math-skill 3.0.0 → 3.0.1

package/references/books/optimization-ml.en.md

@@ -0,0 +1,163 @@
+# Optimization (Including ML Applications)
+
+> **An Introduction to Optimization, With Applications to Machine Learning** (5th Edition, 2024)
+> Edwin K. P. Chong, Wu-Sheng Lu, Stanislaw H. Zak -- John Wiley & Sons (Hardback ISBN 9781119877639)
+>
+> This file is an "activation reference": synthesized distillation, engineering-oriented, not a verbatim excerpt.
+> Goal -- extract the structures from this classic optimization textbook that **can be applied to algorithms / GPU / training Infra**.
+
+## Overview
+
+The fifth edition of a classic continuous optimization textbook. Compared to earlier editions, the largest addition is a completely new **Part V "Optimization in Machine Learning"**, which fully integrates first-order/second-order optimality, duality, KKT, and convergence theory with training practices such as SGD/SVM/PCA. The book has 31 chapters organized into five parts.
+
+Actual chapter map:
+
+- **Part I -- Mathematical Review (Ch 1-5)**
+  - Ch 1 Proof methods and notation; Ch 2 Vector spaces and matrices (rank, inner products and norms).
+  - Ch 3 Transformations: eigenvalues/eigenvectors, orthogonal projections, quadratic forms S3.4, matrix norms S3.5.
+  - Ch 4 Geometry: hyperplanes, **convex sets S4.3**, polytopes and polyhedra.
+  - Ch 5 Calculus: derivative matrices S5.3, **level sets and gradients S5.5**, Taylor series S5.6.
+- **Part II -- Unconstrained Optimization (Ch 6-14)**
+  - Ch 6 First-order/second-order necessary and sufficient conditions for local minima.
+  - Ch 7 One-dimensional search: golden section, Fibonacci, bisection, Newton, secant, line search.
+  - **Ch 8 Gradient methods** (steepest descent S8.2, convergence analysis S8.3).
+  - **Ch 9 Newton's method** (Levenberg-Marquardt S9.3, nonlinear least squares).
+  - Ch 10 Conjugate direction/conjugate gradient methods; **Ch 11 Quasi-Newton methods** (inverse Hessian approximation, DFP S11.4, **BFGS S11.5**).
+  - Ch 12 Solving linear equations (least squares, RLS, Kaczmarz, minimum-norm solutions).
+  - **Ch 13 Neural networks and backpropagation** (single-neuron training S13.2, Backprop S13.3).
+  - Ch 14 Global search: Nelder-Mead, simulated annealing, PSO, genetic algorithms.
+- **Part III -- Linear Programming (Ch 15-19)**
+  - Ch 15 LP fundamentals and geometry; Ch 16 Simplex method.
+  - **Ch 17 LP duality** (dual LP, matrix games).
+  - Ch 18 Non-simplex/interior-point methods (Khachiyan, affine scaling, Karmarkar); Ch 19 Integer programming.
+- **Part IV -- Nonlinear Constrained Optimization (Ch 20-25)**
+  - Ch 20 Equality constraints: tangent/normal spaces S20.3, **Lagrange conditions S20.4**, second-order conditions.
+  - **Ch 21 Inequality constraints and KKT** (KKT S21.1, second-order conditions S21.2).
+  - **Ch 22 Convex optimization** (convex functions S22.2, convex problems S22.3, SDP/LMI S22.4).
+  - **Ch 23 Lagrangian duality** (weak/strong duality, duality gap S23.4.6, Slater S23.6.3, saddle points).
+  - Ch 24 Constrained optimization algorithms (projection S24.2, **projected gradient S24.3**, Armijo S24.4.4, augmented Lagrangian S24.5, penalty methods S24.6).
+  - Ch 25 Multi-objective / robust LP (Pareto, uncertainty).
+- **Part V -- Optimization in ML (Ch 26-31)**
+  - Ch 26 Feature engineering, PCA, SVD, linear autoencoders.
+  - **Ch 27 SGD algorithms** (SGD S27.1, variance reduction **SVRG S27.2**, **distributed SVRG and communication/computation tradeoffs S27.3**).
+  - Ch 28 Linear regression (regularization S28.3, cross-validation); Ch 29 Logistic regression / Softmax.
+  - **Ch 30 SVM** (hinge loss, hard/soft margin); **Ch 31 Kernel methods and K-Means**.
+
+## Core Structures Transferable to AI/Infra
+
+- **First-order optimality + gradient geometry (Ch 6, S5.5)**
+  - Gradient is perpendicular to level sets and is the steepest ascent direction -- the axiomatic root of all training optimizers.
+  - `nabla f = 0` is the stopping criterion; saddle points / non-convexity are the central pain points of modern deep learning.
+- **Convergence analysis framework (Ch 8 S8.3)**
+  - Uses the condition number kappa = lambda_max/lambda_min to characterize the convergence rate of steepest descent.
+  - Explains "why ill-conditioned networks are hard to train, why normalization / preconditioning is needed."
+- **Second-order curvature and damping (Ch 9)**
+  - Newton's method uses the Hessian to provide affine-invariant step sizes and directions.
+  - Levenberg-Marquardt's `(H+mu I)` damping = trust-region idea, the ancestor of Adam's `epsilon` and second-order optimizers.
+- **Quasi-Newton low-rank updates (Ch 11)**
+  - BFGS/DFP uses only gradient differences, maintaining an inverse Hessian approximation via rank-1/rank-2 updates.
+  - Direct intellectual ancestor of L-BFGS, K-FAC, and Shampoo.
+- **Matrix-free second-order methods (Ch 10)**
+  - Conjugate gradient requires only Hessian-vector products without storing the full Hessian; corresponds to autodiff HVP (Hessian-free).
+- **Constraint geometry (Ch 20-21, 24)**
+  - Tangent/normal spaces -> Lagrange/KKT -> projected gradient + penalty / augmented Lagrangian.
+  - Forms a complete toolkit for "training with constraints."
+- **Duality and saddle points (Ch 17, 23)**
+  - Strong duality <=> minimax = maximin; KKT, complementary slackness, Slater conditions.
+  - Min-max training (GAN / adversarial robustness) and SVM duality both fall here.
+- **Stochastic and distributed methods (Ch 27)**
+  - SGD's unbiased gradient estimation, SVRG variance reduction.
+  - **Explicit "communication vs. computation" tradeoff in distributed settings** -- the theoretical root of data-parallel training.
+- **Low-rank / spectral methods (Ch 26, S3.4)**
+  - SVD/PCA/linear autoencoders, quadratic forms and spectra -- the mathematical foundation of LoRA, KV compression, and spectral normalization.
+
+## Problem Types Suited for Activation
+
+- Selecting / designing optimizers, or explaining training dynamics (why divergence, oscillation, or stagnation at saddle points occurs).
+- Diagnosing ill-conditioning and slow convergence: quantifying "hard to train" via the condition number kappa.
+- Training with constraints: weight-norm balls, spectral norms, safety / budget constraints, requiring projection or penalty methods.
+- Min-max / adversarial / dual perspectives: replacing a hard primal with an easier dual (e.g., kernel Gram matrix).
+- Communication-computation tradeoffs, gradient compression, and variance reduction in distributed training.
+- Scenarios requiring second-order information but unable to compute the full Hessian (curvature-adaptive preconditioning).
+
+## Possible Algorithmic Inspirations
+
+- **Adaptive optimizers**
+  - Levenberg-Marquardt's `(H+mu I)` damping -> Adam's `epsilon`, trust regions, adaptive learning rates.
+  - Making "curvature / damping" explicit rather than staying with purely heuristic hyperparameter tuning.
+- **Feasible second-order for large models**
+  - L-BFGS: Store only the most recent m gradient pairs (low-rank history, memory O(md)).
