math-skill 2.0.1 → 2.1.0

package/knowledge-base/overview.en.md

@@ -0,0 +1,228 @@
+# Mathematical Knowledge System Overview
+
+## Overview
+
+The mathematical knowledge system is the structured framework of the discipline of mathematics, spanning from foundational concepts to cutting-edge subfields. It describes not only the hierarchical relationships among sub-disciplines, but also how mathematical methods complement and synergize across different problem domains.
+
+This overview is designed to help you:
+
+- Quickly locate the discipline and method area to which a mathematical problem belongs;
+- Understand the correspondence between the 16 thinking weapons in this project (15 weapons + math-research-activator) and mathematical sub-disciplines;
+- Build a holistic understanding from problem to tool, from concept to application.
+
+The development of mathematics has been jointly driven by logical reasoning, scientific needs, and cross-disciplinary applications.
+
+## 1. The Three Foundational Pillars of Mathematics
+
+The edifice of modern mathematics is built on **set theory** and **mathematical logic**. The three foundational disciplines are:
+
+### Algebra
+
+The study of numbers, structures, relationships, and symbolic operations.
+
+| Level | Content | Core Concepts |
+|-------|---------|--------------|
+| Elementary Algebra | Equations, inequalities, polynomial operations | Variables, identities, operation laws |
+| Advanced Algebra (Linear Algebra) | Vector spaces, linear transformations, matrices | Linear spaces, bases, dimension, eigenvalues |
+| Abstract Algebra | Groups, rings, fields | Algebraic structures, homomorphisms, isomorphisms |
+| Category Theory | Abstract theory of objects and morphisms | Functors, natural transformations, universal properties |
+
+### Geometry
+
+The study of space, shape, structure, and their relationships.
+
+| Level | Content | Core Concepts |
+|-------|---------|--------------|
+| Euclidean Geometry | Plane and solid geometry | Points, lines, planes, angles, distances |
+| Analytic Geometry | Studying geometry via algebraic methods | Coordinate systems, equations, curves |
+| Non-Euclidean Geometry | Geometries with modified parallel postulates | Hyperbolic geometry, elliptic geometry |
+| Differential Geometry | Studying geometry via calculus | Curvature, geodesics, manifolds |
+| Fractal Geometry | Self-similar geometric structures | Fractal dimension, iterated function systems |
+
+### Analysis
+
+The study of functions, limits, continuity, differentiation, and integration.
+
+| Level | Content | Core Concepts |
+|-------|---------|--------------|
+| Calculus | Limits, derivatives, integrals | Continuity, differentiability, integrability |
+| Mathematical Analysis | Rigorous limit theory | $\varepsilon$-$\delta$ language, uniform convergence |
+| Real Analysis | Measure theory, Lebesgue integration | Measure spaces, $L^p$ spaces |
+| Complex Analysis | Theory of complex functions | Analytic functions, residues, conformal mappings |
+| Functional Analysis | Analysis on infinite-dimensional spaces | Banach spaces, Hilbert spaces, operators |
+| Differential Equations | ODEs and PDEs | Existence, uniqueness, stability, numerical methods |
+
+## 2. Major Branches
+
+### 1. Number Theory
+
+The study of integer properties, such as prime distribution, congruences, and Diophantine equations.
+
+- **Elementary Number Theory**: Divisibility, congruences, primes
+- **Analytic Number Theory**: Using analytical methods for number-theoretic problems (e.g., the Prime Number Theorem)
+- **Algebraic Number Theory**: Using algebraic methods for number-theoretic problems (e.g., algebraic number fields)
+- **Geometric Number Theory**: Using geometric methods for number-theoretic problems
+
+### 2. Probability & Statistics
+
+The study of random phenomena and data analysis, widely applied in finance, biology, and social sciences. Corresponding thinking weapons: **Probability & Statistics**, **Information Theory**, **Causal Inference**.
+
+- **Probability Theory**: Random variables, distributions, limit theorems → See **Probability & Statistics** (Kolmogorov axioms)
+- **Mathematical Statistics**: Parameter estimation, hypothesis testing, regression analysis → See **Probability & Statistics** (regression modeling, experimental design)
+- **Stochastic Processes**: Markov chains, Brownian motion, martingale theory
+- **Bayesian Statistics**: Priors, posteriors, MCMC → See **Information Theory** (maximum entropy principle)
+
+### 3. Topology
+
+The study of invariant properties of spaces under continuous deformation. Corresponding thinking weapon: **Topological Thinking**.
+
+- **Point-Set Topology**: Open sets, closed sets, connectedness, compactness → See **Symmetry & Invariance** (invariant perspective)
+- **Algebraic Topology**: Homotopy, homology, cohomology → See **Topological Thinking** (fundamental group, Betti numbers)
+- **Differential Topology**: Manifolds, tangent spaces, differential forms
+
+### 4. Discrete Mathematics
+
+Set theory, graph theory, mathematical logic, etc. — the mathematical foundation of computer science. Corresponding thinking weapons: **Algorithmic & Computational Thinking**, **Discrete & Combinatorial Thinking**.
