math-skill 2.1.0 → 3.0.1

package/lenses/local-to-global.en.md

@@ -0,0 +1,52 @@
+# Local-to-Global Lens
+
+> Patching local properties into global, sheaf cohomology obstructions — can local solutions be seamlessly assembled into a global solution? Where do the obstructions lie?
+
+## What This Perspective Is
+
+This is a "patcher's" perspective — starting from local patches that cover a space, asking: "Can properties that hold in each local region be consistently assembled into a globally valid property?" The core conviction: the difficulty of many global problems lies not in local solving but in the compatibility between local solutions. The partition of unity theorem guarantees that smooth functions can always be patched from local to global, but sheaf cohomology precisely characterizes when such patching fails — a nonzero cohomology group signals the existence of a global obstruction.
+
+## Problems It Diagnoses Well
+
+- Whether locally defined quantities (gradients, features, representations) can be consistently assembled into a global quantity
+- When analytic continuation is unique and when multivaluedness arises (applicability of the monodromy theorem)
+- Whether local consensus in a distributed system can guarantee global consistency
+- Whether local trivializations of a fiber bundle can be patched into a global trivialization — what is the topological obstruction?
+- Detecting global inconsistencies across overlapping covers via Cech cohomology
+
+## Problems It Doesn't Fit
+
+- Problems that are inherently global and indivisible — no natural local cover exists
+- Concerns only single-point properties rather than the local-to-global transition
+- Purely algebraic problems — no concept of spatial covering or patching is involved
+
+## Knowledge Domains It Routes To
+
+- **topology/persistent-homology**: Persistent homology — a bridge from local neighborhoods to global topological features
+- **topology/fundamental-group**: Fundamental group as a global invariant of path connectivity, detecting "holes" invisible locally
+- **topology/euler-characteristic**: Euler characteristic — linking local combinatorial information to global topology
+- **differential-geometry/connection**: Connections defining parallel transport — consistency conditions from local tangent spaces to global
+- **differential-geometry/manifold**: Atlases and coordinate transformations — the manifold definition itself is the paradigm of local-to-global
+
+## AI Designs It May Inspire
+
+- **Sheaf Consistency Loss**: Penalize incompatibility between representations in adjacent local regions, driving globally consistent representation learning
+- **Local-Global Verifier**: Solve independently on multiple patches, then check global consistency via the Cech condition
+- **Cohomological Obstruction Detector**: Automatically identify which local solution combinations have topological obstructions requiring global correction
+- **Partition-and-Stitch Framework**: Decompose a global problem into a weighted superposition of local subproblems using the partition of unity idea
+
+## Reasoning Protocol
+
+1. **Choose a local cover**: What family of open sets covers the problem space? What are the granularity and overlap of the cover?
+2. **Solve local problems**: Solve independently on each covering set, recording the form and scope of each solution
+3. **Check compatibility conditions**: Are the local solutions consistent on overlap regions? Do the transition functions satisfy the cocycle condition?
+4. **Identify cohomological obstructions**: If compatibility fails, compute the Cech cohomology group — a nonzero group indicates an irremovable global obstruction
+5. **Decide on a strategy**: Is the obstruction removable (adjust local solutions) or essential (a global method is required, or multivaluedness must be accepted)?
+
+## Acceptance Criteria
+
+- The local cover is clearly defined with stated granularity and overlap
+- Each local solution is independently provided with its scope annotated
+- Compatibility conditions on overlap regions have been checked and results recorded
+- If obstructions exist, the cohomology group has been computed or estimated and the obstruction type classified
+- A final strategy is determined — patching succeeded, global correction needed, or obstruction is irremovable