+  - Hessian-free: Autodiff HVP + CG (matrix-free, no need to materialize the Hessian).
+  - K-FAC / Shampoo: Approximate the Hessian as **block-diagonal / Kronecker factors**, reducing each block to a small GEMM.
+- **Efficient solving via the dual perspective**
+  - SVM converts a high-dimensional primal into a dual that depends only on the kernel Gram matrix (Ch 30-31), a big win when sample count << dimensionality.
+  - Dual decomposition of constrained problems is naturally parallelizable.
+- **Constrained training**
+  - Projected gradient (S24.3) for norm-ball / spectral-norm constraints (weight clipping, spectral normalization).
+  - Augmented Lagrangian / penalty methods (S24.5-S24.6) soften hard constraints into differentiable regularization.
+- **Variance reduction / large batch**
+  - SVRG's (S27.2) control variate idea -> gradient accumulation, stability analysis of large-batch training.
+- **Distributed training**
+  - S27.3 "Communication vs. Computation" directly corresponds to all-reduce and computation overlap, gradient compression, federated / data security.
+
+## GPU Friendliness Warning
+
+> The following item-by-item evaluation uses the **eight-dimension scorecard** from `../gpu-friendly-math.md` (read that first).
+> Conclusion: The book's first-order / stochastic / low-rank content is naturally GPU-friendly; second-order methods and search-based methods require heavy adaptation or elimination.
+
+- **Full Hessian in second-order methods (Ch 9, 11)**
+  - Violates **Dimension 4 (Memory)**: Dense Hessian is O(d^2), impossible to materialize for hundreds of millions of parameters.
+  - Violates **Dimension 2 (GEMM-mappability)**: Inversion / factorization is not batched-GEMM friendly.
+  - Violates **Dimension 5 (Low-precision stability)**: Ill-conditioned inversion causes catastrophic cancellation under bf16/fp16.
+  - Adaptation: Matrix-free HVP + CG, L-BFGS low-rank, K-FAC block-diagonal -> restores **Dimension 2/4** friendliness.
+- **Line search (Ch 7 golden section / Armijo S24.4.4)**
+  - Violates **Dimension 1 (Tensorization)**: Essentially a scalar loop + data-dependent branching (step-by-step comparison of function values).
+  - Violates **Dimension 8 (Operator fusion)**: Frequent small kernels, control-flow divergence.
+  - Adaptation: Large models almost universally use scheduled step sizes (warmup + cosine) instead of step-by-step line search.
+- **First-order / SGD (Ch 8, 27)**
+  - **Dimension 1/2 friendly**: Gradients = tensor algebra, expressible as GEMM.
+  - **Dimension 6 (Parallelism and communication)** is good: Data-parallel all-reduce can overlap with backprop -- the fundamental reason this is the default approach for large models.
+- **Global search (Ch 14: GA/SA/PSO)**
+  - Violates **Dimension 1**: Non-differentiable, discrete stochastic search, blocks end-to-end gradient training.
+  - **Dimension 6** is also poor: Inter-population dependencies, hard to parallelize. Only suitable for black-box hyperparameter search, not for the training inner loop.
+- **LP simplex / interior-point methods (Ch 16, 18)**
+  - Simplex row operations are acceptable; interior-point methods require solving a linear system at each step, **Dimension 2/6** limited by factorization and communication.
+  - Suitable for medium-scale constrained subproblems, not for placement inside every training step.
+- **Projections (S24.2)**
+  - Norm-ball / box projections are cheap elementwise operations (**Dimension 1/8** friendly).
+  - General polyhedral projections require solving a QP (**Dimension 2** degrades).
+- **Convergence depends on condition number kappa**
+  - Large kappa -> **Dimension 5** is further amplified at low precision (ill-conditioned gradients).
+  - Must pair with normalization / preconditioning; otherwise bf16 training diverges.
+
+## Which Thinking Lens to Invoke
+
+- **variational** (primary): The complete objective-constraint-optimality-convergence framework; this book is its core source; translate real-world tasks (classification / regression / constraints) into solvable optimization problems.
+- **algorithmic**: Convergence properties, complexity, step size / stopping criteria for iterative algorithms.
+- **duality**: Duality, kernel methods, variable substitution, SVD/PCA -- "equivalence transformations to simplify problems."
+- **probabilistic**: SGD stochastic gradients, SVRG variance reduction, cross-validation / regularization.
+
+## Anti-patterns
+
+- Applying **full-Hessian Newton** directly to large models -- O(d^2) memory and inversion blow up immediately (must use matrix-free / low-rank / block-diagonal).
+- Using **line search** to tune step sizes at every step of a large model -- scalar serial, control-flow divergence, burns through compute; should switch to scheduled learning rates.
+- Using **GA/SA/PSO to train neural networks** -- non-differentiable, cannot parallelize, extremely sample-inefficient; limited to black-box hyperparameter search only.
+- Discussing convergence while **ignoring the condition number kappa** -- expecting low-precision convergence without normalization / preconditioning is wishful thinking.
+- Forcing **LP simplex thinking** onto continuously differentiable problems.
+- Treating **duality / KKT as universal** -- non-convex problems typically lack strong duality and have duality gaps (S23.4.6); KKT is only a necessary condition.
+- Treating this "activation reference" as a source of rigorous proofs -- details and theorem conditions must be verified against the original book.
+
+## Deep-dive Entry
+
+> **Bibliographic information**: Edwin K. P. Chong, Wu-Sheng Lu, Stanislaw H. Zak, *An Introduction to Optimization, With Applications to Machine Learning*, 5th Edition, John Wiley & Sons, 2024. ISBN 978-1-119-87763-9.
+>
+> **Activation method**: Place `An Introduction to Optimization With Applications to Machine Learning.pdf` in the `math_book/` folder at the project root; the Agent can then automatically search the original text. The PDF is not distributed via npm/git (copyright reasons) and must be obtained separately.
+
+Full-fidelity lookup = have the Agent directly search the local PDF
+`math_book/An Introduction to Optimization With Applications to Machine Learning.pdf`, locating by actual chapter numbers:
+
+- **Ch 8 Gradient Methods** (S8.3 convergence analysis, condition numbers) + **Ch 11 Quasi-Newton Methods** (S11.5 BFGS) -- Optimizers and feasible second-order methods.
+- **Ch 22 Convex Optimization Problems** (S22.2 convex functions, S22.4 SDP/LMI) -- Convexity criteria and semidefinite programming.
+- **Ch 23 Lagrangian Duality** (S23.5 strong duality, S23.6.3 Slater conditions) + **Ch 21 KKT Conditions** -- Duality / KKT / saddle points.
+- **Ch 24 Algorithms for Constrained Optimization** (S24.3 projected gradient, S24.5 augmented Lagrangian, S24.6 penalty methods) -- Constrained training algorithms.
+- **Ch 27 Stochastic Gradient Descent Algorithms** (S27.1 SGD, S27.2 SVRG, S27.3 distributed and communication/computation) -- Large-scale training core.