+
+- **Set Theory**: Sets, relations, functions, cardinality, ordinals
+- **Graph Theory**: Graphs, paths, connectivity, coloring, network flows
+- **Mathematical Logic**: Propositional logic, predicate logic, computability → See **Axiomatic Thinking**, **Logical Deduction**
+- **Combinatorics**: Counting, permutations and combinations, generating functions → See **Discrete & Combinatorial Thinking**
+- **Algorithms & Complexity**: Sorting, searching, P/NP, decidability → See **Algorithmic & Computational Thinking**
+
+### 5. Applied Mathematics Branches
+
+Applying mathematical methods to real-world problems. Corresponding thinking weapons: **Optimization**, **Information Theory**, **Game Theory**, **Algorithmic & Computational Thinking**, **Causal Inference**.
+
+- **Operations Research**: Linear programming, integer programming, dynamic programming, queueing theory → See **Optimization** (LP/IP/DP taxonomy), **Algorithmic & Computational Thinking** (solution algorithms)
+- **Control Theory**: System control, optimal control, robust control → See **Optimization** (optimal control as variational optimization)
+- **Information Theory**: Entropy, channel capacity, data compression, coding theory → See **Information Theory** (Shannon entropy, coding theorems)
+- **Game Theory**: Strategic interaction, equilibrium analysis, mechanism design → See **Game Theory** (Nash equilibrium, minimax)
+- **Causal Inference**: Causal graph models, intervention analysis, counterfactual reasoning → See **Causal Inference** (DAGs, do-calculus)
+- **Financial Mathematics**: Option pricing, risk management, stochastic calculus → See **Modeling** (Black-Scholes), **Probability & Statistics**
+- **Computational Mathematics**: Numerical analysis, finite elements, Monte Carlo methods → See **Algorithmic & Computational Thinking** (numerical algorithms)
+- **Mathematical Foundations of Machine Learning**: Optimization, statistical learning theory, kernel methods → See **Optimization**, **Probability & Statistics**, **Information Theory** (MDL/AIC)
+
+## 3. Hierarchical Structure of the Knowledge System
+
+From a learning-path perspective, mathematical knowledge can be organized into levels:
+
+### Foundation Level
+
+Number sense, logic and classification, arithmetic, and basic geometry.
+
+- Concepts and operations of numbers
+- Basic logical reasoning
+- Arithmetic operations (addition, subtraction, multiplication, division)
+- Basic geometric shapes and properties
+
+### Algebra Level
+
+Variables, equations, functions, geometric proofs.
+
+- Algebraic expressions and equations
+- Function concepts and basic function families
+- Plane geometry proofs
+- Vectors and coordinates
+
+### Synthesis Level
+
+Functions and derivatives, calculus, sequences, solid geometry, advanced probability and statistics.
+
+- Limits and continuity
+- Differentiation and integration
+- Sequences and series
+- Solid geometry
+- Probability distributions and statistical inference
+
+### Frontier Level
+
+Mathematical analysis, advanced algebra, analytic/differential geometry, number theory, topology, etc.
+
+- Rigorous analytical theory ($\varepsilon$-$\delta$)
+- Abstract algebraic structures (groups, rings, fields)
+- Manifolds and differential geometry
+- Algebraic/analytic number theory
+- Point-set/algebraic topology
+- Functional analysis and operator theory
+
+## 4. Levels of Mathematical Thinking Methods
+
+| Level | Thinking Method | Description |
+|-------|----------------|-------------|
+| Foundation | Logical deduction, inductive analogy | The basis of all mathematical thinking |
+| Method | Axiomatization, abstraction, modeling | Methods for constructing mathematical theories |
+| Tool | Optimization, transformation, probability & statistics | Tools for solving concrete problems |
+| Extension | Algorithms & computation, information theory, game theory, causal inference | Tools applied to computation, information, interaction, and causation |
+| Philosophy | Symmetry & invariance, topological thinking, discrete & combinatorial thinking | Philosophical perspectives for understanding structure and essence |
+
+## 5. Connections Between Mathematics and Other Disciplines
+
+| Discipline | Mathematical Tools Used | Typical Applications |
+|-----------|------------------------|---------------------|
+| Physics | Calculus, linear algebra, group theory | Mechanics, quantum mechanics, relativity |
+| Computer Science | Discrete mathematics, graph theory, probability | Algorithm analysis, cryptography, AI |
+| Economics | Optimization, game theory, differential equations | Market equilibrium, pricing models |
+| Biology | Differential equations, statistics, graph theory | Population dynamics, systems biology |
+| Engineering | Differential equations, Fourier analysis, numerical methods | Control systems, signal processing |
+| Social Sciences | Statistics, game theory, network analysis | Social networks, decision analysis |
+
+## 6. Mapping Thinking Weapons to Mathematical Branches
+