package/lenses/local-to-global.md

@@ -0,0 +1,52 @@
+# 局部到全局透镜
+
+> 局部性质拼接为全局、层上同调障碍——局部解能否无缝组装成全局解？障碍在哪里？
+
+## 它是什么视角
+
+这是一种"拼接者"的视角——从覆盖空间的局部 patches 出发，追问"每个局部区域内成立的性质，能否一致地拼接为全局成立的性质？"核心信念：许多全局问题的难度不在于局部求解，而在于局部解之间的相容性。单位分解定理保证了光滑函数总可局部拼接为全局，但层上同调精确刻画了什么时候这种拼接会失败——上同调群非零 = 全局障碍存在。
+
+## 适合诊断什么问题
+
+- 局部定义的量（梯度、特征、表示）能否一致地组装为全局量？
+- 解析延拓何时唯一、何时出现多值性（单值化定理的适用性）
+- 分布式系统中局部共识能否保证全局一致性？
+- 纤维丛的局部平凡化能否拼接为全局平凡化——拓扑障碍是什么？
+- Cech 上同调检测覆盖之间的全局不一致性
+
+## 不适合什么问题
+
+- 问题本身就是全局的且不可分解——没有自然的局部覆盖
+- 只关心单点性质而非局部到全局的过渡
+- 纯代数问题——不涉及空间覆盖与拼接的概念
+
+## 会路由到哪些知识域
+
+- **topology/persistent-homology**：持续同调——从局部邻域到全局拓扑特征的桥梁
+- **topology/fundamental-group**：基本群作为路径连通性的全局不变量，检测局部无法捕获的"洞"
+- **topology/euler-characteristic**：Euler 示性数——局部组合信息与全局拓扑的关联
+- **differential-geometry/connection**：联络定义平行移动——局部切空间到全局的一致性条件
+- **differential-geometry/manifold**：图册与坐标变换——流形定义本身即局部到全局的范式
+
+## 可能产生哪些 AI 设计
+
+- **层一致性损失**：惩罚相邻局部区域表示之间的不相容，驱动全局一致表示学习
+- **局部-全局验证器**：在多 patch 上独立求解后用 Cech 条件检验全局一致性
+- **上同调障碍检测器**：自动识别哪些局部解组合存在拓扑障碍，需要全局修正
+- **分区拼接框架**：用单位分解思想将全局问题分解为加权局部子问题的叠加
+
+## 推理协议
+
+1. **选择局部覆盖**：用什么开集族覆盖问题空间？覆盖的粒度和重叠度如何？
+2. **求解局部问题**：在每个覆盖集上独立求解，记录解的形式与适用范围
+3. **检查相容性条件**：在重叠区域，局部解是否一致？转移函数是否满足余环条件？
+4. **识别上同调障碍**：若相容性失败，计算 Cech 上同调群——非零群 = 不可消除的全局障碍
+5. **决定策略**：障碍可消除（调整局部解）还是本质性的（需要全局方法或接受多值性）？
+
+## 验收标准
+
+- 局部覆盖已明确定义，覆盖粒度与重叠度已说明
+- 每个局部解已独立给出并标注适用范围
+- 重叠区域的相容性条件已检查，结果已记录
+- 若存在障碍，上同调群已计算或估计，障碍类型已分类
+- 最终策略已确定——拼接成功/需要全局修正/障碍不可消除

package/lenses/perturbation.en.md

@@ -0,0 +1,51 @@
+# Perturbation Lens
+
+> Propagation of small perturbations, stability, and robustness — a system's sensitivity to tiny changes determines its reliability
+
+## What This Perspective Is
+
+This is a "stress-tester's" perspective — for any mathematical object or system design, ask: "If the input, parameters, or structure undergo a small change, how much does the output shift? Is the shift controllable?" The core conviction: a well-posed system's response to perturbation should be bounded and predictable; if a design collapses under infinitesimal perturbation, it is destined to fail in practice. The condition number is the precise measure of perturbation amplification.
+
+## Problems It Diagnoses Well
+
+- Robustness analysis of models against input noise or adversarial perturbations
+- Small parameter changes causing solution jumps in optimization — is the problem ill-conditioned?
+- Stability of eigenvalues and eigenvectors under matrix perturbation (Davis-Kahan theorem)
+- Identifying regular vs. singular perturbations in asymptotic expansions
+- Error propagation and condition number analysis in numerical algorithms
+
+## Problems It Doesn't Fit
+
+- Problems where the perturbation itself is the object of study (e.g., butterfly effect in chaotic systems is a feature, not a defect)
+- Large-deformation or global structural analysis — perturbation theory only concerns local neighborhoods
+- Discrete combinatorial problems — perturbation theory relies on continuity assumptions
+
+## Knowledge Domains It Routes To
+
+- **matrix-analysis/matrix-perturbation**: Weyl's inequality, Davis-Kahan theorem, perturbation bounds for eigenvalues and singular values
+- **optimization/constrained-optimization**: Stability of KKT conditions, sensitivity of optimal solutions to perturbation
+- **probability/concentration-inequality**: Concentration phenomena under random perturbation, sub-Gaussian tail bounds
+- **differential-geometry/curvature**: Curvature as a measure of geodesic deviation — perturbation amplification in geometric terms
+
+## AI Designs It May Inspire
+
+- **Perturbation Regularization**: Add input or weight perturbation terms to the loss to train models insensitive to small changes
+- **Condition Number Monitor**: Track the condition number of weight matrices or the Hessian in real time to warn of ill-conditioning
+- **Robustness Verification Layer**: Quantify maximum output shift using epsilon-delta bounds, providing formal robustness guarantees
+- **Adaptive Preconditioning**: Dynamically adjust optimizer step size based on the perturbation amplification factor
+
+## Reasoning Protocol
+
+1. **Identify the perturbation source**: Does the perturbation occur in the input, parameters, or structure? What is its magnitude epsilon?
+2. **Compute sensitivity**: Derive the Jacobian or condition number — the ratio of output shift Delta to perturbation epsilon
+3. **Classify the perturbation**: Regular perturbation (expansion converges order by order) vs. singular perturbation (leading-order term changes)
+4. **Establish perturbation bounds**: Use known theorems (Weyl, Davis-Kahan, Lipschitz constants) to provide rigorous upper bounds
+5. **Assess robustness**: Is the perturbation amplification within acceptable range? If not, what regularization is needed?
+
+## Acceptance Criteria
+
+- The perturbation source and its magnitude epsilon are clearly defined
+- Sensitivity or condition number has been computed or estimated
+- The perturbation type has been classified (regular or singular)
+- The output shift has a quantified upper bound (not merely a heuristic estimate)
+- The robustness conclusion is actionable — pass, fail, or specification of required regularization

