@baimingtao/lbs-agent 1.0.0

package/extensions/skills/builtin/research/research-paper-writing/references/paper-types.md

@@ -0,0 +1,481 @@
+# 超越实证 ML 的论文类型
+
+撰写非标准论文类型的指南：理论论文、综述/教程论文、基准/数据集论文和立场论文。每种类型都有其独特的结构、证据标准和目标会议期望。
+
+---
+
+## 目录
+
+- [理论论文](#theory-papers)
+- [综述与教程论文](#survey-and-tutorial-papers)
+- [基准与数据集论文](#benchmark-and-dataset-papers)
+- [立场论文](#position-papers)
+- [可复现性与重复性论文](#reproducibility-and-replication-papers)
+
+---
+
+## 理论论文
+
+### 何时撰写理论论文
+
+如果你的论文符合以下情况，它应该是一篇理论论文：
+- 主要贡献是定理、边界、不可能性结果或形式化刻画
+- 实验是补充性验证，而不是核心证据
+- 贡献在于增进理解，而不是为了达到 state-of-the-art 的数值
+
+### 结构
+
+```
+1. Introduction (1-1.5 pages)
+   - Problem statement and motivation
+   - Informal statement of main results
+   - Comparison to prior theoretical work
+   - Contribution bullets (state theorems informally)
+
+2. Preliminaries (0.5-1 page)
+   - Notation table
+   - Formal definitions
+   - Assumptions (numbered, referenced later)
+   - Known results you build on
+
+3. Main Results (2-3 pages)
+   - Theorem statements (formal)
+   - Proof sketches (intuition + key steps)
+   - Corollaries and special cases
+   - Discussion of tightness / optimality
+
+4. Experimental Validation (1-2 pages, optional but recommended)
+   - Do theoretical predictions match empirical behavior?
+   - Synthetic experiments that isolate the phenomenon
+   - Comparison to bounds from prior work
+
+5. Related Work (1 page)
+   - Theoretical predecessors
+   - Empirical work your theory explains
+
+6. Discussion & Open Problems (0.5 page)
+   - Limitations of your results
+   - Conjectures suggested by your analysis
+   - Concrete open problems
+
+Appendix:
+   - Full proofs
+   - Technical lemmas
+   - Extended experimental details
+```
+
+### 撰写定理
+
+**表述规范的定理模板：**
+
+```latex
+\begin{assumption}[Bounded Gradients]\label{assum:bounded-grad}
+There exists $G > 0$ such that $\|\nabla f(x)\| \leq G$ for all $x \in \mathcal{X}$.
+\end{assumption}
+
+\begin{theorem}[Convergence Rate]\label{thm:convergence}
+Under Assumptions~\ref{assum:bounded-grad} and~\ref{assum:smoothness},
+Algorithm~\ref{alg:method} with step size $\eta = \frac{1}{\sqrt{T}}$ satisfies
+\[
+\frac{1}{T}\sum_{t=1}^{T} \mathbb{E}\left[\|\nabla f(x_t)\|^2\right]
+\leq \frac{2(f(x_1) - f^*)}{\sqrt{T}} + \frac{G^2}{\sqrt{T}}.
+\]
+In particular, after $T = O(1/\epsilon^2)$ iterations, we obtain an
+$\epsilon$-stationary point.
+\end{theorem}
+```
+
+**定理表述规则：**
+- 明确陈述所有假设（编号并命名）
+- 包含正式的边界，而不仅仅是 "converges at rate O(·)"
+- 添加通俗语言的推论："In particular, this means..."
+- 与已知边界进行比较："This improves over [prior work]'s bound of O(·) by a factor of..."
+
+### 证明草图
+
+证明草图是理论论文正文中最重要的一部分。审稿人会借此评估你是拥有真正的洞见，还是仅仅在进行机械推导。
+
+**好的证明草图模式：**
+
+```latex
+\begin{proof}[Proof Sketch of Theorem~\ref{thm:convergence}]
+The key insight is that [one sentence describing the main idea].
+
+The proof proceeds in three steps:
+\begin{enumerate}
+\item \textbf{Decomposition.} We decompose the error into [term A]
+  and [term B] using [technique]. This reduces the problem to
+  bounding each term separately.
+
+\item \textbf{Bounding [term A].} By [assumption/lemma], [term A]
+  is bounded by $O(\cdot)$. The critical observation is that
+  [specific insight that makes this non-trivial].