+The 16 thinking weapons in this project (15 specialized weapons + 1 math-research-activator auto-trigger entry point) do not exist in isolation; they form a complementary toolkit with mathematical branches. Below is a simplified mapping to help you find suitable mathematical methods directly from problem types. v2 also includes `references/books/*.md` × 7 volumes covering algebraic geometry / differential geometry / Lie theory / abstract algebra / matrix analysis / optimization / manifolds and other modern mathematical structures, activated on demand into algorithm design (see README "Three-Layer Progressive Disclosure").
+
+| Thinking Weapon | Corresponding Mathematical Branch | Typical Methods / Concepts |
+|----------------|----------------------------------|---------------------------|
+| 🧭 Math Research Activator | Meta-cognition, problem classification, modern math mapping | Diagnosis → Mapping → Routing → GPU Filtering, dual acceptance gates |
+| 📐 Axiomatic Thinking | Mathematical logic, set theory | Axiomatic systems, formal languages, consistency, independence |
+| 🧩 Abstraction | Algebra, category theory, topology | Abstract structures, isomorphisms, universal properties |
+| 🧠 Logical Deduction | Mathematical logic, proof theory | Propositional logic, predicate logic, inference rules |
+| 🌉 Modeling | Applied mathematics, statistics | Equation-based modeling, dimensional analysis, validation |
+| ⚖️ Optimization | Optimization theory, operations research | Convex optimization, KKT conditions, dynamic programming |
+| 🎲 Probability & Statistics | Probability theory, mathematical statistics | Random variables, hypothesis testing, regression analysis |
+| 🔄 Transformation | Analysis, generating functions | Fourier, Laplace, algebraic transformations |
+| ⚛️ Symmetry & Invariance | Group theory, geometry | Group actions, invariants, quotient spaces |
+| 📈 Induction & Analogy | Elementary mathematics, number theory | Inductive proofs, analogical reasoning, pattern recognition |
+| 🖥️ Algorithmic & Computational Thinking | Computation theory, discrete mathematics | Complexity, computability, algorithm paradigms |
+| 📡 Information Theory | Information theory, statistical learning | Entropy, mutual information, coding limits |
+| 🎯 Game Theory | Mathematical economics, mechanism design | Nash equilibrium, incentive compatibility, optimal strategy |
+| 🔗 Causal Inference | Causal inference, statistics | DAGs, do-calculus, intervention analysis |
+| 🌀 Topological Thinking | Topology, algebraic topology | Homotopy, homology, topological invariants |
+| 🧮 Discrete & Combinatorial Thinking | Combinatorics, graph theory | Pigeonhole principle, generating functions, enumeration |
+
+## 7. How to Choose a Thinking Weapon
+
+When facing a problem, the most important first step is not "analyze hard," but "choose the right tool." Here is a selection guide:
+
+### Quick Selection Guide
+
+| Core Problem Characteristic | Most Likely Suitable Thinking Weapon |
+|----------------------------|-------------------------------------|
+| Multi-party interaction; my optimum depends on others | 🎯 Game Theory |
+| Uncertainty / randomness | 🎲 Probability & Statistics |
+| Optimal choice under constraints | ⚖️ Optimization |
+| Difficult to handle from current perspective | 🔄 Transformation |
+| Need to extract essential structure | 🧩 Abstraction |
+| Need rigorous reasoning and verification | 🧠 Logical Deduction |
+| Need to discover patterns from experience | 📈 Induction & Analogy |
+| Need to build a predictive model | 🌉 Modeling |
+| Invariance amid change | ⚛️ Symmetry & Invariance |
+| Need executable steps | 🖥️ Algorithmic & Computational Thinking |
+| Counting / structure over finite objects | 🧮 Discrete & Combinatorial Thinking |
+
+### Using the Activator
+
+If you are unsure which tool to use, simply invoke the math-research-activator via the `/ask` command. It will diagnose the problem, map to modern mathematical structures, recommend the 1–3 most suitable thinking weapons, and perform GPU feasibility filtering. When algorithm / kernel / model code appears in the workspace, the activator will also intervene automatically.
+
+### Path
+
+v2 has removed the "research / life dual-path" and unified into a single research / algorithm path: preserving complete mathematical notation and derivations, and enforcing the GPU 8-dimension gate when used for algorithm / operator design.
+
+## 8. How to Use This Overview
+
+- Start from the problem characteristics: determine whether it is "structural," "dynamic," "stochastic," "interactive," or "countable."
+- Consult the Quick Selection Guide or use the `/ask` command to find the closest thinking weapon.
+- Combined with the "Hierarchical Structure of the Knowledge System," judge whether the current problem is better suited to foundational approaches or frontier methods.
+- If the problem spans multiple categories, invoke multiple thinking weapons simultaneously — e.g., "Modeling + Optimization," "Probability + Causation," "Abstraction + Algorithms."
+- For algorithm / operator design problems, let the activator transfer modern mathematical structures (algebraic geometry / Lie theory / topology, etc.) into the design and pass them through the GPU 8-dimension gate.
+- When studying or reading literature, use this overview as an organizing framework to place scattered concepts into a unified knowledge map.