package/references/books/optimization-ml.md

@@ -1,4 +1,4 @@
-# ⚙️ 最优化（含 ML 应用）/ Optimization with ML
+# 最优化（含 ML 应用）/ Optimization with ML
 
 > **An Introduction to Optimization, With Applications to Machine Learning** (5th Edition, 2024)
 > Edwin K. P. Chong, Wu-Sheng Lu, Stanisław H. Żak — John Wiley & Sons（Hardback ISBN 9781119877639）
@@ -132,11 +132,10 @@
 
 ## 该调用哪个思想透镜
 
-- **optimization**（主）：目标-约束-最优性-收敛的完整框架，本书是其核心出处。
-- **algorithmic-thinking**：迭代算法的收敛性、复杂度、步长 / 停机判据。
-- **transformation**：对偶、核技巧、变量替换、SVD/PCA——"等价转换简化问题"。
-- **modeling**：把现实任务（分类 / 回归 / 约束）翻译成可解的优化问题。
-- **probability-statistics**：SGD 随机梯度、SVRG 方差缩减、交叉验证 / 正则化。
+- **variational**（主）：目标-约束-最优性-收敛的完整框架，本书是其核心出处；把现实任务（分类 / 回归 / 约束）翻译成可解的优化问题。
+- **algorithmic**：迭代算法的收敛性、复杂度、步长 / 停机判据。
+- **duality**：对偶、核技巧、变量替换、SVD/PCA——"等价转换简化问题"。
+- **probabilistic**：SGD 随机梯度、SVRG 方差缩减、交叉验证 / 正则化。
 
