Selected work

Representative Papers

Designing a Token Economy: Incentives, Governance, and Tokenomics

Feb 10, 2026

This study addresses the absence of a systematic, reusable, and empirically grounded end-to-end approach that integrates incentive mechanisms, governance structures, and tokenomics in current token economic designs. To bridge this gap, the paper proposes the Token Economic Design Method (TEDM), which, for the first time, unifies these three dimensions into a structured and actionable design framework, with explicit emphasis on sociotechnical context and early-stage design considerations. Developed through the design science research paradigm and informed by qualitative synthesis, co-design case studies, and expert interviews, TEDM was empirically validated through its application to the Currynomics stablecoin ecosystem and subsequent expert evaluation. The results demonstrate that TEDM effectively supports the analysis and construction of tokenized ecosystems, offering practical and reusable design guidance.

3 citationsRead paper

Handling mild outliers and unobserved values in compositional datasets using finite mixtures of mean-parametrised Dirichlet models

Aug 24, 2026

本文提出了一种基于均值参数化Dirichlet模型的混合模型，用于处理同时存在缺失值和异常点的成分数据集，并通过期望最大化算法进行参数估计。

0 citationsRead paper

The Illusion of Cross-Lingual Safety in Low-Resource Languages

Aug 11, 2026

Current safety alignment of large language models is predominantly based on English, and their cross-lingual generalization to low-resource languages remains poorly understood, posing potential risks. This work introduces the LoDNA dataset, comprising both literal translations and culturally localized prompts, to systematically evaluate the transferability of safety mechanisms across four African languages. We propose a probing method grounded in the geometric structure of the model’s latent space to analyze internal representations underlying refusal behaviors. Our study reveals, for the first time, significant limitations in cross-lingual safety alignment: in most language–model combinations, harmful prompts retain less than 10% of the refusal signal observed in English, indicating that semantic alignment does not ensure consistent safety routing. These findings challenge the assumption of a language-invariant harm manifold.

0 citationsRead paper

Blast Radius

Aug 07, 2026

This work addresses the high computational cost and inefficient token consumption in agent programming caused by poor context management. The authors propose a predictive memory management layer that models contexts in a Polish context space, coupling contextual and code channels to assess prompt reachability and incorporating a reversible context eviction mechanism. They introduce an innovative archiving strategy termed NECROPHORESIS, enabling byte-level reversible storage of dead contexts, and integrate a Recurring Dead Matter (RDM) algorithm to identify and bury redundant, useless records. Experimental results across seven OpenAI models demonstrate a 17–26% reduction in token consumption—the lowest overflow rate among compared methods—and reveal that 378 of 450 buried records were duplicate dead content, none of which required recall, thereby validating both the efficacy and reversibility of the proposed approach.

0 citationsRead paper

Bounded elementary extensions of trees with unbounded paths

Jul 21, 2026

This study addresses the problem of elementarily embedding trees with unbounded paths into bounded trees to support the formal modeling of infinite computational processes. To this end, the authors propose a set of sufficient conditions guaranteeing the existence of such embeddings and introduce several tree operations that yield a compositional semantic framework grounded in the Feferman–Vaught theorem. This framework employs first-order logic to characterize path structures and establishes that the defined operations preserve logical properties. The main contribution lies in developing an extendable method for bounded trees that enables tractable modeling of infinite computation sequences, thereby providing a model-theoretic foundation for finite representations of infinite behaviors.

0 citationsRead paper

Recent publications

Latest Papers

Handling mild outliers and unobserved values in compositional datasets using finite mixtures of mean-parametrised Dirichlet models

Aug 24, 2026

本文提出了一种基于均值参数化Dirichlet模型的混合模型，用于处理同时存在缺失值和异常点的成分数据集，并通过期望最大化算法进行参数估计。

0 citationsRead paper

The Illusion of Cross-Lingual Safety in Low-Resource Languages

Aug 11, 2026

Current safety alignment of large language models is predominantly based on English, and their cross-lingual generalization to low-resource languages remains poorly understood, posing potential risks. This work introduces the LoDNA dataset, comprising both literal translations and culturally localized prompts, to systematically evaluate the transferability of safety mechanisms across four African languages. We propose a probing method grounded in the geometric structure of the model’s latent space to analyze internal representations underlying refusal behaviors. Our study reveals, for the first time, significant limitations in cross-lingual safety alignment: in most language–model combinations, harmful prompts retain less than 10% of the refusal signal observed in English, indicating that semantic alignment does not ensure consistent safety routing. These findings challenge the assumption of a language-invariant harm manifold.

0 citationsRead paper

Blast Radius

Aug 07, 2026

This work addresses the high computational cost and inefficient token consumption in agent programming caused by poor context management. The authors propose a predictive memory management layer that models contexts in a Polish context space, coupling contextual and code channels to assess prompt reachability and incorporating a reversible context eviction mechanism. They introduce an innovative archiving strategy termed NECROPHORESIS, enabling byte-level reversible storage of dead contexts, and integrate a Recurring Dead Matter (RDM) algorithm to identify and bury redundant, useless records. Experimental results across seven OpenAI models demonstrate a 17–26% reduction in token consumption—the lowest overflow rate among compared methods—and reveal that 378 of 450 buried records were duplicate dead content, none of which required recall, thereby validating both the efficacy and reversibility of the proposed approach.

0 citationsRead paper

Bounded elementary extensions of trees with unbounded paths

Jul 21, 2026

This study addresses the problem of elementarily embedding trees with unbounded paths into bounded trees to support the formal modeling of infinite computational processes. To this end, the authors propose a set of sufficient conditions guaranteeing the existence of such embeddings and introduce several tree operations that yield a compositional semantic framework grounded in the Feferman–Vaught theorem. This framework employs first-order logic to characterize path structures and establishes that the defined operations preserve logical properties. The main contribution lies in developing an extendable method for bounded trees that enables tractable modeling of infinite computation sequences, thereby providing a model-theoretic foundation for finite representations of infinite behaviors.

0 citationsRead paper

An extendable, integrated, and dynamic approach to forecasting and stress-testing credit risk

Jun 17, 2026

This study addresses the limitations of traditional stress testing approaches, which often decouple loan origination dynamics and neglect the correlation structure among risk indicators, thereby failing to capture the evolving nature of credit risk. To overcome these shortcomings, the paper proposes an integrated, scalable dynamic stress testing framework that, for the first time, jointly models loan issuance and credit risk prediction. The framework employs a multi-state probabilistic model to simulate loan cash flows and embeds macroeconomic stress scenarios directly within Monte Carlo simulations. It allows risk parameters to adjust dynamically in response to both macroeconomic and microeconomic variables and explicitly incorporates the interdependencies among key risk metrics. This approach significantly enhances the realism, flexibility, and forward-looking capability of stress testing, enabling dynamic forecasts of portfolio-level default and loss rates under a wide range of scenarios.

0 citationsRead paper