feat: publish data engineering chapter

src/components/SiteHeader.astro

@@ -11,6 +11,7 @@ const items = [
   { id: "deepseek", href: "/deepseek/", label: "DeepSeek" },
   { id: "foundations", href: "/foundations/", label: "基础原理" },
   { id: "scaling", href: "/scaling/", label: "Scaling" },
+  { id: "data", href: "/pretraining/data/", label: "数据工程" },
   { id: "moe", href: "/moe/", label: "MoE" },
   { id: "long-context", href: "/long-context/", label: "长上下文" },
   { id: "reasoning", href: "/reasoning/", label: "推理" },

src/data/chapters.ts

@@ -86,12 +86,12 @@ export const chapters: Chapter[] = [
     title: "数据工程与预训练配方",
     kicker: "DATA",
     question: "更多网页为什么不等于更好的模型？",
-    summary: "追踪采集、过滤、去重、混合、课程、合成数据与污染控制，并明确公开报告的知识边界。",
-    status: "queued",
-    progress: 8,
-    papers: 14,
+    summary: "用十二张账追踪采集、解析、过滤、去重、混合、改写、Tokenizer、Packing、课程与污染，并串起 DeepSeek / Kimi 数据谱系。",
+    status: "published",
+    progress: 73,
+    papers: 31,
     prerequisites: ["01", "04"],
-    highlights: ["数据质量", "混合策略", "污染"],
+    highlights: ["十二张账", "DeepSeek/Kimi 谱系", "四联实验"],
   },
   {
     number: "06",

