary strategies to optimize performance across varying market conditions.

High-resolution nowcasting flood prediction using streaming rainfall big data is desired for soft countermeasures against pluvial floods. Although an integrated flood analysis model consisting of a diffusion-wave equation, momentum equations and so on can simulate flood processes accurately, the model is unsuitable for nowcasting flood prediction due to its high computational cost. To realize accurate and computationally inexpensive nowcasting pluvial flood prediction, we have applied the knowledge distillation (KD) technique for training a lightweight neural network with the integrated flood analysis as a teacher. In the previous work, we showed its applicability in terms of prediction time and accuracy. However, this KD-based approach would not be sufficiently accurate in predicting floods caused by rainfall in minor rainfall patterns. To cope with it, we propose a prioritized sampling method that compensates for the imbalance between rainfall patterns. The rainfall patterns are mined from big rainfall data based on the spatiotemporal features of rainfall intensity over a rainfall duration. Compared to random sampling, we show that our prioritized sampling reduces the average prediction error of floods caused by rainfall in a minor rainfall pattern by 37 cm per mesh, which is equivalent to 96% reduction in error rate.

With the development of 360° cameras and viewing devices, panoramic vision has become increasingly familiar to the general public. Services that allow users to view scenes from 360Âř perspectives, such as Google Street View, that provides 360° still images of roads system, have become popular. However, there is no service exists that allows users to post and share unique 360° videos of participatory events using an intuitive interface, which enable switching to different viewpoints. We believe that such a system would increase the enjoyment of various entertainment events. Therefore, we have designed MM360, an intuitive GPS-linked 360° video sharing system that allows users to capture and post 360° videos easily and change view positions seamlessly.