A characterization of the reversibility of linear cellular automata
本文解决了线性细胞自动机可逆性的问题，通过证明在特定条件下存在双射线性细胞自动机其逆不是细胞自动机。
0 citationsRead paper
Selected work
Representative Papers
Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes
This work addresses the challenges of constructing and managing generative AI agent systems for long-horizon, stateful, multi-step business processes by proposing a graph-structured workflow design methodology. Leveraging the LangGraph framework, it explicitly models core mechanisms such as state management, conditional routing, and human-in-the-loop interventions. The approach is instantiated in three representative applications: SQL analysis with repair loops, retrieval-augmented generation gated by evidential validation, and human-AI collaborative policy review supporting interruption and checkpoint-based recovery. By treating behaviors like routing, pausing, and audit trails as explicit product features rather than implicit prompt logic, this study not only delineates the applicability boundaries of LangGraph in high-complexity workflows but also substantially enhances system controllability, reliability, and auditability in real-world operational settings, establishing a reusable engineering paradigm.
0 citationsRead paper
The Because-Calculus: Separating Production, Existence, and Interpretation in Computation
This work addresses the conflation of recoverable and non-recoverable effect operations in conventional program calculi, where a uniform `do` construct leads to vacuous resumption bindings. To resolve this, the paper introduces the because-calculus, which structurally separates effect registration (non-recoverable) from effect proof (recoverable) via a refined type system. Key innovations include dual effect rows and level-indexed types that statically eliminate invalid resumption clauses at compile time, and a novel Resumption Subconstraint that, for the first time, statically rules out vacuous resumptions. The authors establish a non-faithful collapse theorem mapping the calculus into a handler-based framework and formally prove progress, subject reduction, and tower progress properties. A categorical semantics further provides rigorous mathematical interpretations for all typing judgments.
0 citationsRead paper
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
This study systematically evaluates the stability and applicability of a validated instructional feedback classification protocol across evolving text representation methods—ranging from sparse features and frozen Transformer embeddings to prompting large language models—and under English–Spanish cross-lingual transfer. Through stratified cross-validation and human annotation consistency analysis, the research finds that while state-of-the-art large models circa 2026 achieve the highest F1 scores on Spanish topic classification, they do not significantly outperform lightweight models in sentiment classification or English tasks. These results demonstrate the protocol’s robustness over time and across languages, suggesting that model selection should prioritize deployment constraints over methodological novelty. This work provides the first empirical evidence of the resilience of an instructional feedback classification framework amid technological advances and multilingual scenarios.
0 citationsRead paper
Pandas for Reproducible Data Analysis: From Spreadsheets to Research-Grade Python Workflows
This work addresses the significant limitations of spreadsheet-based analysis in reproducibility, auditability, version control, and automation. It proposes a migration pathway from Excel to research-grade analytical workflows by leveraging Python’s pandas library as a bridge. The study introduces an innovative set of Excel-to-pandas mapping rules, categorizes nine canonical workflow patterns, and compiles a catalog of common failure modes. Seven end-to-end real-world examples demonstrate the approach in practice. By retaining Excel as a familiar interface for input and output while integrating version control, automated refreshing, and seamless incorporation of statistical and machine learning methods, the proposed framework enables governed, reproducible, and auditable tabular data analysis.
0 citationsRead paper
Recent publications
Latest Papers
A characterization of the reversibility of linear cellular automata
本文解决了线性细胞自动机可逆性的问题，通过证明在特定条件下存在双射线性细胞自动机其逆不是细胞自动机。
0 citationsRead paper
Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes
This work addresses the challenges of constructing and managing generative AI agent systems for long-horizon, stateful, multi-step business processes by proposing a graph-structured workflow design methodology. Leveraging the LangGraph framework, it explicitly models core mechanisms such as state management, conditional routing, and human-in-the-loop interventions. The approach is instantiated in three representative applications: SQL analysis with repair loops, retrieval-augmented generation gated by evidential validation, and human-AI collaborative policy review supporting interruption and checkpoint-based recovery. By treating behaviors like routing, pausing, and audit trails as explicit product features rather than implicit prompt logic, this study not only delineates the applicability boundaries of LangGraph in high-complexity workflows but also substantially enhances system controllability, reliability, and auditability in real-world operational settings, establishing a reusable engineering paradigm.
0 citationsRead paper
The Because-Calculus: Separating Production, Existence, and Interpretation in Computation
This work addresses the conflation of recoverable and non-recoverable effect operations in conventional program calculi, where a uniform `do` construct leads to vacuous resumption bindings. To resolve this, the paper introduces the because-calculus, which structurally separates effect registration (non-recoverable) from effect proof (recoverable) via a refined type system. Key innovations include dual effect rows and level-indexed types that statically eliminate invalid resumption clauses at compile time, and a novel Resumption Subconstraint that, for the first time, statically rules out vacuous resumptions. The authors establish a non-faithful collapse theorem mapping the calculus into a handler-based framework and formally prove progress, subject reduction, and tower progress properties. A categorical semantics further provides rigorous mathematical interpretations for all typing judgments.
0 citationsRead paper
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
This study systematically evaluates the stability and applicability of a validated instructional feedback classification protocol across evolving text representation methods—ranging from sparse features and frozen Transformer embeddings to prompting large language models—and under English–Spanish cross-lingual transfer. Through stratified cross-validation and human annotation consistency analysis, the research finds that while state-of-the-art large models circa 2026 achieve the highest F1 scores on Spanish topic classification, they do not significantly outperform lightweight models in sentiment classification or English tasks. These results demonstrate the protocol’s robustness over time and across languages, suggesting that model selection should prioritize deployment constraints over methodological novelty. This work provides the first empirical evidence of the resilience of an instructional feedback classification framework amid technological advances and multilingual scenarios.
0 citationsRead paper
Pandas for Reproducible Data Analysis: From Spreadsheets to Research-Grade Python Workflows
This work addresses the significant limitations of spreadsheet-based analysis in reproducibility, auditability, version control, and automation. It proposes a migration pathway from Excel to research-grade analytical workflows by leveraging Python’s pandas library as a bridge. The study introduces an innovative set of Excel-to-pandas mapping rules, categorizes nine canonical workflow patterns, and compiles a catalog of common failure modes. Seven end-to-end real-world examples demonstrate the approach in practice. By retaining Excel as a familiar interface for input and output while integrating version control, automated refreshing, and seamless incorporation of statistical and machine learning methods, the proposed framework enables governed, reproducible, and auditable tabular data analysis.
0 citationsRead paper