src/data/papers.ts

@@ -4,6 +4,7 @@ export type PaperTopic =
   | "长上下文"
   | "MoE"
   | "Scaling"
+  | "数据"
   | "训练系统"
   | "低精度"
   | "后训练"
@@ -123,8 +124,8 @@ export const papers: Paper[] = [
     year: 2019,
     title: "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer",
     url: "https://arxiv.org/abs/1910.10683",
-    topics: ["Transformer", "Scaling"],
-    contribution: "T5 统一 text-to-text 接口并系统研究架构与数据。",
+    topics: ["Transformer", "Scaling", "数据"],
+    contribution: "T5 统一 text-to-text 接口，并以 C4 建立现代 Common Crawl 清洗基线。",
     verified: true,
   },
   {
@@ -397,7 +398,7 @@ export const papers: Paper[] = [
     year: 2021,
     title: "GLaM: Efficient Scaling of Language Models with Mixture-of-Experts",
     url: "https://arxiv.org/abs/2112.06905",
-    topics: ["MoE", "Scaling"],
+    topics: ["MoE", "Scaling", "数据"],
     contribution: "展示 MoE 在能耗与推理计算上高效扩展语言模型。",
     verified: true,
   },
@@ -446,8 +447,8 @@ export const papers: Paper[] = [
     year: 2024,
     title: "DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model",
     url: "https://arxiv.org/abs/2405.04434",
-    topics: ["MoE", "长上下文", "训练系统"],
-    contribution: "联合 DeepSeekMoE 与 MLA，直接压缩推理 KV Cache。",
+    topics: ["MoE", "长上下文", "数据", "训练系统"],
+    contribution: "联合 DeepSeekMoE 与 MLA，并披露 8.1T 中英数据、过滤取舍和训练配方。",
     spotlight: "DeepSeek",
     verified: true,
   },
@@ -472,7 +473,7 @@ export const papers: Paper[] = [
     year: 2024,
     title: "DeepSeek-V3 Technical Report",
     url: "https://arxiv.org/abs/2412.19437",
-    topics: ["MoE", "Scaling", "训练系统", "低精度"],
+    topics: ["MoE", "Scaling", "数据", "训练系统", "低精度"],
     contribution: "671B-A37B；FP8、MTP、无辅助损失平衡与 DualPipe。",
     spotlight: "DeepSeek",
     verified: true,
@@ -545,8 +546,8 @@ export const papers: Paper[] = [
     year: 2024,
     title: "DeepSeek LLM: Scaling Open-Source Language Models with Longtermism",
     url: "https://arxiv.org/abs/2401.02954",
-    topics: ["Scaling"],
-    contribution: "中英 dense 基线与公开 scaling-law 研究。",
+    topics: ["Scaling", "数据"],
+    contribution: "中英 dense 基线、跨 91 个 Common Crawl dump 去重与公开 scaling-law 研究。",
     spotlight: "DeepSeek",
     verified: true,
   },
@@ -554,7 +555,7 @@ export const papers: Paper[] = [
     year: 2021,
     title: "The Pile: An 800GB Dataset of Diverse Text for Language Modeling",
     url: "https://arxiv.org/abs/2101.00027",
-    topics: ["Scaling"],
+    topics: ["Scaling", "数据"],
     contribution: "公开多域预训练语料与数据配比研究基础。",
     verified: true,
   },
@@ -562,7 +563,7 @@ export const papers: Paper[] = [
     year: 2023,
     title: "The RefinedWeb Dataset for Falcon LLM",
     url: "https://arxiv.org/abs/2306.01116",
-    topics: ["Scaling"],
+    topics: ["Scaling", "数据"],
     contribution: "证明高质量过滤与去重的 Web 数据可以支撑强模型。",
     verified: true,
   },
@@ -570,10 +571,170 @@ export const papers: Paper[] = [
     year: 2024,
     title: "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research",
     url: "https://arxiv.org/abs/2402.00159",
-    topics: ["Scaling"],
+    topics: ["Scaling", "数据"],
     contribution: "开放 3T Token 语料与完整数据处理工具。",
     verified: true,
   },
+  {
+    year: 2019,
+    title: "CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data",
+    url: "https://arxiv.org/abs/1911.00359",
+    topics: ["数据"],
+    contribution: "把去重、语言识别和 Wikipedia-like 质量过滤组织成可扩展网页语料流水线。",
+    verified: true,
+  },
+  {
+    year: 2020,
+    title: "Extracting Training Data from Large Language Models",
+    url: "https://arxiv.org/abs/2012.07805",
+    topics: ["数据", "评测"],
+    contribution: "从 GPT-2 抽取逐字训练片段与 PII，实证训练记忆和隐私泄露风险。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "Deduplicating Training Data Makes Language Models Better",
+    url: "https://arxiv.org/abs/2107.06499",
+    topics: ["数据", "评测"],
+    contribution: "连接近重复、验证集重合、训练效率与逐字记忆，建立现代 fuzzy dedup 主线。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "ROOTS: One Massive Multilingual Dataset for 1.6TB of Text",
+    url: "https://arxiv.org/abs/2303.03915",
+    topics: ["数据"],
+    contribution: "总结 59 种语言、1.6TB 多语言语料的协作建设、治理与数据文档。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Efficient Training of Language Models to Fill in the Middle",
+    url: "https://arxiv.org/abs/2207.14255",
+    topics: ["数据"],
+    contribution: "通过 PSM/SPM 数据重排获得代码中间补全能力，并消融变换率和格式。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining",
+    url: "https://arxiv.org/abs/2305.10429",
+    topics: ["数据", "Scaling"],
+    contribution: "用小代理模型学习 domain weights，再迁移到更大目标模型。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "SemDeDup: Data-efficient Learning at Web-scale through Semantic Deduplication",
+    url: "https://arxiv.org/abs/2303.09540",
+    topics: ["数据"],
+    contribution: "在预训练 embedding 空间聚类语义近重复，研究硬删除与多样性收益。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "D4: Improving LLM Pretraining via Document De-Duplication and Diversification",
+    url: "https://arxiv.org/abs/2308.12284",
+    topics: ["数据"],
+    contribution: "先去重再主动保留多样性，说明智能重复与随机重复并不等价。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "PALOMA: A Benchmark for Evaluating Language Model Fit",
+    url: "https://arxiv.org/abs/2312.10523",
+    topics: ["数据", "评测"],