package/lenses/perturbation.md

@@ -0,0 +1,51 @@
+# 微扰透镜
+
+> 小扰动的传播、稳定性、鲁棒性——系统对微小变化的敏感度决定了它的可靠性
+
+## 它是什么视角
+
+这是一种"压力测试者"的视角——对任何数学对象或系统设计，追问"如果输入/参数/结构发生微小变化，输出会偏移多少？偏移是否可控？"核心信念：一个良态系统的输出对扰动的响应应当是有界的、可预测的；如果一个设计在无穷小扰动下就崩溃，那它在现实中注定失败。条件数是扰动放大倍数的精确度量。
+
+## 适合诊断什么问题
+
+- 模型对输入噪声/对抗扰动的鲁棒性分析
+- 优化问题中参数微变导致解的跳变——问题是病态的吗？
+- 特征值/特征向量在矩阵微扰下的稳定性（Davis-Kahan 定理）
+- 渐近展开中正则扰动 vs 奇异扰动的识别
+- 数值算法的误差传播与条件数分析
+
+## 不适合什么问题
+
+- 扰动本身就是研究对象（如混沌系统中蝴蝶效应是特征而非缺陷）
+- 需要大变形/全局结构分析——微扰只关心局部邻域
+- 离散组合问题——微扰理论依赖连续性假设
+
+## 会路由到哪些知识域
+
+- **matrix-analysis/matrix-perturbation**：Weyl 不等式、Davis-Kahan 定理、特征值/奇异值的扰动界
+- **optimization/constrained-optimization**：KKT 条件的稳定性、扰动后最优解的灵敏度
+- **probability/concentration-inequality**：随机扰动下的集中现象、亚高斯尾部界
+- **differential-geometry/curvature**：曲率作为测地线偏离的度量——几何意义上的扰动放大
+
+## 可能产生哪些 AI 设计
+
+- **扰动正则化**：在损失中加入输入/权重扰动项，训练对微小变化不敏感的模型
+- **条件数监控器**：实时跟踪权重矩阵/Hessian 的条件数，预警病态
+- **鲁棒性验证层**：用 ε-δ 界量化模型输出的最大偏移，提供形式化鲁棒性保证
+- **自适应预条件**：根据扰动放大因子动态调整优化器步长
+
+## 推理协议
+
+1. **识别扰动源**：扰动发生在输入、参数还是结构上？扰动的量级 ε 是多少？
+2. **计算灵敏度**：求导/Jacobian/条件数——输出偏移 Δ 与扰动 ε 的比值 Δ/ε
+3. **判断扰动类型**：正则扰动（展开式逐阶收敛）vs 奇异扰动（主导项阶次改变）
+4. **给出扰动界**：用已知定理（Weyl、Davis-Kahan、Lipschitz 常数）给出严格上界
+5. **评估鲁棒性**：扰动放大是否在可接受范围内？若不可接受，如何正则化？
+
+## 验收标准
+
+- 扰动源与扰动量级 ε 已明确定义
+- 灵敏度/条件数已计算或估计
+- 扰动类型已判定（正则/奇异）
+- 输出偏移有量化上界（非仅启发式估计）
+- 鲁棒性结论可执行——通过/不通过/需要何种正则化