 ## 反模式
 
@@ -150,7 +149,7 @@
 
 ## 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.
+> **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。
 

package/references/books/smooth-manifolds.en.md

@@ -0,0 +1,105 @@
+# Smooth Manifolds
+
+> **Book**: John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition. Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8 / DOI 10.1007/978-1-4419-9982-5. MSC 53-01 / 58-01 / 57-01.
+> **Positioning**: Equipping objects that "locally look like Euclidean space but can bend globally" (manifolds) with calculus (tangent spaces, vector fields, differential forms, flows, Lie derivatives) -- the mathematical mother of **manifold optimization, latent-space geometry, and differentiable structures**.
+
+## Overview
+
+Smooth manifold = a space that can be locally linearized by coordinate charts, with charts glued together by smooth transition maps. The main thread of the book: **first transplant Euclidean calculus onto curved spaces, then study geometric and topological invariants on them**. For AI, the most valuable part is the "differentiable machinery" in the first half -- tangent/cotangent spaces, vector fields, flows, Riemannian metrics.
+
+Actual chapter map (2nd ed., chapter numbers match the book):
+
+- **Ch 1-2 Smooth Manifolds / Smooth Maps**: topological manifolds, smooth structures (atlases), smooth maps, partitions of unity. -> The language of local linearization + global patching.
+- **Ch 3 Tangent Vectors**: tangent space T_pM, differential / pushforward df_p, tangent bundle TM. -> **The core of local linearization**, the geometric prototype of backpropagation.
+- **Ch 4-5 Submersions, Immersions, Embeddings / Submanifolds**: constant rank theorem, embeddings, regular level sets -> submanifolds. -> Constraint sets = submanifolds.
+- **Ch 6 Sard's Theorem**: critical values have measure zero, Whitney embedding theorem (n-dimensional manifolds embed in R^{2n}). -> Embedding dimensions / manifold hypothesis.
+- **Ch 7 Lie Groups**: both group and manifold (SO(n), U(n), GL(n), Stiefel...), Lie algebra = tangent space at the identity. -> Orthogonal/unitary weight constraints, equivariance.
+- **Ch 8-9 Vector Fields / Integral Curves and Flows**: vector fields, integral curves, flows (one-parameter diffeomorphism groups), Lie derivatives and Lie brackets [X,Y]. -> **The mother structure of Neural ODE / diffusion / continuous normalizing flows**.
+- **Ch 10-12 Vector Bundles / Cotangent Bundle / Tensors**: bundles, covector fields (1-forms), pullbacks, tensors. -> The true nature of gradients is covectors.
+- **Ch 13 Riemannian Metrics**: inner product at each point, length/distance/volume, tangent-cotangent isomorphism (musical sharp/flat, raising/lowering indices). -> **The metric source for natural gradients / Riemannian optimization**.
+- **Ch 14-16 Differential Forms / Orientations / Integration**: k-forms, wedge products, exterior derivative d (d^2=0), orientations, volume forms, integration on manifolds and change of variables. -> The log-det-Jacobian in normalizing flows = pullback of volume forms.
+- **Ch 17-18 De Rham Cohomology / de Rham Theorem**: closed forms modulo exact forms = topological invariants read from differential data. -> Global obstructions / cohomological regularization.
+- **Ch 19-22 Distributions & Foliations / Exponential Map / Quotient Manifolds / Symplectic Manifolds**: integrable distributions (Frobenius), exponential map (retraction prototype), quotient manifolds (Grassmannian etc.), symplectic forms and Hamiltonian flows. -> Retractions, quotient-space constraints, symplectic integrators / HMC.
+
+**Author's stated boundary (preface)**: the book stops at "building the tools," **deliberately omitting** connections, geodesics, curvature, fiber bundles, and Hodge theory -- these are covered in Lee's sequel *Riemannian Manifolds*. So if a problem truly requires the deep geometry of curvature/parallel transport, this book only provides the entry point via metrics and the exponential map; one must continue with a Riemannian geometry text.
+
+## Core Structures Transferable to AI/Infra
+
+- **Tangent space = local linearization of parameter/latent space**. `df_p: T_pM -> T_{f(p)}N` is the Jacobian / pushforward; backpropagation = pushforward along composed maps (the geometric version of the chain rule). All first-order methods live in the tangent space.
+- **Gradients are covectors, not vectors**. Autodiff produces 1-forms (elements of the cotangent space); to obtain a descent direction (tangent vector) one must use the **metric to raise indices** (sharp). Euclidean metric -> ordinary gradient; Fisher metric -> natural gradient. **This is the manifold-level root cause of natural gradients / mirror descent**.
+- **Constraint sets = submanifolds**. Regular level set theorem: when g is a submersion, the solution set `g(x)=c` is a smooth submanifold; constrained optimization = unconstrained optimization on a submanifold.
+- **Lie groups = differentiable symmetry groups**. SO(n)/U(n)/Stiefel/Grassmannian are all manifolds; their Lie algebras (e.g., skew-symmetric matrices so(n)) are linear spaces, mapped back to the group via `exp` -> **reparameterize "constrained weights" as "unconstrained Lie algebra + exp"**.
+- **Flows = time-parameterized families of diffeomorphisms**. Learning a vector field + integrating along it = Neural ODE / continuous normalizing flows / diffusion sampling. Flow invertibility and volume preservation directly correspond to model properties.
+- **Riemannian metric = designable/learnable "local geometry"**. It determines distances, angles, volumes, and orthogonality relations; changing the metric changes optimization trajectories and sampling measures.
+- **Differential forms + volume forms = the language of change of variables**. The `log|det J|` term in normalizing flows is precisely the pullback of a volume form under a map; choosing the right structure (triangular/coupling Jacobians) makes it cheap.
+
+## Problem Types Suited for Activation
+
+- Parameters should satisfy **geometric constraints**: orthogonality, unit norm, unit determinant, SPD, low-rank manifolds, hyperbolic/spherical latent spaces.
+- Optimization is more natural on **curved spaces**: subspace learning on Stiefel/Grassmannian, rotation/pose estimation, hyperspherical representations.
+- Need **structure-preserving dynamics**: invertible generative models, volume-preserving flows, Hamiltonian systems, energy-conserving long-horizon simulations.
+- **Latent space geometry**: interpolation, geodesics, metric learning, clustering/nearest-neighbor on manifolds.
+- Need to upgrade from correlations to **topological invariants**: detecting "holes" in latent spaces, global obstructions, cohomology-based consistency regularization.
+
+## Possible Algorithmic Inspirations
+
+- **Riemannian/manifold optimizers**: transplanting Adam/SGD onto Stiefel, Grassmannian, SPD, hyperbolic spaces -- projecting gradients to the tangent space + retraction back to the manifold.
+- **Orthogonal/Stiefel constrained weights**: using Cayley transforms or QR-retractions to maintain `W^T W = I`, mitigating gradient explosion/vanishing in RNNs/deep networks; or using so(n) Lie algebra + matrix-exp to reparameterize rotations.