+    contribution: "提出固定训练顺序、子文档去污染、细粒度 domain 和 bits-per-byte 语料评测协议。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale",
+    url: "https://arxiv.org/abs/2406.17557",
+    topics: ["数据"],
+    contribution: "以大规模网页清洗消融构建 FineWeb 与教育价值子集。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "DataComp-LM: In Search of the Next Generation of Language Model Pretraining Datasets",
+    url: "https://arxiv.org/abs/2406.11794",
+    topics: ["数据", "Scaling", "评测"],
+    contribution: "固定 240T candidate pool、模型尺度与 53 项评测，使数据 pipeline 可以同协议比较。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling",
+    url: "https://arxiv.org/abs/2401.16380",
+    topics: ["数据"],
+    contribution: "WRAP 用受控改写增加网页语料的表达覆盖，并研究 Token utility。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Fewer Truncations Improve Language Modeling",
+    url: "https://arxiv.org/abs/2404.10830",
+    topics: ["数据", "训练系统"],
+    contribution: "Best-fit packing 减少长文档截断，在固定序列长度下保护文档完整性。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "SoftDedup: Efficient Data Reweighting at Scale",
+    url: "https://arxiv.org/abs/2407.06654",
+    topics: ["数据"],
+    contribution: "按常见 n-gram 频率降低样本权重，探索比硬删除更连续的去重策略。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "MATES: Model-Aware Data Selection for Efficient Language Model Pretraining",
+    url: "https://arxiv.org/abs/2406.06046",
+    topics: ["数据", "Scaling"],
+    contribution: "以当前模型状态动态估计样本对目标验证分布的影响。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Investigating Data Contamination in Modern Benchmarks for Large Language Models",
+    url: "https://arxiv.org/abs/2401.06059",
+    topics: ["数据", "评测"],
+    contribution: "区分 text contamination 与 ground-truth contamination，并检查 n-gram 检测的边界。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training",
+    url: "https://arxiv.org/abs/2403.09611",
+    topics: ["数据", "多模态"],
+    contribution: "系统消融 caption、interleaved image-text、text-only mixture 与视觉组件。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "JEST: Joint Example Selection for Multimodal Learning",
+    url: "https://arxiv.org/abs/2406.17711",
+    topics: ["数据", "多模态"],
+    contribution: "按 batch 的联合可学习性选择多模态样本，研究动态数据价值。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Group-MATES: Data-Efficient Pretraining with Group-Level Data Influence Modeling",
+    url: "https://arxiv.org/abs/2502.14709",
+    topics: ["数据", "Scaling"],
+    contribution: "把模型感知的数据影响估计扩展到 group-level 选择。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Swallow: Continued Pre-training with Synthetic Data for Efficient Language Model Adaptation",
+    url: "https://arxiv.org/abs/2505.02881",
+    topics: ["数据", "后训练"],
+    contribution: "用 SwallowCode 与 SwallowMath 研究受控合成数据的继续预训练收益与边界。",
+    verified: true,
+  },
   {
     year: 2017,
     title: "Deep Learning Scaling is Predictable, Empirically",
@@ -1157,8 +1318,8 @@ export const papers: Paper[] = [
     year: 2024,
     title: "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models",
     url: "https://arxiv.org/abs/2402.03300",
-    topics: ["推理", "后训练"],
-    contribution: "数学数据管线与无独立 critic 的 GRPO。",
+    topics: ["数据", "推理", "后训练"],
+    contribution: "从 40B HTML pages 发现 120.2B 数学语料，并提出无独立 critic 的 GRPO。",
     spotlight: "DeepSeek",
     verified: true,
   },
@@ -1344,8 +1505,8 @@ export const papers: Paper[] = [
     year: 2025,
     title: "Kimi K2: Open Agentic Intelligence",
     url: "https://arxiv.org/abs/2507.20534",
-    topics: ["MoE", "训练系统", "Agent", "后训练", "推理"],
-    contribution: "开放 1T MoE Agent 模型，以 verifiable gym 与 self-critique rubric 做 joint RL。",
+    topics: ["MoE", "数据", "训练系统", "Agent", "后训练", "推理"],
+    contribution: "开放 1T MoE Agent 模型，以 15.5T、知识/数学改写与 verifiable gym / self-critique joint RL 协同。",
     spotlight: "Kimi",
     verified: true,
   },
@@ -1353,7 +1514,7 @@ export const papers: Paper[] = [
     year: 2026,
     title: "Kimi K2.5: Visual Agentic Intelligence",
     url: "https://arxiv.org/abs/2602.02276",
-    topics: ["训练系统", "Agent", "多模态", "推理"],
+    topics: ["数据", "训练系统", "Agent", "多模态", "推理"],
     contribution: "把视觉、工具使用和并行 Agent Swarm 纳入统一后训练。",
     spotlight: "Kimi",
     verified: true,
@@ -1484,8 +1645,8 @@ export const papers: Paper[] = [
     year: 2026,
     title: "DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence",
     url: "https://arxiv.org/abs/2606.19348",
-    topics: ["长上下文", "MoE", "训练系统", "推理"],
-    contribution: "CSA/HCA 混合注意力、mHC、Muon 与 1M 上下文双模型。",
+    topics: ["长上下文", "MoE", "数据", "训练系统", "推理"],
+    contribution: "32/33T 长文与 agentic 数据、CSA/HCA、mHC、Muon 和 1M 上下文双模型。",
     spotlight: "DeepSeek",
     verified: true,
   },
@@ -1493,8 +1654,8 @@ export const papers: Paper[] = [
     year: 2026,
     title: "Kimi K3: Open Frontier Intelligence",
     url: "https://arxiv.org/abs/2607.24653",
-    topics: ["长上下文", "MoE", "训练系统", "低精度", "推理", "Agent", "多模态", "评测"],
-    contribution: "2.8T-A104B、KDA/MLA、AttnRes、Stable LatentMoE 与 1M Agentic RL。",
+    topics: ["长上下文", "MoE", "数据", "训练系统", "低精度", "推理", "Agent", "多模态", "评测"],
+    contribution: "四文本域与视觉语料、2.8T-A104B、KDA/MLA、Stable LatentMoE 与 1M Agentic RL。",
     spotlight: "Kimi",
     verified: true,
   },
@@ -1506,6 +1667,7 @@ export const paperTopics: PaperTopic[] = [
   "长上下文",
   "MoE",
   "Scaling",
+  "数据",
   "训练系统",
   "低精度",
   "后训练",