package/knowledge-base/overview.md

@@ -1,3 +1,5 @@
+> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `overview.en.md`。
+
 # 数学知识体系概述 / Mathematical Knowledge System Overview
 
 ## 概述

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "math-skill",
-  "version": "2.0.1",
+  "version": "2.1.0",
   "description": "数学思想武器 v2：自动触发的现代数学能力激活器，把代数几何/微分几何/李理论等现代数学激活到算法与 GPU 协同设计研究中——既在 math 上 beautiful，又 GPU friendly。Mathematical Thinking Weapons v2: an auto-triggered activator that brings modern mathematics (algebraic geometry, differential geometry, Lie theory, …) into algorithm & GPU co-design research — beautiful in math, friendly to GPUs.",
   "keywords": [
     "math",
@@ -41,7 +41,8 @@
     "agentic-workflow",
     "auto-trigger",
     "co-design",
-    "research"
+    "research",
+    "bilingual"
   ],
   "license": "MIT",
   "author": "the-thinker0",
@@ -55,6 +56,7 @@
   },
   "files": [
     "README.md",
+    "README.en-US.md",
     "LICENSE",
     "commands/",
     "skills/",

package/references/agentic-workflow.en.md

@@ -0,0 +1,53 @@
+# Agentic Research Workflow / Human-in-the-Agent-Loop
+
+> Distilled from frontline auto-research practice (Infra / Algorithms / Chip Co-design). It defines the **collaborative mindset** this skill expects: what humans do, what the agent does, and what loop grounds "activating mathematical capability" in practice.
+> The activator references this file at runtime. This file defines the collaboration style the skill expects.
+
+## Creed
+
+1. **The mathematical foundation of this AI revolution is the first time 20th-century mathematics has stepped onto the commercial computing stage** — category theory, algebraic topology, algebraic geometry. The mathematical foundations of most mainstream algorithms still largely rest on the calculus and linear algebra of 1800–1900. Activating modern mathematics in algorithm design is the most important task during the algorithm exploration phase.
+2. **Humility**: The breadth of knowledge from the pre-training stage already surpasses any individual. **More knowledge is learned from the model than taught to it.** Letting go of the bias toward "teaching the model" usually yields better results.
+3. **Mathematical beauty ≠ computability**: Many mathematically elegant constructs break down in the face of GPU parallelism and low-precision arithmetic errors. Every deliverable must pass the acceptance gate defined in `gpu-friendly-math.md`.
+
+## Division of Labor
+
+**Humans are responsible for (what humans excel at and find most valuable):**
+- **Cross-domain activation**: Transferring the structure of one domain to another. The model already contains sufficient internal knowledge, but "without someone to activate it, that knowledge is unlikely to be developed." Example: applying algebraic geometry perspectives to study model architectures; historically, the correspondence between fiber bundles and gauge fields — the structure was already there, awaiting only a single cross-domain activation.
+- **Avoid hard-coding subjective bias**: The more rules you add, the more you constrain the model's ability to explore alternatives. To get good results, **do not impose human subjective preferences by force.**
+- **Expanding cognitive context with the model**: The human brain can manually compare at most 2–3 variables simultaneously, while the model's long context window can weigh many at once. Leveraging the model to expand an individual's cognitive context is a core principle of agentic development.
+- **Choosing directions and setting acceptance gates**: Deciding which path to explore and what standards to apply for acceptance.
+
+**The Agent is responsible for (what the model excels at):**
+- **Large-context search and enumeration**: Enumerating large numbers of candidate structures, comparing multi-parameter combinations in parallel.
+- **Verification**: Checking mathematical correctness + GPU feasibility.
+- **Building and executing test plans**: Recording research tasks as trackable markdown tables, autonomously adding new cases, fixing compilation errors, and retrying on failure.
+
+## The Activation Loop
+
+> The activator's `Diagnosis → Mapping → GPU Filtering` main pipeline is a distillation of this loop.
+
+1. **Diagnosis**: What is the algorithmic structure / bottleneck of the problem? (Do not start by piling on math tutorials.)
+2. **Cross-domain activation**: Scan `books/*.md` for transferable modern mathematical structures, **enumerate multiple candidates** (leveraging the model's large-context advantage).
+3. **Dual acceptance gate**: Each candidate passes two gates — (1) Mathematically correct (differentiable, self-consistent, with correctness guarantees); (2) GPU-feasible (the eight dimensions of `gpu-friendly-math.md`).
+4. **Iterative tracking**: Record candidates, scores, and status in a markdown test plan, converging step by step.
+
+## Markdown Test Plan Template / Tracking Template
+
+Record research tasks in a table that the Agent can continuously update:
+
+```markdown
+| Candidate Structure | Math Correctness | GPU 8-Dim | Complexity | Status | Notes / Next Steps |
+|--------------------|-----------------|-----------|------------|--------|-------------------|
+| Tropical gating replacing TopK | ✅ Differentiable relaxation | 1✅2❌3✅… | Sub-quadratic (per-token) | Verifying | Compare with SWA baseline |
+| …                  |                 |           |            | Todo   |                   |
+```
+
+The Agent is responsible for tracking execution and updating this table; the human is responsible for reading the table and adjusting direction.
+
+## Operating Principles
+
+- **Diagnose first, then map, then filter** — do not produce lengthy math tutorials; go straight to structural mapping and GPU feasibility.
+- **Preserve exploratory freedom**: Add fewer hard rules; leave room for the model to explore.
+- **Humans should be "lazy"**: Delegate all tedious work to the Agent; humans focus only on cross-domain activation and directional judgment.
+- **Progressive disclosure**: The methodology layer, GPU checklist, and book layer are all loaded on demand; only the minimal trigger and diagnostic logic stays resident, to save tokens.
+- **Do not create a pile of skills / rules right away**: The model already has many capabilities; use them fully first, then add structure.