+- **Geodesic interpolation**: using closed-form geodesics for interpolation and mixing in spherical/hyperbolic/SPD latent spaces, replacing Euclidean linear interpolation.
+- **Normalization on manifolds**: interpreting LayerNorm/feature normalization as projection onto spheres/unit manifolds; hyperspherical softmax and spectral normalization are instances of this.
+- **Neural ODE / continuous normalizing flows / diffusion**: learning a vector field X_theta, solving via flows; structured Jacobians make `log-det` cheap.
+- **Symplectic integrators / HMC**: using leapfrog-style symplectic, volume-preserving explicit updates for sampling and "optimization with momentum," stable over long horizons.
+- **Equivariant networks**: using Lie group actions + quotient manifolds to bake symmetries into the architecture (geometric deep learning).
+
+## GPU Friendliness Warning
+
+> The sole authority for the acceptance gate: the **eight dimensions** in `../gpu-friendly-math.md`. The success or failure of manifold methods almost entirely hinges on one point: **whether the retraction / exponential map can be tensorized and expressed as GEMM, or must be solved iteratively.**
+
+Dimension-by-dimension comparison:
+
+- **D1-D2 Tensorization / GEMM**: tangent-space operations (pushforward/pullback, Jacobian-vector products, projecting gradients to the tangent space) are **naturally batched GEMM** [v] -- backpropagation itself is pushforward, which is extremely GPU-friendly. **However**, retractions/exp typically require QR, eigendecomposition, matrix exponentials, or small-matrix inverses: QR/eig are **not clean GEMM**, they are decompositions with serial dependencies (cuSOLVER batched small matrices are acceptable, but large matrices are O(n^3) with poor parallelism) -> **reformable** rather than natively friendly.
+- **D3 Complexity**: geodesic distances, parallel transport, general `log|det J|` are all O(n^3) or worse. **Fix**: restrict to manifolds with closed-form geodesics (spheres/hyperbolic/SO(3)); use triangular/coupling layers in normalizing flows so that log-det reduces to a diagonal sum (O(n)).
+- **D5 Low-precision**: [~] **biggest pitfall**. Matrix `exp / log / sqrt`, eigendecompositions, and the affine-invariant metric for SPD are **catastrophically unstable** under bf16/fp16, often silently requiring fp32/fp64. Manifold primitives frequently "appear to run but have numerically diverged long ago."
+- **D6 Parallelism & communication**: the squaring chain in scaling-and-squaring, ODE integration steps, Householder/QR all have **serial recurrences**, making cross-SM/device overlap difficult. Positive counter-example: explicit symplectic integrators (leapfrog) are highly parallel [v].
+- **D4/D7/D8 Memory / Sparsity / Fusion**: if Lie algebra/rotation parameterizations are restricted to **small matrices or block-diagonal** structures (e.g., per-head rotations, SO(3) Rodrigues closed form), they can be fused into kernels and use Tensor Cores; large dense manifold operators require materializing large intermediate tensors.
+
+**Conclusions and reform strategies (echoing the toolbox in gpu-friendly-math.md)**:
+
+1. **Prefer manifolds with closed-form retractions** (spheres, Stiefel-QR, SO(3), hyperbolic).
+2. **Soften whenever possible**: replace hard constraints with pure-GEMM regularization terms (e.g., `lambda ||W^T W - I||^2` instead of strict orthogonal manifold) -- for most training this suffices.
+3. **Small matrices / blocking**: restrict exp/Cayley/QR to small blocks or per-head, batched as batched GEMM.
+4. **Structured Jacobians**: insist on triangular/coupling structures in normalizing flows, avoiding general LU for computing determinants.
+5. **Precision guardrails**: for all matrix exp/log/eig, enforce fp32 accumulation and numerical stabilization (log-sum-exp style).
+
+## Which Design Lens to Invoke
+
+- **variational (primary)**: constrained optimization, Riemannian/manifold optimization, retraction selection.
+- **symmetry**: Lie groups, equivariance, quotient manifolds, invariants under group actions.
+- **duality**: coordinate chart transitions, pushforward/pullback, change of variables in normalizing flows, diffeomorphisms.
+- **topological**: de Rham cohomology, global obstructions, "holes" and connectivity of latent spaces.
+- **categorical**: extracting the "locally linear + smoothly patched" manifold skeleton from high-dimensional messy ambient data (the manifold hypothesis).
+
+## Anti-patterns
+
+- **Confusing ML "tensors" (arrays) with mathematical tensors (multilinear, with covariant/contravariant transformation laws)**, mistakenly assuming coordinate-independent invariance comes for free.
+- **Putting exp / geodesics / matrix-log into bf16 hot training loops**: both slow (serial decomposition) and silently divergent. Ask first: "is there a closed-form retraction / can it be softened?"
+- **Not softening when you should**: using strict manifold constraints for marginal gains while paying the throughput and stability cost of QR/eig; for many tasks, an orthogonality regularization term suffices.
+- **Confusing gradients (covectors) with descent directions (vectors)**: forgetting the metric and treating raw autodiff output directly as natural gradients.
+- **The illusion of a single global coordinate chart**: covering an entire manifold with one global parameterization inevitably introduces singularities (e.g., Euler angle gimbal lock); manifolds inherently require atlases / redundant parameterizations.
+- **Manifold hypothesis overuse**: deploying the full Riemannian machinery when the parameter space is already flat Euclidean -- pure over-engineering (violates simplicity-first).
+
+## Deep Dive Entry
+
+> **Bibliographic info**: John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition, Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8.
+>
+> **Activation method**: Place `Introduction to Smooth Manifolds.pdf` in the `math_book/` folder at the project root; the Agent can then automatically search the original text. The PDF is not distributed via npm/git (copyright reasons); obtain it independently.
+
+> **Full-fidelity lookup**: when original definitions/theorems/proofs are needed, have the Agent **automatically search the local PDF** `math_book/Introduction to Smooth Manifolds.pdf` (locate by chapter number / keywords, do not rely on memory to restate). The following are actual chapter numbers (2nd ed.):
+
+- **Ch 3 Tangent Vectors** -- tangent spaces, differentials/pushforwards, tangent bundles: local linearization and the geometric prototype of backpropagation.
+- **Ch 11 The Cotangent Bundle** -- covector fields (1-forms), `df` as a covector, pullbacks: the true nature of gradients = covectors.
+- **Ch 13 Riemannian Metrics** -- metrics, tangent-cotangent isomorphism (sharp/flat), distances: the root of natural gradients / Riemannian optimization.
+- **Ch 9 Integral Curves and Flows** -- flows, integral curves, Lie derivatives/Lie brackets: Neural ODE / diffusion / structure-preserving dynamics.
+- **Ch 20 The Exponential Map** -- the exponential map: the retraction prototype, and also the main bottleneck for GPU feasibility.
+
+(Extensions: Ch 7 Lie Groups -> orthogonal/unitary constraints and equivariance; Ch 14 Differential Forms -> volume forms and log-det-Jacobian; Ch 22 Symplectic Manifolds -> symplectic integrators / HMC.)