package/lenses/probabilistic.en.md

@@ -0,0 +1,48 @@
+# Probabilistic Lens
+
+> Uncertainty is quantifiable — probability is quantified belief, data is quantified evidence
+
+## What Perspective It Offers
+
+The probabilistic perspective is a way of "making rational decisions under uncertainty": the world is full of uncertainty, and rational decision-making does not mean pursuing certainty but rather making choices that optimize expected value amid uncertainty. Bayesian updating is the core operation — a prior, upon encountering new data, becomes a posterior; the posterior, upon encountering further data, becomes the new prior. A critical distinction must be maintained: statistical significance is not the same as practical significance (p < 0.05 does not mean a large effect), and correlation is not causation (P(Y|X) is not P(Y|do(X))).
+
+## What Problems It Is Suited to Diagnose
+
+- Quantifying uncertainty — probability distributions, confidence intervals, and effect-size estimation
+- Bayesian inference — step-by-step belief updating through the prior–likelihood–posterior cycle
+- Hypothesis testing and experimental design — significance tests, power analysis, and sample-size planning
+- Causal effect estimation — distinguishing statistical association from causal effect
+
+## What Problems It Is Not Suited For
+
+- Deterministic problems — the answer is known or can be obtained by deduction; probabilistic tools are unnecessary
+- Extremely small sample sizes (n < 5) with no possibility of increase — report the data itself rather than inferences from it
+- Data that is entirely missing or severely corrupted — no meaningful statistical operation can be performed
+
+## Which Knowledge Domains It Routes To
+
+- `probability/entropy`: Kolmogorov axioms, distribution families, and the law of large numbers / CLT — the mathematical foundations of uncertainty
+- `probability/kl-divergence`: MLE, hypothesis testing, Bayesian inference, and regression modeling — extracting patterns from data
+- causal inference (no KB card yet, use critic): DAGs, the back-door criterion, and do-calculus — the reasoning framework from association to causation
+
+## What AI Designs It May Inspire
+
+- **Belief-Updating Engine**: Implements an automatic chain of Bayesian prior-to-posterior updates
+- **Experiment Design Advisor**: Automatically computes the minimum sample size based on effect size and statistical power
+- **Causal Identification Module**: Constructs a DAG from variable relationships and identifies back-door paths and adjustment sets
+
+## Reasoning Protocol
+
+1. **Define the Random Phenomenon**: Specify the random variables, sample space, event space, and probability measure
+2. **Select a Probabilistic Model**: Choose a distribution based on data type, sample size, and the underlying physical mechanism
+3. **Statistical Inference**: Point estimation / MLE, confidence intervals, hypothesis testing, or Bayesian updating
+4. **Causal Assessment** (where applicable): Construct a DAG, identify confounders, and apply the back-door criterion
+5. **Quantify Uncertainty**: Provide confidence or credible intervals, report effect sizes, and distinguish statistical significance from practical significance
+
+## Acceptance Criteria
+
+- Random variables and distributions have been explicitly defined
+- The inference method (frequentist or Bayesian) has been selected with stated rationale
+- The meaning of p-values has been correctly understood (not "degree of confidence")
+- Correlation and causation have been distinguished, and confounders have been checked
+- Effect sizes and uncertainty have been reported, not merely point estimates

package/lenses/probabilistic.md

@@ -0,0 +1,48 @@
+# 概率透镜
+
+> 不确定性是可量化的——概率是量化的信念，数据是量化的证据
+
+## 它是什么视角
+
+概率是一种"在不确定性中做理性决策"的眼光：世界充满不确定性，理性决策不是追求确定性，而是在不确定性中做出期望值最优的选择。贝叶斯更新是核心操作——先验遇新数据变成后验，后验遇更新数据又成为新先验。关键区分：统计显著不等于实际显著（p<0.05 不等于效应大），相关不等于因果（P(Y|X) 不等于 P(Y|do(X))）。
+
+## 适合诊断什么问题
+
+- 量化不确定性——概率分布、置信区间、效应量评估
+- 贝叶斯推断——先验-似然-后验的逐步信念更新
+- 假设检验与实验设计——显著性检验、功效分析、样本量规划
+- 因果效应估计——区分统计关联与因果效应
+
+## 不适合什么问题
+
+- 确定性问题——已知答案或可演绎推理得到，不需要概率工具
+- 样本量极小（n<5）且无法增加——应报告数据本身而非推断
+- 数据完全缺失或严重损坏——无法做有意义的统计操作
+
+## 会路由到哪些知识域
+
+- `probability/entropy`：Kolmogorov 公理、分布族、大数定律/CLT——不确定性的数学基础
+- `probability/kl-divergence`：MLE、假设检验、贝叶斯推断、回归建模——从数据中提取规律
+- 因果推断（暂无知识卡，由 critic 审查）：DAG、后门准则、do-演算——从关联到因果的推理框架
+
+## 可能产生哪些 AI 设计
+
+- **信念更新引擎**：实现贝叶斯先验→后验的自动更新链条
+- **实验设计顾问**：根据效应量与功效自动计算最小样本量
+- **因果识别器**：从变量关系构建 DAG，识别后门路径与调整集
+
+## 推理协议
+
+1. **定义随机现象**：明确随机变量、样本空间、事件域、概率测度
+2. **选择概率模型**：根据数据类型、样本量、物理机制选择分布
+3. **统计推断**：点估计/MLE、置信区间、假设检验或贝叶斯更新
+4. **因果评估**（如适用）：构建 DAG，识别混淆变量，应用后门准则
+5. **量化不确定性**：给出置信/可信区间，报告效应量，区分统计显著与实际显著
+
+## 验收标准
+
+- 随机变量与分布已明确定义
+- 推断方法（频率/贝叶斯）已选择并说明理由
+- p-value 的含义已正确理解（非"把握程度"）
+- 相关与因果已区分，混淆变量已检查
+- 效应量与不确定性已报告，非仅点估计