+
+\item \textbf{Combining.} Choosing $\eta = 1/\sqrt{T}$ balances
+  the two terms, yielding the stated bound.
+\end{enumerate}
+
+The full proof, including the technical lemma for Step 2,
+appears in Appendix~\ref{app:proofs}.
+\end{proof}
+```
+
+**差的证明草图**：使用稍微不同的符号重述定理，或者仅仅说 "the proof follows standard techniques."
+
+### 附录中的完整证明
+
+```latex
+\appendix
+\section{Proofs}\label{app:proofs}
+
+\subsection{Proof of Theorem~\ref{thm:convergence}}
+
+We first establish two technical lemmas.
+
+\begin{lemma}[Descent Lemma]\label{lem:descent}
+Under Assumption~\ref{assum:smoothness}, for any step size $\eta \leq 1/L$:
+\[
+f(x_{t+1}) \leq f(x_t) - \frac{\eta}{2}\|\nabla f(x_t)\|^2 + \frac{\eta^2 L}{2}\|\nabla f(x_t)\|^2.
+\]
+\end{lemma}
+
+\begin{proof}
+[Complete proof with all steps]
+\end{proof}
+
+% Continue with remaining lemmas and main theorem proof
+```
+
+### 理论论文常见陷阱
+
+| 陷阱 | 问题 | 修复方法 |
+|---------|---------|-----|
+| 假设过强 | 使结果变得微不足道 | 讨论哪些假设是必要的；证明 lower bounds |
+| 未与现有边界比较 | 审稿人无法评估贡献 | 添加边界比较表 |
+| 证明草图仅仅是缩短的完整证明 | 无法传达洞见 | 专注于 1-2 个核心思想；将机械推导推迟到附录 |
+| 没有实验验证 | 审稿人会质疑其实际相关性 | 添加检验预测的合成实验 |
+| 符号不一致 | 让审稿人感到困惑 | 在 Preliminaries 中创建符号表 |
+| 在可以使用简单证明时使用过于复杂的证明 | 审稿人会怀疑有误 | 优先考虑清晰度而非通用性 |
+
+### 理论论文的目标会议
+
+| 会议 | 理论接收率 | 备注 |
+|-------|----------------------|-------|
+| **NeurIPS** | 中等 | 重视具有实际影响的理论 |
+| **ICML** | 高 | 强大的理论 track |
+| **ICLR** | 中等 | 偏好带有实验验证的理论 |
+| **COLT** | 高 | 专注理论的会议 |
+| **ALT** | 高 | 算法学习理论 |
+| **STOC/FOCS** | 针对具有 TCS 风格的结果 | 如果贡献主要是组合/算法方面的 |
+| **JMLR** | 高 | 无页数限制；适合冗长的证明 |
+
+---
+
+## 综述与教程论文
+
+### 何时撰写综述
+
+- 一个子领域已经成熟到值得进行综合梳理
+- 你发现了单篇论文中未指出的不同工作之间的联系
+- 该领域的新手没有一个好的切入点
+- 自上一次综述以来，领域格局发生了重大变化
+
+**警告**：综述需要真正的专业知识。非该领域专家撰写的综述，无论多么全面，都会遗漏细节并错误地描述相关工作。
+
+### 结构
+
+```
+1. Introduction (1-2 pages)
+   - Scope definition (what's included and excluded, and why)
+   - Motivation for the survey now
+   - Overview of organization (often with a figure)
+
+2. Background / Problem Formulation (1-2 pages)
+   - Formal problem definition
+   - Notation (used consistently throughout)
+   - Historical context
+
+3. Taxonomy (the core contribution)
+   - Organize methods along meaningful axes
+   - Present taxonomy as a figure or table
+   - Each category gets a subsection
+
+4. Detailed Coverage (bulk of paper)
+   - For each category: representative methods, key ideas, strengths/weaknesses
+   - Comparison tables within and across categories
+   - Don't just describe — analyze and compare
+
+5. Experimental Comparison (if applicable)
+   - Standardized benchmark comparison
+   - Fair hyperparameter tuning for all methods
+   - Not always feasible but significantly strengthens the survey
+
+6. Open Problems & Future Directions (1-2 pages)
+   - Unsolved problems the field should tackle
+   - Promising but underexplored directions
+   - This section is what makes a survey a genuine contribution
+
+7. Conclusion
+```
+
+### 分类体系设计
+
+分类体系是综述的核心学术贡献。它应该：
+
+- **有意义**：分类应对应真实的方法学差异，而不是任意的分组