package/references/books/smooth-manifolds.md

@@ -1,4 +1,4 @@
-# 🌐 光滑流形 / Smooth Manifolds
+# 光滑流形 / Smooth Manifolds
 
 > **书目**：John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition. Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8 / DOI 10.1007/978-1-4419-9982-5. MSC 53-01 / 58-01 / 57-01.
 > **定位**：把"局部像欧氏空间、整体可弯曲"的对象（manifold）配上微积分（切空间、向量场、微分形式、流、李导数），是 **流形优化、隐空间几何、可微结构** 的数学母体。
@@ -16,7 +16,7 @@
 - **Ch 7 Lie Groups**：既是群又是流形（SO(n), U(n), GL(n), Stiefel…），李代数 = 单位元处切空间。→ 正交/酉权重约束、等变。
 - **Ch 8–9 Vector Fields / Integral Curves and Flows**：向量场、积分曲线、流（flow，单参数微分同胚群）、李导数与李括号 [X,Y]。→ **Neural ODE / 扩散 / 连续归一化流** 的母结构。
 - **Ch 10–12 Vector Bundles / Cotangent Bundle / Tensors**：丛、余向量场（1-form）、拉回（pullback）、张量。→ 梯度的真身是余向量。
-- **Ch 13 Riemannian Metrics**：每点内积、长度/距离/体积、切-余切同构（musical ♯/♭，升降指标）。→ **自然梯度 / 黎曼优化的度量来源**。
+- **Ch 13 Riemannian Metrics**：每点内积、长度/距离/体积、切-余切同构（musical (sharp)/(flat)，升降指标）。→ **自然梯度 / 黎曼优化的度量来源**。
 - **Ch 14–16 Differential Forms / Orientations / Integration**：k-形式、楔积、外微分 d（d²=0）、定向、体积形式、流形上积分与变量替换。→ 归一化流的 log-det-Jacobian = 体积形式拉回。
 - **Ch 17–18 De Rham Cohomology / de Rham Theorem**：闭形式模去恰当形式 = 从微分数据读出的拓扑不变量。→ 全局障碍 / 上同调正则。
 - **Ch 19–22 Distributions & Foliations / Exponential Map / Quotient Manifolds / Symplectic Manifolds**：可积分布（Frobenius）、指数映射（retraction 原型）、商流形（Grassmann 等）、辛形式与 Hamilton 流。→ retraction、商空间约束、辛积分器 / HMC。
@@ -26,7 +26,7 @@
 ## 可迁移到 AI/Infra 的核心结构
 
 - **切空间 = 参数/隐空间的局部线性化（local linearization）**。`df_p: T_pM → T_{f(p)}N` 就是 Jacobian / pushforward；反向传播 = 沿复合映射做 pushforward（链式法则的几何版）。一切一阶方法都活在切空间里。
-- **梯度是余向量（covector），不是向量**。autodiff 给出的是 1-form（余切空间元素）；要变成可下降的方向（切向量）必须用 **度量升指标**（♯）。欧氏度量 → 普通梯度；Fisher 度量 → 自然梯度（natural gradient）。**这是自然梯度 / 镜像下降的流形根因**。
+- **梯度是余向量（covector），不是向量**。autodiff 给出的是 1-form（余切空间元素）；要变成可下降的方向（切向量）必须用 **度量升指标**（(sharp)）。欧氏度量 → 普通梯度；Fisher 度量 → 自然梯度（natural gradient）。**这是自然梯度 / 镜像下降的流形根因**。
 - **约束集 = 子流形（submanifold）**。正则水平集定理：当 g 是 submersion 时 `g(x)=c` 的解集是光滑子流形；约束优化 = 在子流形上做无约束优化。
 - **李群 = 可微的对称群**。SO(n)/U(n)/Stiefel/Grassmann 都是流形；其李代数（如反对称矩阵 so(n)）是线性空间，用 `exp` 映射回群 → **把"约束权重"重参数化为"无约束李代数 + exp"**。
 - **流（flow）= 时间参数化的微分同胚族**。学一个向量场 + 沿它积分 = Neural ODE / 连续归一化流 / 扩散采样。流的可逆性、保体积性直接对应模型性质。
@@ -57,10 +57,10 @@
 
 逐维对照：
 
-- **维度 1–2 张量化 / GEMM**：切空间运算（pushforward/pullback、Jacobian-向量积、把梯度投影到切空间）**天然是 batched GEMM** ✅——反向传播本就是 pushforward，这部分对 GPU 极友好。**但** retraction/exp 多半要 QR、特征分解、矩阵指数或小矩阵求逆：QR/eig **不是干净的 GEMM**，是带串行依赖的分解（cuSOLVER 批量小矩阵尚可，大矩阵 O(n³) 且并行差）→ **可改造** 而非天然友好。
+- **维度 1–2 张量化 / GEMM**：切空间运算（pushforward/pullback、Jacobian-向量积、把梯度投影到切空间）**天然是 batched GEMM** [v]——反向传播本就是 pushforward，这部分对 GPU 极友好。**但** retraction/exp 多半要 QR、特征分解、矩阵指数或小矩阵求逆：QR/eig **不是干净的 GEMM**，是带串行依赖的分解（cuSOLVER 批量小矩阵尚可，大矩阵 O(n³) 且并行差）→ **可改造** 而非天然友好。
 - **维度 3 复杂度**：测地线距离、平行移动、一般 `log|det J|` 都是 O(n³) 起。**改造**：限定有闭式测地线的流形（球面/双曲/SO(3)）；归一化流用三角/耦合层让 log-det 退化成对角和（O(n)）。
-- **维度 5 低精度**：⚠️ **最大坑**。矩阵 `exp / log / sqrt`、特征分解、SPD 的仿射不变度量在 bf16/fp16 下 **灾难性不稳定**，常静默地需要 fp32/fp64。流形原语经常"表面能跑、数值早已发散"。
-- **维度 6 并行与通信**：scaling-and-squaring 的平方链、ODE 积分步、Householder/QR 都有 **串行递推**，难跨 SM/设备 overlap。反例向好：显式辛积分器（leapfrog）高并行 ✅。
+- **维度 5 低精度**：[~] **最大坑**。矩阵 `exp / log / sqrt`、特征分解、SPD 的仿射不变度量在 bf16/fp16 下 **灾难性不稳定**，常静默地需要 fp32/fp64。流形原语经常"表面能跑、数值早已发散"。
+- **维度 6 并行与通信**：scaling-and-squaring 的平方链、ODE 积分步、Householder/QR 都有 **串行递推**，难跨 SM/设备 overlap。反例向好：显式辛积分器（leapfrog）高并行 [v]。
 - **维度 4/7/8 显存 / 稀疏 / 融合**：李代数/旋转参数化若限制在 **小矩阵或块对角**（如逐头旋转、SO(3) 的 Rodrigues 闭式），可融进 kernel、走 Tensor Core；大稠密流形算子则要物化大中间张量。
 