package/lenses/projection.en.md

@@ -0,0 +1,50 @@
+# Projection & Decomposition Lens
+
+> Complex wholes can be orthogonally decomposed into independent components — conflicts are exposed in subspaces, signal and noise are separated under projection.
+
+## What Perspective It Offers
+
+This is a "separator's" perspective — projecting mixed wholes onto orthogonal subspaces, splitting shared information from conflicting information, signal from noise, global structure from local detail. The core conviction: any vector can be decomposed into a parallel component plus an orthogonal component, and this decomposition is the first step toward understanding conflicts, eliminating redundancy, and compressing information.
+
+## What Problems It Is Suited to Diagnose
+
+- Multiple information sources are mixed; need to separate shared components from specific components (multi-domain learning, multimodal fusion)
+- Representations contain conflicting gradients or contradictory signals (multi-task learning, adversarial training)
+- Need to reduce dimensions or compress while preserving key structure (KV-Cache compression, feature selection)
+- Need to eliminate redundancy or orthogonalize multiple objectives (decorrelation, diversity constraints)
+
+## What Problems It Is Not Suited For
+
+- The problem itself is an indecomposable whole (strongly coupled systems, chaotic dynamics)
+- The subspace assumption is too strong — data does not lie on a low-dimensional subspace
+- Scenarios that require retaining all information with zero loss
+
+## Which Knowledge Domains It Routes To
+
+- **matrix-analysis/projection**: Orthogonal projection matrices, Courant-Fischer variational characterization
+- **matrix-analysis/spectral-decomposition**: EVD/SVD, principal component analysis
+- **matrix-analysis/low-rank-approximation**: Eckart-Young theorem, truncated SVD
+- **optimization/constrained-optimization**: Orthogonality-constrained optimization, Stiefel manifold
+
+## What AI Designs It May Inspire
+
+- **Shared-Private Decomposition**: Project multi-domain representations into a shared subspace plus domain-specific orthogonal complements
+- **Orthogonal Gradient Projection**: In multi-task learning, project new-task gradients onto the orthogonal complement of old-task gradients
+- **Low-Rank KV-Cache Compression**: Project K/V into a low-dimensional subspace, truncating weak components
+- **Head Diversity Constraint**: Force different attention heads to project onto approximately orthogonal subspaces
+
+## Reasoning Protocol
+
+1. **Identify mixed sources**: Which information, gradients, or representations are mixed together? Where do conflicts arise?
+2. **Define subspaces**: How are the dimensions of the shared space versus the specific space determined? What is the effective rank?
+3. **Construct projection operators**: $P = AA^H$ (orthonormal basis) or $P = A(A^HA)^{-1}A^H$ (general basis)
+4. **Perform decomposition**: $x = Px + (I-P)x$; evaluate the contribution of each component separately
+5. **Verify orthogonality**: Are $P^2 = P$ and $P = P^H$ satisfied? Is the condition number well-controlled?
+
+## Acceptance Criteria
+
+- The subspace decomposition is explicitly defined (dimensions, basis vectors, projection matrices)
+- The contributions of both components after projection have been separately quantified
+- Orthogonality conditions have been verified ($P^2 = P$, numerical condition number checked)
+- Compression/discard decisions are supported by quantified information-loss evidence
+- The output includes actionable conclusions, not merely the decomposition process