src/pages/index.astro

@@ -8,6 +8,7 @@ const routes: Record<string, string> = {
   roadmap: "/roadmap/",
   foundations: "/foundations/",
   scaling: "/scaling/",
+  "pretraining/data": "/pretraining/data/",
   moe: "/moe/",
   "long-context": "/long-context/",
   reasoning: "/reasoning/",
@@ -80,6 +81,7 @@ const paths = [
           <a class="button" href="/k3/">直接解剖 K3</a>
           <a class="button" href="/deepseek/">DeepSeek 专题</a>
           <a class="button" href="/scaling/">Scaling Laws 专题</a>
+          <a class="button" href="/pretraining/data/">数据工程专题</a>
           <a class="button" href="/moe/">MoE 专题</a>
           <a class="button" href="/long-context/">长上下文专题</a>
           <a class="button" href="/reasoning/">推理专题</a>
@@ -93,20 +95,36 @@ const paths = [
         <div class="hero-stats">
           <div><b>16</b><span>核心专题</span></div>
           <div><b>151</b><span>K3 报告来源</span></div>
-          <div><b>182</b><span>关键论文索引</span></div>
+          <div><b>202</b><span>关键论文索引</span></div>
           <div><b>47p</b><span>K3 技术报告</span></div>
         </div>
       </aside>
     </div>
     <div class="scope-strip">
       <span>研究范围</span>
-      <p>表示学习 · Transformer · Scaling · MoE · 长上下文 · 训练系统 · 后训练 · 推理 · Agent · 多模态 · 服务与评测</p>
+      <p>表示学习 · Transformer · Scaling · 数据工程 · MoE · 长上下文 · 训练系统 · 后训练 · 推理 · Agent · 多模态 · 服务与评测</p>
       <a href="/progress/">查看实时进度 →</a>
     </div>
   </section>
 