 **结论与改造手法（呼应 gpu-friendly-math.md 工具箱）**：
@@ -73,11 +73,11 @@
 
 ## 该调用哪个思想透镜
 
-- **optimization（⚖️ 优化思想）**：主武器——约束下寻最优、黎曼/流形优化、retraction 选型。
-- **symmetry（⚛️ 对称与不变性）**：李群、等变、商流形、群作用下的不变量。
+- **variational（变分透镜）**：主透镜——约束下寻最优、黎曼/流形优化、retraction 选型。
+- **symmetry（对称与不变性）**：李群、等变、商流形、群作用下的不变量。
 - **duality（对偶透镜）**：坐标卡变换、pushforward/pullback、归一化流的变量替换、微分同胚。
-- **topological-thinking（🌀 拓扑思想）**：de Rham 上同调、全局障碍、隐空间的"洞"与连通性。
-- **abstraction（🧩 抽象化思想）**：从高维杂乱的环境数据中抽出"局部线性 + 光滑拼接"的流形骨架（流形假设）。
+- **topological（拓扑透镜）**：de Rham 上同调、全局障碍、隐空间的"洞"与连通性。
+- **categorical（范畴化透镜）**：从高维杂乱的环境数据中抽出"局部线性 + 光滑拼接"的流形骨架（流形假设）。
 
 ## 反模式
 
@@ -90,7 +90,7 @@
 
 ## 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.
+> **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。
 
@@ -98,7 +98,7 @@
 
 - **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。
 - **Ch 11 The Cotangent Bundle** — 余向量场（1-form）、`df` 作为余向量、pullback：梯度真身 = 余向量。
-- **Ch 13 Riemannian Metrics** — 度量、切-余切同构（♯/♭）、距离：自然梯度 / 黎曼优化的根。
+- **Ch 13 Riemannian Metrics** — 度量、切-余切同构（(sharp)/(flat)）、距离：自然梯度 / 黎曼优化的根。
 - **Ch 9 Integral Curves and Flows** — 流、积分曲线、李导数/李括号：Neural ODE / 扩散 / 保结构动力学。
 - **Ch 20 The Exponential Map** — 指数映射：retraction 原型，也是 GPU 可行性的主瓶颈。
 

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

@@ -5,6 +5,19 @@
 >
 > This file is the single source of truth for the "GPU-feasibility" acceptance gate. The activator, the 15 thinking lenses, the book references, and the math-critic all point here.
 
+## Eight-Dimension Abbreviations
+
+| Abbrev. | Full Name |
+|---------|-----------|
+| D1 | Tensorization |
+| D2 | GEMM-mappability |
+| D3 | Complexity |
+| D4 | Memory & KV-Cache |
+| D5 | Low-precision stability |
+| D6 | Parallelism & communication |
+| D7 | Sparse structure |
+| D8 | Operator fusion |
+
 ## Core Proposition
 
 **Mathematical beauty ≠ computability.** For a structure to truly enter training and inference on modern GPU clusters, it must simultaneously satisfy two requirements:
@@ -18,7 +31,7 @@ Many "beautiful on paper" modern mathematical structures cannot run at high perf
 
 For any candidate structure (operator, attention variant, routing mechanism, regularization term, compression scheme…) rate each dimension as `Friendly / Retrofittable / Unfriendly` and provide adaptation recommendations.
 
-| # | Dimension | Key Question | Friendly ✅ | Unfriendly ❌ |
+| # | Dimension | Key Question | Friendly [v] | Unfriendly [x] |
 |---|-----------|-------------|------------|--------------|
 | 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 |
@@ -57,7 +70,7 @@ Drawn from the auto-research directions cited in `agentic-workflow.md`, demonstr
 
 | 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) |
+| Tropical Gating | Tropical semiring, piecewise-linear | Replaces Top-K: element-wise max-plus — dim 1 [v] Tensorization / dim 2 [x] Not a Tensor Core GEMM (runs on CUDA cores) / dim 3 [v] 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) |

package/references/gpu-friendly-math.md

@@ -7,6 +7,19 @@
 >
 > This file is the single source of truth for the "GPU-feasibility" acceptance gate. The activator, the 15 thinking lenses, the book references, and the math-critic all point here.
 
+## 八维缩写速查
+
+| 缩写 | 全称 |
+|------|------|
+| D1 | 张量化 |
+| D2 | GEMM 可映射 |
+| D3 | 复杂度 |
+| D4 | 显存与 KV-Cache |
+| D5 | 低精度稳定 |
+| D6 | 并行与通信 |
+| D7 | 稀疏结构 |
+| D8 | 算子融合 |
+
 ## 核心命题 / Core Proposition
 