package/lenses/projection.md

@@ -0,0 +1,50 @@
+# 投影与分解透镜 / Projection & Decomposition Lens
+
+> 复杂整体可以正交分解为独立分量——冲突在子空间中暴露，信号与噪声在投影下分离。
+
+## 它是什么视角
+
+这是一种"分离者"的视角——将混杂的整体投影到正交子空间，把共享信息与冲突信息、信号与噪声、全局结构与局部细节拆分开来。核心信念：任何向量都可以分解为平行分量 + 正交分量，这种分解是理解冲突、消除冗余、压缩信息的第一步。
+
+## 适合诊断什么问题
+
+- 多个信息源混杂，需要分离共享成分与特异成分（多域学习、多模态融合）
+- 表示中存在冲突梯度或矛盾信号（多任务学习、对抗训练）
+- 需要降维或压缩但保留关键结构（KV-Cache 压缩、特征选择）
+- 需要消除冗余或正交化多个目标（去相关、diversity 约束）
+
+## 不适合什么问题
+
+- 问题本身就是不可分解的整体（强耦合系统、混沌动力学）
+- 子空间假设过强——数据不在低维子空间上
+- 需要保留全部信息不能有任何损失的场景
+
+## 会路由到哪些知识域
+
+- **matrix-analysis/projection**：正交投影矩阵、Courant-Fischer 变分刻画
+- **matrix-analysis/spectral-decomposition**：EVD/SVD、主成分分析
+- **matrix-analysis/low-rank-approximation**：Eckart-Young 定理、截断 SVD
+- **optimization/constrained-optimization**：正交约束优化、Stiefel 流形
+
+## 可能产生哪些 AI 设计
+
+- **Shared-Private 分解**：将多域表示投影为共享子空间 + 域特异正交补
+- **正交梯度投影**：在多任务学习中，将新任务梯度投影到旧任务梯度的正交补
+- **低秩 KV-Cache 压缩**：将 K/V 投影到低维子空间，截断弱分量
+- **Head diversity 约束**：强制不同 attention head 投影到近似正交的子空间
+
+## 推理协议
+
+1. **识别混杂源**：哪些信息/梯度/表示被混在一起？冲突在哪里发生？
+2. **定义子空间**：共享空间 vs 特异空间的维度如何确定？有效秩是多少？
+3. **构造投影算子**：$P = AA^H$（正交基）或 $P = A(A^HA)^{-1}A^H$（一般基）
+4. **执行分解**：$x = Px + (I-P)x$，分别评估两个分量的贡献
+5. **验证正交性**：$P^2 = P$、$P = P^H$ 是否满足？条件数是否可控？
+
+## 验收标准
+
+- 子空间分解已显式定义（维度、基向量、投影矩阵）
+- 投影后两个分量的贡献已分别量化
+- 正交性条件已验证（$P^2 = P$、数值条件数已检查）
+- 压缩/丢弃决策有信息损失量化依据
+- 输出包含可执行结论，不只是分解过程

package/lenses/spectral.en.md

@@ -0,0 +1,52 @@
+# Spectral Decomposition Lens
+
+> Any linear operator can be decomposed into a superposition of eigencomponents — eigenvalues reveal dominant structure, eigenvectors reveal dominant directions.
+
+## What Perspective It Offers
+
+This is a "decomposer's" perspective — breaking complex linear operators (matrices, kernel functions, graph Laplacians) into spectra of eigenvalues and singular values, using dominant eigencomponents to capture global behavior and tail eigenvalues to quantify noise and redundancy. The core conviction: the spectrum — the distribution of eigenvalues — determines everything about an operator: its condition number, rank, stability, and convergence rate.
+
+## What Problems It Is Suited to Diagnose
+
+- What is the dominant structure of a matrix or operator? What is its effective rank?
+- Optimizer convergence is slow — is the condition number too large? How should a preconditioner be designed?
+- Where are the critical bottlenecks in a graph or network? Is the spectral gap too small?
+- Need to reduce dimensions while preserving maximum variance — are the first k principal components sufficient?
+- How large is the spectral drift after quantization or pruning? Has stability been compromised?
+
+## What Problems It Is Not Suited For
+
+- Problems dominated by nonlinear effects — spectral decomposition is a linear tool
+- Operators that are not diagonalizable (non-normal matrices, defective matrices) — Jordan form is required
+- Problems that require preserving global topological structure — spectral methods may destroy topology
+
+## Which Knowledge Domains It Routes To
+
+- **matrix-analysis/spectral-decomposition**: EVD, Schur decomposition, normal matrices
+- **matrix-analysis/low-rank-approximation**: Eckart-Young theorem, randomized SVD
+- **matrix-analysis/matrix-perturbation**: Weyl's inequality, Davis-Kahan theorem
+- **matrix-analysis/positive-semidefinite**: Spectral properties of PSD matrices, Cholesky factorization
+
+## What AI Designs It May Inspire
+
+- **Spectral Normalization**: Constrain the largest singular value of weight matrices to stabilize training
+- **Low-Rank Adaptation (LoRA)**: Fine-tune in a truncated SVD subspace
+- **Spectral Graph Attention**: Use graph Laplacian eigenvectors for positional encoding
+- **Spectral Clustering Routing**: Use top-k eigenvectors for MoE token assignment
+- **Effective Rank Monitoring**: Track the stable rank of weight matrices to detect overfitting
+
+## Reasoning Protocol
+
+1. **Identify the operator**: Which matrix, kernel, or graph requires spectral analysis? What are its dimensions?
+2. **Compute or estimate the spectrum**: Full EVD (small matrices) / power iteration for dominant eigenvalues / randomized SVD
+3. **Analyze the spectral distribution**: Condition number, spectral gap, effective rank, decay rate
+4. **Identify dominant components**: What proportion of the variance or Frobenius norm is explained by the first k eigenvalues?
+5. **Assess truncation impact**: Quantify the error introduced by discarding tail eigenvalues (Eckart-Young provides a sharp bound)
+
+## Acceptance Criteria
+
+- The target operator is clearly defined
+- The spectrum (or dominant eigenvalues/singular values) has been computed or estimated
+- Spectral distribution metrics are reported (condition number, spectral gap, effective rank)
+- Truncation and approximation decisions are backed by quantitative error bounds (Weyl / Davis-Kahan / Eckart-Young)
+- The output includes actionable conclusions (preconditioner design, dimensionality selection, stability guarantees)