package/references/agentic-workflow.md

@@ -1,3 +1,5 @@
+> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `agentic-workflow.en.md`。
+
 # Agentic 研究工作方式 / Human-in-the-Agent-Loop
 
 > 提炼自一线 auto-research 实践（Infra / 算法 / 芯片 Co-design）。它定义本 skill 期望的**协作思维方式**：人做什么、Agent 做什么、用什么循环把"激发数学能力"落地。

package/references/books/abstract-algebra.md

@@ -110,6 +110,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Joseph A. Gallian, *Contemporary Abstract Algebra*, 8th Edition, Brooks/Cole, Cengage Learning, 2013. ISBN 978-1-133-59971-5.
+>
+> **启用方式**：将 `Contemporary Abstract Algebra.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 > **全保真回查 = Agent 自动搜索本地 PDF**：`math_book/Contemporary Abstract Algebra.pdf`。需要精确定义/定理/例子时，让 Agent 按下列真实章号定向略读，不要凭记忆；若安装环境没有 `math_book/`，停在本蒸馏稿层。
 
 - **Ch 5 Permutation Groups**——轨道 orbit / 稳定子 stabilizer：等变权重共享的根。

package/references/books/algebraic-geometry-rising-sea.md

@@ -154,6 +154,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Ravi Vakil, *The Rising Sea: Foundations of Algebraic Geometry*, Princeton University Press, 2025. ISBN 978-0-691-26866-8.
+>
+> **启用方式**：将 `The Rising Sea Foundations of Algebraic Geometry.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 **全保真回查（full-fidelity lookup）**：当摘要不足以支撑设计时，让 Agent 自动检索本地 PDF
 `math_book/The Rising Sea Foundations of Algebraic Geometry.pdf`
 （用 `pdftotext -f <start> -l <end>` 取定向页，**不要 dump 整本**）。

package/references/books/differential-geometry.md

@@ -127,6 +127,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Jeffrey M. Lee, *Manifolds and Differential Geometry*, Graduate Studies in Mathematics Vol. 107, American Mathematical Society, 2009. ISBN 978-0-8218-4815-9.
+>
+> **启用方式**：将 `Manifolds and Differential Geometry.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 > 全保真回查 = 让 Agent **自动搜索本地 PDF** `math_book/Manifolds and Differential Geometry.pdf`（按章号 / 节号定位，勿凭记忆复述）。本摘要只给坐标，不替代原文。
 
 - **§6.8 Principal and Associated Bundles** + **§12.12 G-Connections**：规范等变的几何基础（主丛 + 联络 = 规范场）。

package/references/books/matrix-analysis.md

@@ -130,6 +130,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Roger A. Horn & Charles R. Johnson, *Matrix Analysis*, 2nd Edition, Cambridge University Press, 2013. ISBN 978-0-521-83940-2.
+>
+> **启用方式**：将 `Matrix Analysis.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 **全保真回查 = 让 Agent 自动搜索本地 PDF `math_book/Matrix Analysis.pdf`**：用 `pdftotext` 抽取 → `grep` 定位关键词/定理名 → `Read` 命中页精读。本文件是"激活索引"，不是替代品；需要精确陈述、证明或常数时，回原书核对。
 
 值得深读的真实章节：

package/references/books/micro-lie-theory.md

@@ -103,6 +103,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Joan Solà, Jérémie Deray, Dinesh Atchuthan, *A micro Lie theory for state estimation in robotics*, arXiv:1812.01537v9, 2021. 配套开源 C++ 库 [manif](https://github.com/artivis/manif)。
+>
+> **启用方式**：将 `A micro Lie theory.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 > 全保真回查 = 让 Agent 自动检索本地 PDF：`math_book/A micro Lie theory.pdf`（用 `pdftotext` 或 Read PDF pages）。下列为该 PDF 内的真实章节/公式块定位：
 