 **数学美 ≠ 可算。** 一个结构要真正进入现代 GPU 集群的训练与推理，必须同时满足两件事：
@@ -20,7 +33,7 @@
 
 对任何候选结构（算子、注意力变体、路由、正则项、压缩方案……）逐项评 `友好 / 可改造 / 不友好`，并给出改造建议。
 
-| # | 维度 | 关键问题 | 友好 ✅ | 不友好 ❌ |
+| # | 维度 | 关键问题 | 友好 [v] | 不友好 [x] |
 |---|------|---------|--------|----------|
 | 1 | **张量化 / Tensorization** | 能否表达为稠密张量运算，避免逐元素不规则控制流？ | 批量张量代数 | 标量循环、数据相关分支 |
 | 2 | **GEMM 可映射 / GEMM mappability** | 能否落到 矩阵乘 / batched GEMM / 卷积，吃满 Tensor Core？ | 可写成 GEMM 链 | 无法矩阵化的不规则运算 |
@@ -59,7 +72,7 @@
 
 | 组件 | 数学来源 | GPU 友好性 |
 |------|---------|-----------|
-| 热带门控 Tropical Gating | 热带半环分段线性 | 替代 Top-K：逐元素 max-plus——dim 1 ✅ 张量化 / dim 2 ❌ 非 Tensor Core GEMM（落 CUDA core）/ dim 3 ✅ 仅逐 token 门控亚二次（min-plus matmul 则 APSP-hard 非亚二次）；次可微，折点需 LogSumExp 软化（软化退回标准 softmax）|
+| 热带门控 Tropical Gating | 热带半环分段线性 | 替代 Top-K：逐元素 max-plus——dim 1 [v] 张量化 / dim 2 [x] 非 Tensor Core GEMM（落 CUDA core）/ dim 3 [v] 仅逐 token 门控亚二次（min-plus matmul 则 APSP-hard 非亚二次）；次可微，折点需 LogSumExp 软化（软化退回标准 softmax）|
 | 胞腔层扩散 Cellular Sheaf Diffusion | 代数几何/拓扑（层、限制映射）| 每边低秩线性变换 = 小 GEMM（维度 2/4）|
 | Čech 上同调正则 | 代数拓扑（一阶上同调 H¹）| 局部、廉价；作幻觉的代数判据（维度 3/8）|
 | 低秩基底 KV 压缩（Plücker/Grassmannian 视角） | 射影几何 | 存基底而非 Plücker 坐标（后者低秩时反扩张）；块摘要候选，压缩率/误差/吞吐需实测（维度 4）|

package/skills/math-research-activator/SKILL.en.md

@@ -6,7 +6,33 @@ description: |
 
 
 > **File routing**: When this document references any file (lenses, knowledge-base, design-patterns, references, agents), always load the `.en.md` variant if it exists. For example, `../../lenses/symmetry.md` → load `lenses/symmetry.en.md`.
-# 🧭 Math Research OS
+>
+> ## Language Routing & Mixed-Input Rules
+>
+> Language routing only determines "which language version to read" and "what language to respond in." It does NOT affect whether the math system triggers or the A/B/C/D/E scenario classification.
+>
+> ### Decision Rules
+>
+> 1. **Judge the natural-language frame first**
+>    - If the user's sentence structure, verbs, and mood particles are primarily Chinese, treat as Chinese even if English technical terms are interspersed.
+>    - E.g., "帮我 design 一个 attention" / "这个 loss 有没有理论问题" → Chinese.
+>
+> 2. **English technical terms do not count as English primary language**
+>    - attention, loss, routing, embedding, manifold, operator, kernel, KV-cache, transformer, MoE, etc. are domain terms and do not trigger a switch to English.
+>
+> 3. **Code, paths, and formulas are excluded from language detection**
+>    - File paths, function names, variable names, LaTeX formulas, and CLI arguments do not count toward language ratio.
+>
+> 4. **When primary language is unclear, follow the user's last clear language**
+>    - If the CN/EN ratio is close and indeterminate, use the user's most recent unambiguous natural language.
+>    - If there is no prior context, default to Chinese.
+>
+> 5. **Output language matches primary language**
+>    - Chinese primary → read `SKILL.md`, respond in Chinese, retaining necessary English terms.
+>    - English primary → read `SKILL.en.md`, respond in English.
+>    - If the user explicitly requests "in English" / "in Chinese," follow the explicit request.
+
+# Math Research OS
 
 > "The thinking system does not hand out theorems, the knowledge system does not indulge in loose inspiration, and the design layer does not fake profundity."
 

package/skills/math-research-activator/SKILL.md

@@ -5,9 +5,32 @@ description: |
   English: Mathematical research OS — auto-diagnoses user intent, routes to thinking lenses, math knowledge base, or design translation layer. Triggers on architecture/operator design, theoretical analysis, math-to-AI transfer. Does NOT trigger for pure engineering tasks.
 ---
 
-> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `SKILL.en.md`；中文消息则继续使用本文件。
-
-# 🧭 数学研究操作系统 / Math Research OS
+> ## 语言路由与混合输入规则
+>
+> 语言路由只决定"读取哪个语言版本的说明"和"最终用什么语言回答"，不参与数学系统是否触发、也不参与 A/B/C/D/E 场景判断。
+>
+> ### 判定规则
+>
+> 1. **先判断自然语言主框架**
+>    - 如果用户的请求句式、动词、语气词主要是中文，即使夹杂英文技术词，也按中文处理。
+>    - 例如："帮我 design 一个 attention""这个 loss 有没有理论问题""能不能用 manifold 做 routing"均按中文处理。
+>
+> 2. **英文技术词不计入英文主语言**
+>    - attention、loss、routing、embedding、manifold、operator、kernel、KV-cache、transformer、MoE 等 AI/数学/工程术语视为领域术语，不作为切换到英文的依据。
+>
+> 3. **代码、路径、公式不参与语言判定**
+>    - 文件路径、函数名、变量名、LaTeX 公式、命令行参数不计入语言比例。
+>
+> 4. **主语言不明显时，沿用用户上一轮主要语言**
+>    - 若中英文比例接近且无法判断，以用户最近一次明确使用的自然语言为准。
+>    - 若没有上下文，默认中文。
+>
+> 5. **输出语言与主语言一致**
+>    - 中文主语言 → 读取中文 `SKILL.md`，用中文回答，保留必要英文术语。
+>    - 英文主语言 → 读取 `SKILL.en.md`，用英文回答。
+>    - 用户明确要求"用英文/用中文"时，以用户显式要求为准。
+
+# 数学研究操作系统 / Math Research OS
 
 > "思想系统不负责给定理，知识系统不负责乱启发，设计层不负责装深刻。"