package/lenses/spectral.md

@@ -0,0 +1,52 @@
+# 谱分解透镜 / Spectral Decomposition Lens
+
+> 任何线性算子都可以分解为特征分量的叠加——特征值揭示主导结构，特征向量揭示主导方向。
+
+## 它是什么视角
+
+这是一种"分解者"的视角——将复杂线性算子（矩阵、核函数、图 Laplacian）分解为特征值/奇异值的谱，用主导特征分量捕获全局行为，用尾部特征量化噪声与冗余。核心信念：谱（特征值分布）决定了算子的一切——条件数、秩、稳定性、收敛速度。
+
+## 适合诊断什么问题
+
+- 矩阵/算子的主导结构是什么？有效秩是多少？
+- 优化器收敛速度慢——条件数是否过大？预条件如何设计？
+- 图/网络的关键瓶颈在哪里？谱隙（spectral gap）是否过小？
+- 需要降维但保留最大方差——前 k 个主成分够不够？
+- 量化/剪枝后的谱漂移有多大？稳定性是否被破坏？
+
+## 不适合什么问题
+
+- 非线性效应主导的问题——谱分解是线性工具
+- 算子本身不可对角化（非正规矩阵、亏损矩阵）——需要 Jordan 形式
+- 需要保留全局拓扑结构的问题——谱方法可能破坏拓扑
+
+## 会路由到哪些知识域
+
+- **matrix-analysis/spectral-decomposition**：EVD、Schur 分解、正规矩阵
+- **matrix-analysis/low-rank-approximation**：Eckart-Young 定理、随机化 SVD
+- **matrix-analysis/matrix-perturbation**：Weyl 不等式、Davis-Kahan 定理
+- **matrix-analysis/positive-semidefinite**：PSD 矩阵的谱性质、Cholesky
+
+## 可能产生哪些 AI 设计
+
+- **谱归一化**：约束权重矩阵的最大奇异值，稳定训练
+- **低秩适配器 (LoRA)**：在截断 SVD 子空间中做微调
+- **谱图注意力**：用图 Laplacian 特征向量做位置编码
+- **谱聚类路由**：用 top-k 特征向量做 MoE token 分配
+- **有效秩监控**：跟踪权重矩阵的稳定秩，检测过拟合
+
+## 推理协议
+
+1. **识别算子**：哪个矩阵/核/图需要谱分析？维度多大？
+2. **计算或估计谱**：完整 EVD（小矩阵）/ 幂迭代估计主导特征值 / 随机化 SVD
+3. **分析谱分布**：条件数、谱隙、有效秩、衰减率
+4. **识别主导分量**：前 k 个特征值解释了多大比例的方差/Frobenius 范数？
+5. **评估截断影响**：丢弃尾部特征造成的误差（Eckart-Young 给出精确界）
+
+## 验收标准
+
+- 目标算子已明确定义
+- 谱（或主导特征值/奇异值）已计算或估计
+- 谱分布指标已给出（条件数、谱隙、有效秩）
+- 截断/近似决策有量化误差界（Weyl/Davis-Kahan/Eckart-Young）
+- 输出包含可执行结论（预条件设计、降维维度选择、稳定性保证）