 1. **§II-D 指数映射 + Fig. 1**：exp/log 与大写 Exp/Log 算子（式 23–24）——流形↔切空间桥梁与闭式来源；配 Ex. 3（SO(3) 的李代数 `[ω]×`）、Ex. 4（SO(3) 的 exp = Rodrigues）。

package/references/books/optimization-ml.md

@@ -150,6 +150,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：Edwin K. P. Chong, Wu-Sheng Lu, Stanisław H. Żak, *An Introduction to Optimization, With Applications to Machine Learning*, 5th Edition, John Wiley & Sons, 2024. ISBN 978-1-119-87763-9.
+>
+> **启用方式**：将 `An Introduction to Optimization With Applications to Machine Learning.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 全保真回查 = 让 Agent 直接搜索本地 PDF
 `math_book/An Introduction to Optimization With Applications to Machine Learning.pdf`，按真实章号定位：
 

package/references/books/smooth-manifolds.md

@@ -90,6 +90,10 @@
 
 ## 深挖入口
 
+> **📖 书目信息**：John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition, Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8.
+>
+> **启用方式**：将 `Introduction to Smooth Manifolds.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
+
 > **全保真回查**：需要原文定义/定理/证明时，让 Agent **自动搜索本地 PDF** `math_book/Introduction to Smooth Manifolds.pdf`（按章号/关键词定位，勿凭记忆复述）。下列为真实章号（2nd ed.）：
 
 - **Ch 3 Tangent Vectors** — 切空间、微分/pushforward、切丛：局部线性化与反传的几何原型。

package/references/gpu-friendly-math.en.md

@@ -0,0 +1,65 @@
+# GPU-Friendly Math Checklist
+
+> This file is the **single source of truth** for the "GPU-feasibility" acceptance gate.
+> The activator, the 16 thinking weapons, `books/*.md`, and `../agents/math-critic.md` all reference this file; no duplicate definitions elsewhere.
+>
+> This file is the single source of truth for the "GPU-feasibility" acceptance gate. The activator, the 16 weapons, the book references, and the math-critic all point here.
+
+## Core Proposition
+
+**Mathematical beauty ≠ computability.** For a structure to truly enter training and inference on modern GPU clusters, it must simultaneously satisfy two requirements:
+
+1. **Mathematically correct (beautiful in math)** — The structure is self-consistent, differentiable (or relaxable to differentiable), with correctness guarantees.
+2. **Hardware-feasible (friendly to GPU)** — It can be efficiently mapped onto GPU microarchitecture (Tensor Cores, memory hierarchy, parallelism, and interconnects).
+
+Many "beautiful on paper" modern mathematical structures cannot run at high performance once they encounter GPU parallelism and low-precision arithmetic errors. This checklist turns "GPU feasibility" into an **item-by-item scorable** engineering standard, preventing non-computable constructs from being accepted as deliverables.
+
+## The 8-Dimension Scorecard
+
+For any candidate structure (operator, attention variant, routing mechanism, regularization term, compression scheme…) rate each dimension as `Friendly / Adaptable / Unfriendly` and provide adaptation recommendations.
+
+| # | Dimension | Key Question | Friendly ✅ | Unfriendly ❌ |
+|---|-----------|-------------|------------|--------------|
+| 1 | **Tensorization** | Can it be expressed as dense tensor operations, avoiding element-wise irregular control flow? | Batched tensor algebra | Scalar loops, data-dependent branches |
+| 2 | **GEMM Mappability** | Can it be reduced to matrix multiplication / batched GEMM / convolution to fully utilize Tensor Cores? | Expressible as a GEMM chain | Irregular computations that cannot be expressed as matrix operations |
+| 3 | **Complexity** | Is the forward/backward pass sub-quadratic? How does it scale with sequence length / model size? | Linear / sub-quadratic, blockable | $O(n^2)$ or worse memory/compute blowup |
+| 4 | **Memory & KV-Cache** | Peak memory usage; activation / state / KV footprint; can it be compressed? | Low-rank / quantized / block-summary compressible | Must materialize large intermediate tensors |
+| 5 | **Low-Precision Stability** | Is it stable under fp16/bf16/fp8 with deterministic reproducibility? | Controlled dynamic range, numerically robust | Catastrophic cancellation, ill-conditioned, requires fp64 |