+- **全面**：每篇相关的论文都应该能归入某一类
+- **互斥（理想情况下）**：每篇论文只属于一个主要类别
+- **名称具有信息量**："Attention-based methods" > "Category 3"
+- **可视化**：展示分类体系的图表几乎总是有帮助的
+
+**关于 "LLM Reasoning" 综述的分类维度示例：**
+- 按技术划分：chain-of-thought, tree-of-thought, self-consistency, tool use
+- 按训练需求划分：prompting-only, fine-tuned, RLHF
+- 按推理类型划分：数学、常识、逻辑、因果
+
+### 写作标准
+
+- **引用每一篇相关论文** —— 作者会检查他们的工作是否被包含在内
+- **公平公正** —— 不要因为你不喜欢就否定某些方法
+- **综合提炼，而不仅仅是列举** —— 识别模式、权衡和开放性问题
+- **包含比较表** —— 即使是定性的也可以（特征/属性检查表）
+- **在提交前更新** —— 检查 arXiv 上自你开始撰写以来发表的论文
+
+### 综述论文的目标会议
+
+| 会议 | 备注 |
+|-------|-------|
+| **TMLR** (Survey track) | 专门的综述投稿；无页数限制 |
+| **JMLR** | 长篇幅，备受推崇 |
+| **Foundations and Trends in ML** | 受邀，但可以主动提出 |
+| **ACM Computing Surveys** | 面向广泛的 CS 领域受众 |
+| **arXiv** (standalone) | 无同行评审，但如果写得好，曝光率很高 |
+| **Conference tutorials** | 在 NeurIPS/ICML/ACL 上作为教程展示；写成论文 |
+
+---
+
+## 基准与数据集论文
+
+### 何时撰写基准论文
+
+- 现有基准没有衡量你认为重要的内容
+- 出现了新能力，但没有标准的评估方式
+- 现有基准已经饱和（所有方法的得分都 >95%）
+- 你想在碎片化的子领域中标准化评估
+
+### 结构
+
+```
+1. Introduction
+   - What evaluation gap does this benchmark fill?
+   - Why existing benchmarks are insufficient
+
+2. Task Definition
+   - Formal task specification
+   - Input/output format
+   - Evaluation criteria (what makes a good answer?)
+
+3. Dataset Construction
+   - Data source and collection methodology
+   - Annotation process (if human-annotated)
+   - Quality control measures
+   - Dataset statistics (size, distribution, splits)
+
+4. Baseline Evaluation
+   - Run strong baselines (don't just report random/majority)
+   - Show the benchmark is challenging but not impossible
+   - Human performance baseline (if feasible)
+
+5. Analysis
+   - Error analysis on baselines
+   - What makes items hard/easy?
+   - Construct validity: does the benchmark measure what you claim?
+
+6. Intended Use & Limitations
+   - What should this benchmark be used for?
+   - What should it NOT be used for?
+   - Known biases or limitations
+
+7. Datasheet (Appendix)
+   - Full datasheet for datasets (Gebru et al.)
+```
+
+### 证据标准
+
+审稿人评估基准的标准不同于评估方法论文的标准：
+
+| 标准 | 审稿人检查的内容 |
+|-----------|---------------------|
+| **评估的新颖性** | 这是否衡量了现有基准没有衡量的内容？ |
+| **构建效度** | 基准是否真正衡量了所声称的能力？ |
+| **难度校准** | 既不能太简单（饱和）也不能太难（随机表现） |
+| **标注质量** | 一致性指标、标注员资质、标注指南 |
+| **文档说明** | 数据表、许可协议、维护计划 |
+| **可复现性** | 其他人能轻松使用这个基准吗？ |
+| **伦理考量** | 偏差分析、知情同意、敏感内容处理 |
+
+### 数据集文档（必需）
+
+遵循 Datasheets for Datasets 框架 (Gebru et al., 2021)：
+
+```
+Datasheet Questions:
+1. Motivation
+   - Why was this dataset created?
+   - Who created it and on behalf of whom?
+   - Who funded the creation?
+
+2. Composition
+   - What do the instances represent?
+   - How many instances are there?
+   - Does it contain all possible instances or a sample?
+   - Is there a label? If so, how was it determined?
+   - Are there recommended data splits?
+
+3. Collection Process
+   - How was the data collected?
+   - Who was involved in collection?
+   - Over what timeframe?
+   - Was ethical review conducted?