package/lenses/symmetry.en.md

@@ -0,0 +1,49 @@
+# Symmetry Lens
+
+> Seek the invariant amid change — every symmetry corresponds to a conserved quantity, and every invariant is a key to simplifying the problem
+
+## What Perspective It Offers
+
+Symmetry is a way of "finding what remains unchanged under transformations": when confronting a complex system, first ask, "Under what transformations do which properties of the system remain invariant?" Invariants are the core tool for simplification — they distinguish only between orbits (equivalence classes), not between elements within the same orbit. A complete set of invariants can embed the entire space into a simpler quotient space, achieving a full classification. Noether's theorem tells us that every continuous symmetry necessarily corresponds to a conservation law.
+
+## What Problems It Is Suited to Diagnose
+
+- Facing a complex system and seeking simplification clues — use invariants to reduce dimensionality
+- Needing to classify or identify objects — use orbits (the quotient space X/G)
+- Searching for conserved quantities or invariants — functions that are constant on orbits
+- Determining the solvability of equations (Galois theory) or designing equivariant structures
+
+## What Problems It Is Not Suited For
+
+- The system is completely asymmetric with no discernible pattern — no group action is available to exploit
+- Precise numerical solutions are required — symmetry provides structural information, not specific values
+- Symmetry breaking is the central mechanism — one should turn to analyzing the breaking pattern rather than searching for invariants
+- The group structure is too complex — when the quotient space is no simpler than the original space
+
+## Which Knowledge Domains It Routes To
+
+- `lie-theory/group-action`: Group actions, the orbit-stabilizer theorem, and Burnside's lemma — the algebraic foundations of symmetry
+- **lie-theory**: Lie groups, Lie algebras, and Noether's theorem — continuous symmetries and conservation laws
+- `lie-theory/lie-group`: Galois groups and solvable groups — algebraic criteria for the solvability of equations
+
+## What AI Designs It May Inspire
+
+- **Symmetry Detector**: Identifies candidate transformation groups from a problem description and verifies the group axioms
+- **Invariant Extractor**: Computes invariants using the Reynolds operator or Lie algebra generators
+- **Quotient-Space Classifier**: Works on X/G and uses a complete set of invariants to classify equivalence classes
+
+## Reasoning Protocol
+
+1. **Identify the Transformation Group**: List the candidate transformations of the system, organize them into a candidate group, and verify closure, associativity, identity, and inverses
+2. **Find Invariants**: For finite groups, use the Reynolds operator; for continuous groups, use Lie algebra generator equations
+3. **Simplify Using Invariants**: Work on the quotient space X/G, replacing constrained variables with invariants
+4. **Orbit Classification**: Use the orbit-stabilizer theorem and assess the completeness of the invariant set
+5. **Check for Symmetry Breaking**: Identify G → H breaking patterns and analyze Goldstone modes
+
+## Acceptance Criteria
+
+- The candidate group has been verified through the axioms (not merely assumed to have group structure)
+- Invariants have been explicitly given, distinguishing orbital invariants from global invariants
+- The simplification strategy has stated the degree of dimensionality reduction
+- Symmetry breaking has been checked (presence or absence; spontaneous or explicit)
+- Classification results and the completeness of the invariant set have been assessed

package/lenses/symmetry.md

@@ -0,0 +1,49 @@
+# 对称透镜
+
+> 在变化中寻找不变——每一个对称性都对应一个守恒量，每一个不变量都是简化问题的钥匙
+
+## 它是什么视角
+
+对称是一种"在变换下寻找不变"的眼光：面对复杂系统时，先问"什么变换下系统的哪些性质不变？"不变量是简化问题的核心工具——它只区分轨道（等价类），不区分同轨道内的元素。完备的不变量集能将整个空间嵌入更简单的商空间，实现完全分类。Noether 定理告诉我们：连续对称必然对应守恒律。
+
+## 适合诊断什么问题
+
+- 面对复杂系统想找简化线索——利用不变量降维
+- 需要分类/识别对象——利用轨道（商空间 X/G）
+- 寻找守恒量或不变量——轨道上取常值的函数
+- 判断方程可解性（Galois 理论）或设计等变结构
+
+## 不适合什么问题
+
+- 系统完全不对称且无规律——无群作用可利用
+- 需要精确数值解——对称性给结构信息而非具体数值
+- 对称破缺是核心机制——应转向分析破缺模式而非找不变量
+- 群结构过于复杂——商空间不比原空间简单时
+
+## 会路由到哪些知识域
+
+- `lie-theory/group-action`：群作用、轨道-稳定子定理、Burnside 引理——对称性的代数基础
+- **lie-theory**：李群/李代数、Noether 定理——连续对称与守恒律
+- `lie-theory/lie-group`：Galois 群、可解群——方程可解性的代数判据
+
+## 可能产生哪些 AI 设计
+
+- **对称性探测器**：从问题描述中识别候选变换群，验证群公理
+- **不变量提取器**：利用 Reynolds 算子或 Lie 代数生成元计算不变量
+- **商空间分类器**：在 X/G 上工作，用完备不变量集实现等价类分类
+
+## 推理协议
+
+1. **识别变换群**：列出系统可能的变换，组织为候选群，验证封闭/结合/单位/逆
+2. **寻找不变量**：有限群用 Reynolds 算子，连续群用 Lie 代数生成元方程
+3. **利用不变量简化**：在商空间 X/G 上工作，用不变量替代被约束变量
+4. **轨道分类**：利用轨道-稳定子定理，评估不变量完备性
+5. **检查对称破缺**：识别 G→H 破缺模式，分析 Goldstone 模数
+
+## 验收标准
+
+- 候选群已通过公理验证（不是假设它有群结构）
+- 不变量已显式给出，区分了轨道不变量与全局不变量
+- 简化策略已说明维度缩减程度
+- 对称破缺已检查（存在/破缺、自发/显式）
+- 分类结果与不变量完备性已评估