+| 6 | **Parallelism & Communication** | Can it be parallelized across SMs / devices? Communication-to-compute ratio; can overlap be achieved? | Highly parallel, communication overlap-able | Long serial recurrences, communication bottleneck |
+| 7 | **Sparsity** | Structured or unstructured sparsity? | Block / banded structured sparsity | Random gather/scatter |
+| 8 | **Kernel Fusion** | Can kernels be fused to avoid materializing large intermediates (FlashAttention-style)? | Fusible, recomputable | Frequent small kernels, divergent control flow |
+
+**Scoring conclusion**: Retain only candidates that are **mathematically beautiful AND (all eight dimensions friendly or adaptable)**; any dimension rated "unfriendly and non-adaptable" means the candidate must be adapted or eliminated.
+
+## Common "Beautiful but Non-Computable" Anti-Patterns
+
+- **Dense global $O(n^2)$ operators**: Naive softmax attention explodes with context length.
+- **Unstructured sparsity / irregular graph traversal**: Random memory access destroys locality.
+- **High-precision dependency**: Ill-conditioned problems that require fp64 for correctness (most training runs only bf16/fp16/fp8).
+- **Serial recurrence**: Long-range dependencies that cannot be parallelized (naive RNN-style).
+- **Frequent small kernels + control-flow divergence**: Launch overhead and warp divergence consume throughput.
+- **Non-differentiable / requiring discrete search**: Breaks end-to-end gradient-based training.
+
+## Make-It-Computable Toolkit
+
+Common techniques for transforming "beautiful but non-computable" into "both beautiful and computable":
+
+- **Discrete → continuous relaxation**: Gumbel-softmax; **piecewise-linear** gating on the **tropical semiring** as a replacement for hard Top-K.
+- **Block sparsification**: Dense attention within blocks, structured sparse between blocks (e.g., DeepSeek CSA-style blocking).
+- **Low-rank / projection compression**: Restriction maps via low-rank linear transformations; **low-rank basis-style block summaries** for KV-Cache compression (store the basis rather than Plücker coordinates — the latter expands when low-rank).
+- **Numerical reparameterization**: log-sum-exp, normalization, stable softmax — ensuring low-precision stability.
+- **Kernel fusion / recomputation**: Fused kernels, activation recompute to save memory.
+- **Embedding structure into GEMM**: Express algebraic/geometric transformations as **learnable linear maps** so they naturally map onto Tensor Cores.
+
+## Worked Example: Tropical Sheaf Attention
+
+Drawn from the auto-research directions cited in `agentic-workflow.md`, demonstrating how a **candidate design enters the 8-dimension verification**:
+
+| Component | Mathematical Source | GPU Friendliness |
+|-----------|-------------------|-----------------|
+| Tropical Gating | Tropical semiring, piecewise-linear | Replaces Top-K: element-wise max-plus — dim 1 ✅ Tensorization / dim 2 ❌ Not a Tensor Core GEMM (runs on CUDA cores) / dim 3 ✅ Per-token gating only, sub-quadratic (min-plus matmul is APSP-hard, not sub-quadratic); sub-differentiable, kinks require LogSumExp smoothing (smoothing recovers standard softmax) |
+| Cellular Sheaf Diffusion | Algebraic geometry / topology (sheaves, restriction maps) | Each edge is a low-rank linear transform = small GEMM (dim 2/4) |
+| Čech Cohomology Regularization | Algebraic topology (first cohomology $H^1$) | Local, inexpensive; serves as an algebraic criterion for hallucination (dim 3/8) |
+| Low-Rank Basis KV Compression (Plücker/Grassmannian perspective) | Projective geometry | Store the basis rather than Plücker coordinates (the latter expands when low-rank); block-summary candidate — compression ratio / error / throughput must be benchmarked (dim 4) |
+
+Do not treat the table above as validated conclusions. The correct approach is to enter each component into the test plan: prove or estimate complexity, measure peak memory and throughput, check bf16/fp8 stability, and confirm whether it can be mapped to GEMM / batched GEMM / fused kernels. Only after both empirical benchmarks and theoretical derivations pass should a component be labeled "math beautiful × GPU friendly."