+
+4. Preprocessing
+   - What preprocessing was done?
+   - Was the "raw" data saved?
+
+5. Uses
+   - What tasks has this been used for?
+   - What should it NOT be used for?
+   - Are there other tasks it could be used for?
+
+6. Distribution
+   - How is it distributed?
+   - Under what license?
+   - Are there any restrictions?
+
+7. Maintenance
+   - Who maintains it?
+   - How can users contact the maintainer?
+   - Will it be updated? How?
+   - Is there an erratum?
+```
+
+### 基准论文的目标会议
+
+| 会议 | 备注 |
+|-------|-------|
+| **NeurIPS Datasets & Benchmarks** | 专门的 track；此类论文的最佳目标会议 |
+| **ACL** (Resource papers) | 专注于 NLP 的数据集 |
+| **LREC-COLING** | 语言资源 |
+| **TMLR** | 适合带有分析的基准论文 |
+
+---
+
+## 立场论文
+
+### 何时撰写立场论文
+
+- 你对领域应如何发展有明确的论点
+- 你想挑战一个被广泛接受的假设
+- 你想基于分析提出一个研究议程
+- 你发现了当前方法学中存在的系统性问题
+
+### 结构
+
+```
+1. Introduction
+   - State your thesis clearly in the first paragraph
+   - Why this matters now
+
+2. Background
+   - Current state of the field
+   - Prevailing assumptions you're challenging
+
+3. Argument
+   - Present your thesis with supporting evidence
+   - Evidence can be: empirical data, theoretical analysis, logical argument,
+     case studies, historical precedent
+   - Be rigorous — this isn't an opinion piece
+
+4. Counterarguments
+   - Engage seriously with the strongest objections
+   - Explain why they don't undermine your thesis
+   - Concede where appropriate — it strengthens credibility
+
+5. Implications
+   - What should the field do differently?
+   - Concrete research directions your thesis suggests
+   - How should evaluation/methodology change?
+
+6. Conclusion
+   - Restate thesis
+   - Call to action
+```
+
+### 写作标准
+
+- **以最强烈的论点开篇** —— 不要在第一段含糊其辞
+- **诚实地回应反面论点** —— 最好的立场论文探讨的是最强烈的反对意见，而不是最弱的
+- **提供证据** —— 没有证据的立场论文只是社论
+- **要具体** —— "the field should do X" 好于 "more work is needed"
+- **不要对现有工作进行稻草人谬误式的曲解** —— 公平地描述对立观点
+
+### 立场论文的目标会议
+
+| 会议 | 备注 |
+|-------|-------|
+| **ICML** (Position track) | 立场论文的专属 track |
+| **NeurIPS** (Workshop papers) | Workshop 通常欢迎立场文章 |
+| **ACL** (Theme papers) | 当你的立场与会议主题一致时 |
+| **TMLR** | 接收论证严密的立场论文 |
+| **CACM** | 面向更广泛的 CS 领域受众 |
+
+---
+
+## 可复现性与重复性论文
+
+### 何时撰写可复现性论文
+
+- 你尝试复现已发表的结果，并且取得了成功/失败
+- 你想在不同条件下验证某些声明
+- 你发现某个流行方法的性能依赖于未报告的细节
+
+### 结构
+
+```
+1. Introduction
+   - What paper/result are you reproducing?
+   - Why is this reproduction valuable?
+
+2. Original Claims
+   - State the exact claims from the original paper
+   - What evidence was provided?
+
+3. Methodology
+   - Your reproduction approach
+   - Differences from original (if any) and why
+   - What information was missing from the original paper?
+
+4. Results
+   - Side-by-side comparison with original results
+   - Statistical comparison (confidence intervals overlap?)
+   - What reproduced and what didn't?
+
+5. Analysis
+   - If results differ: why? What's sensitive?
+   - Hidden hyperparameters or implementation details?
+   - Robustness to seed, hardware, library versions?
+
+6. Recommendations
+   - For original authors: what should be clarified?
+   - For practitioners: what to watch out for?
+   - For the field: what reproducibility lessons emerge?
+```
+
+### 目标会议
+
+| 会议 | 备注 |
+|-------|-------|
+| **ML Reproducibility Challenge** | NeurIPS 的年度挑战赛 |
+| **ReScience** | 专门发表重复性研究的期刊 |
+| **TMLR** | 接收带有分析的复现论文 |
+| **Workshops** | 主要会议上的可复现性 Workshop |