-
Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge Graphs
Authors:
Ryoma Kondo,
Riona Matsuoka,
Takahiro Yoshida,
Kazuyuki Yamasawa,
Ryohei Hisano
Abstract:
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 stru…
▽ More
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.
△ Less
Submitted 24 August, 2025;
originally announced August 2025.
-
Video CLIP Model for Multi-View Echocardiography Interpretation
Authors:
Ryo Takizawa,
Satoshi Kodera,
Tempei Kabayama,
Ryo Matsuoka,
Yuta Ando,
Yuto Nakamura,
Haruki Settai,
Norihiko Takeda
Abstract:
Echocardiography records ultrasound videos of the heart, enabling clinicians to assess cardiac function. Recent advances in large-scale vision-language models (VLMs) have spurred interest in automating echocardiographic interpretation. However, most existing medical VLMs rely on single-frame (image) inputs, which can reduce diagnostic accuracy for conditions identifiable only through cardiac motio…
▽ More
Echocardiography records ultrasound videos of the heart, enabling clinicians to assess cardiac function. Recent advances in large-scale vision-language models (VLMs) have spurred interest in automating echocardiographic interpretation. However, most existing medical VLMs rely on single-frame (image) inputs, which can reduce diagnostic accuracy for conditions identifiable only through cardiac motion. In addition, echocardiographic videos are captured from multiple views, each varying in suitability for detecting specific conditions. Leveraging multiple views may therefore improve diagnostic performance. We developed a video-language model that processes full video sequences from five standard views, trained on 60,747 echocardiographic video-report pairs. We evaluated the gains in retrieval performance from video input and multi-view support, including the contributions of various pretrained models. Code and model weights are available at https://github.com/UTcardiology/video-echo-clip
△ Less
Submitted 8 November, 2025; v1 submitted 26 April, 2025;
originally announced April 2025.
-
Hierarchical Narrative Analysis: Unraveling Perceptions of Generative AI
Authors:
Riona Matsuoka,
Hiroki Matsumoto,
Takahiro Yoshida,
Tomohiro Watanabe,
Ryoma Kondo,
Ryohei Hisano
Abstract:
Written texts reflect an author's perspective, making the thorough analysis of literature a key research method in fields such as the humanities and social sciences. However, conventional text mining techniques like sentiment analysis and topic modeling are limited in their ability to capture the hierarchical narrative structures that reveal deeper argumentative patterns. To address this gap, we p…
▽ More
Written texts reflect an author's perspective, making the thorough analysis of literature a key research method in fields such as the humanities and social sciences. However, conventional text mining techniques like sentiment analysis and topic modeling are limited in their ability to capture the hierarchical narrative structures that reveal deeper argumentative patterns. To address this gap, we propose a method that leverages large language models (LLMs) to extract and organize these structures into a hierarchical framework. We validate this approach by analyzing public opinions on generative AI collected by Japan's Agency for Cultural Affairs, comparing the narratives of supporters and critics. Our analysis provides clearer visualization of the factors influencing divergent opinions on generative AI, offering deeper insights into the structures of agreement and disagreement.
△ Less
Submitted 11 November, 2024; v1 submitted 17 September, 2024;
originally announced September 2024.
-
LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis
Authors:
Lecheng Zheng,
Zhengzhang Chen,
Dongjie Wang,
Chengyuan Deng,
Reon Matsuoka,
Haifeng Chen
Abstract:
Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scena…
▽ More
Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scenarios from IT and OT operation systems, encompassing microservices, water distribution, and water treatment systems, with hundreds of system entities involved. We evaluate the quality of LEMMA-RCA by testing the performance of eight baseline methods on this dataset under various settings, including offline and online modes as well as single and multiple modalities. Our experimental results demonstrate the high quality of LEMMA-RCA. The dataset is publicly available at https://lemma-rca.github.io/.
△ Less
Submitted 16 May, 2025; v1 submitted 8 June, 2024;
originally announced June 2024.
-
A link between anomalous viscous loss and boson peak in soft jammed solids
Authors:
Yusuke Hara,
Ryosuke Matsuoka,
Hiroyuki Ebata,
Daisuke Mizuno,
Atsushi Ikeda
Abstract:
Soft jammed solids exhibit intriguing mechanical properties, while their linear response is elusive. In particular, foams and emulsions generally reveal anomalous viscous loss with the loss and storage modulus following $G^{\prime \prime} \propto \sqrtω$ and $G^{\prime} \propto ω^0$. In this study, we offer a comprehensive microscopic understanding of this behavior. Using microrheology experiment,…
▽ More
Soft jammed solids exhibit intriguing mechanical properties, while their linear response is elusive. In particular, foams and emulsions generally reveal anomalous viscous loss with the loss and storage modulus following $G^{\prime \prime} \propto \sqrtω$ and $G^{\prime} \propto ω^0$. In this study, we offer a comprehensive microscopic understanding of this behavior. Using microrheology experiment, we measured $G^* = G^{\prime} + i G^{\prime \prime}$ of concentrated emulsions in a wide range of frequencies. In theory, we applied a linear response formalism for microrheology to a soft sphere model that undergoes the jamming transition. We find that the theory quantitatively explains the experiments without the need for parameter adjustments. Our analysis reveals that the anomalous viscous loss results from the boson peak, which is a universal vibrational property of amorphous solids and reflects the marginal stability in soft jammed solids. We discuss that the anomalous viscous loss is universal in systems with various interparticle interactions as it stems from the universal boson peak, and it even survives below the jamming density where thermal fluctuation is pronounced and the dynamics becomes inherently nonlinear.
△ Less
Submitted 31 January, 2024;
originally announced February 2024.
-
Manifold Learning Approach for Chaos in the Dripping Faucet
Authors:
Hiromichi Suetani,
Karin Soejima,
Rei Matsuoka,
Ulrich Parlitz,
Hiroki Hata
Abstract:
Dripping water from a faucet is a typical example exhibiting rich nonlinear phenomena. For such a system, the time stamps at which water drops separate from the faucet can be directly observed in real experiments, and the time series of intervals τ_n between drop separations becomes a subject of analysis. Even if the mass m_n of a drop at the onset of the n-th separation, which cannot be observed…
▽ More
Dripping water from a faucet is a typical example exhibiting rich nonlinear phenomena. For such a system, the time stamps at which water drops separate from the faucet can be directly observed in real experiments, and the time series of intervals τ_n between drop separations becomes a subject of analysis. Even if the mass m_n of a drop at the onset of the n-th separation, which cannot be observed directly, exhibits perfectly deterministic dynamics, it sometimes fails to obtain important information from time series of τ_n. This is because the return plot τ_n-1 vs. τ_n may become a multi-valued function, i.e., not a deterministic dynamical system. In this paper, we propose a method to construct a nonlinear coordinate which provides a "surrogate" of the internal state m_n from the time series of τ_n. Here, a key of the proposed approach is to use ISOMAP, which is a well-known method of manifold learning. We first apply it to the time series of $τ_n$ generated from the numerical simulation of a phenomenological mass-spring model for the dripping faucet system. It is shown that a clear one-dimensional map is obtained by the proposed approach, whose characteristic quantities such as the Lyapunov exponent, the topological entropy, and the time correlation function coincide with the original dripping faucet system. Furthermore, we also analyze data obtained from real dripping faucet experiments which also provides promising results.
△ Less
Submitted 23 May, 2012;
originally announced May 2012.