package/references/gpu-friendly-math.md

@@ -1,3 +1,5 @@
+> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `gpu-friendly-math.en.md`。
+
 # GPU 友好性总清单 / GPU-Friendly Math Checklist
 
 > 本文件是「GPU 可行性」验收门的**唯一权威来源（single source of truth）**。

package/references/inspiration.en.md

@@ -0,0 +1,113 @@
+# Inspirational Musings
+
+> Mathematics is more than a computational tool — it is a way of thinking. Sometimes a mathematical concept resonates with life itself, and you suddenly realize that behind those cold formulas lies a warm perspective on understanding the world.
+
+---
+
+## 1. The Dragon-Slaying Blade: The Origin of Lie Groups and Lie Algebras
+
+I still remember reading a Zhihu answer while pondering the question "How to understand that the original motivation of Lie groups and Lie algebras was to solve differential equations?" — one response left an indelible impression on me [Source: https://www.zhihu.com/question/356243536/answer/1992290356713259459].
+
+Sophus Lie was a blacksmith who wanted to forge a **dragon-slaying blade** — a universal method for solving all differential equations.
+
+Although the final blade could not slay every dragon, the craft of its forging — the correspondence between Lie groups and Lie algebras — has been passed down through generations. Later researchers discovered that while this blade cannot cut through every differential equation, it serves as a divine instrument for **chopping vegetables** (linearizing nonlinear problems), for **sculpting** (describing physical symmetries), and for **building houses** (robot state estimation).
+
+So, when you stare at a screen full of `se(3)` and exponential map notation and feel dizzy, do not forget that all of this began with a single Norwegian mathematician wondering: what miracles would unfold if you took Galois's game of permuting roots and extended it to the infinitesimal?
+
+**This is what makes mathematics most enchanting.**
+
+A tool invented to solve a specific problem ultimately reveals value far beyond its original intent in entirely different domains. Axiomatic thinking was initially developed to make geometry rigorous, yet it became the foundational language of every mathematical discipline. The Fourier transform was originally devised to solve the heat equation, yet it became central to signal processing and quantum mechanics. Euler's generating functions were initially created to count integer partitions, yet they became universal tools in combinatorics and probability theory.
+
+Mathematical thinking works the same way — you may learn it to review a paper or solve a specific problem, but its true value lies in how it transforms the way you see the world.
+
+---
+
+## 2. Life as an Optimization Problem
+
+If you treat a human being as a high-dimensional, nonlinear, dynamic optimization problem with a time-varying objective function, you will find that optimization theory and life paths share a striking philosophical resonance.
+
+### The Objective Function: What Do You Want to "Optimize"?
+
+In mathematics, the first step is to define the objective function $f(x)$. In life, this is the value you pursue: happiness, achievement, meaning, wealth, balance…
+
+The difficulty is that life goals are often **multi-objective, vague, and time-varying** — and may even conflict with one another.
+
+### Initial Point and Resource Constraints
+
+$x_0$ is your origin, talent, and starting point.
+
+Constraint conditions: time, money, health, social rules… These are like the constraints $g(x) \leq 0$ in an optimization problem, delineating the feasible region.
+
+### Step Size and Direction: Everyday Decisions
+
+**Direction**: The direction you choose to invest effort — career, relationships, fields of study.
+
+**Step size**: The intensity and time you devote to a given direction.
+
+Precision requirement: if every step only pursues immediate returns (e.g., short-term profit maximization), you may fall into a "local optimum" trap — for example, a high-paying but meaningless job, or a busy but stagnant life.
+
+### Local Optimum vs. Global Optimum
+
+This is the core dilemma of "life optimization":
+
+- **Local optimum**: The seemingly best choice within your city, industry, and social circle.
+- **Global optimum**: Perhaps in another country, another field, or another lifestyle, there exists a life that better aligns with your true nature. But you cannot foresee the global landscape, just as an optimization algorithm can only access local information at its current position.
+
+### Randomness and Noise
+
+Life is not a smooth numerical function — it is full of random noise:
+
+Luck, opportunities, unexpected events… These are equivalent to stochastic perturbations $f(x) + \epsilon$ on the objective function.
+
+Therefore, pursuing excessive precision is often uneconomical; what you need is **robustness and adaptability**.
+
+### The Exploration–Exploitation Trade-off
+
+This is the fundamental tension of life:
+
+- **Exploration**: Trying new fields, new relationships, new knowledge — risky, but potentially discovering an entirely new "basin of attraction."
+- **Exploitation**: Deepening your current domain to harvest stable returns.
+
+Explore more when young, exploit more in middle age? But the rule is not fixed.
+
+### Dynamic Objectives and Lifelong Learning
+
+Life goals change: passion at 20, meaning at 40, legacy at 60…
+
+This means the objective function $f(x)$ itself is constantly evolving. Therefore, "optimizing yourself" is more important than "optimizing a fixed target" — this is **meta-optimization** (learning how to learn, adapting how to adapt).
+
+### Algorithm Choice: Your Life Strategy
+
+| Algorithm | Life Strategy |
+|-----------|--------------|
+| Gradient Descent | Follow the most pressing direction at each step (salary, social pressure) |
+| Momentum | Maintain historical inertia (persist in long-term goals, resist short-term fluctuations) |
+| Stochastic Gradient Descent | Accept mini-batch random samples, adjust flexibly |
+| Evolutionary Algorithms | Try multiple life paths, discard ineffective strategies, retain effective patterns |
+
+No single algorithm is universally best; what matters is knowing which strategy you are using and adjusting it at the right time.
+
+### The Most Important Insight
+
+In mathematical optimization, we assume a global optimum $x^*$ exists. But in life, there may be no "absolutely optimal life" at all.
+
+We are merely "participants" in our own lives, searching for a satisfactory solution and striving to make the process full of learning, growth, and meaning.
+
+What matters is not finding the legendary "global optimum," but rather, at each iteration:
+
+- Keeping the general direction roughly correct
+- Balancing exploration and exploitation
+- Accepting noise and constraints
+- Allowing the objective function to evolve gracefully as experience grows
+
+**The process itself is the meaning; optimization is life.**
+
+---
+
+## How These Stories Connect to This Project
+
+The inspiration for this project stems precisely from these two insights:
+
+1. **The value of mathematical tools far exceeds their original intent** — Sophus Lie's dragon-slaying blade story teaches us that a tool invented for solving differential equations ultimately became the universal language for describing symmetry. This is the core idea behind "thinking weapons": every mathematical concept carries transferable value far beyond its original application domain.
+
+2. **Mathematics is a lens for understanding life** — Optimization theory is not just about algorithms; it is a framework for understanding the structure of life decisions. When you transfer the "exploration–exploitation trade-off" from reinforcement learning to career choices, or the "local optimum trap" from convex optimization to everyday decisions, mathematics steps off the blackboard and into daily life.

package/references/inspiration.md

@@ -1,3 +1,5 @@
+> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `inspiration.en.md`。
+
 # 灵感杂谈 / Inspirational Musings
 
 > 数学不只是一种计算工具，更是一种思想方法。有时，某个数学概念与人生之间的共鸣，会让你突然意识到——那些冰冷的公式背后，藏着理解世界的温暖视角。