   <section class="section compact release-section" id="new-chapters">
     <div class="release-grid">
+      <a class="release-card data-release" href="/pretraining/data/">
+        <div>
+          <p class="eyebrow"><span>NEW / CHAPTER 05</span> DATA & PRE-TRAINING</p>
+          <h2>同样一万亿 Token，可以是完全不同的训练经历</h2>
+          <p>
+            用来源、解析、质量、唯一性、污染、混合、变换、Tokenizer、Packing、课程与模型感知价值十二张账，
+            从 C4、Pile、DoReMi 和 DCLM 一路走到 DeepSeek 五代数据工程与 Kimi K2→K3 原生多模态。
+          </p>
+        </div>
+        <dl>
+          <div><dt>LINEAGE</dt><dd>2019 → 2026</dd></div>
+          <div><dt>PAPERS</dt><dd>31 个一手节点</dd></div>
+          <div><dt>LAB</dt><dd>流水线 · 去重 · 混合 · 改写</dd></div>
+        </dl>
+        <span class="release-arrow" aria-hidden="true">进入数据工程专题 →</span>
+      </a>
       <a class="release-card scaling-release" href="/scaling/">
         <div>
           <p class="eyebrow"><span>NEW / CHAPTER 04</span> SCALING LAWS</p>
@@ -420,6 +438,7 @@ const paths = [
       transition: transform 180ms ease, border-color 180ms ease;
     }
 
+    .data-release,
     .scaling-release,
     .training-release,
     .reasoning-release {
@@ -427,6 +446,13 @@ const paths = [
       min-height: 510px;
     }
 
+    .data-release {
+      background:
+        radial-gradient(circle at 82% 18%, rgba(76, 118, 112, 0.2), transparent 30%),
+        repeating-linear-gradient(0deg, transparent 0 46px, rgba(76, 118, 112, 0.045) 46px 47px),
+        var(--paper-raised);
+    }
+
     .scaling-release {
       background:
         radial-gradient(circle at 82% 18%, rgba(159, 91, 52, 0.18), transparent 30%),
@@ -510,6 +536,7 @@ const paths = [
         padding-bottom: 76px;
       }
 
+      .data-release,
       .scaling-release,
       .training-release,
       .reasoning-release {

src/pages/moe/index.astro

@@ -683,7 +683,7 @@ const paperChain = [
         <div class="next-links">
           <a class="button primary" href="/k3/#moe">回到 K3：在整机架构中定位 Stable LatentMoE →</a>
           <a class="button" href="/deepseek/">DeepSeek 完整论文谱系</a>
-          <a class="button" href="/papers/">搜索全部 182 篇论文</a>
+          <a class="button" href="/papers/">搜索全部 202 篇论文</a>
         </div>
       </section>
     </article>

src/pages/progress/index.astro

@@ -12,6 +12,7 @@ const workstreams = [
   { label: "Kimi K3 深读", value: 66, next: "扩写 pre-training / infra 逐图笔记" },
   { label: "Transformer 基础", value: 52, next: "加入矩阵形状动画与手算练习" },
   { label: "Scaling Laws", value: 74, next: "加入真实拟合复现、置信区间与更多模型族对照" },
+  { label: "数据工程与预训练配方", value: 73, next: "逐图精读 FineWeb / DCLM，加入真实去重与 mixture traces" },
   { label: "DeepSeek 专题", value: 71, next: "补 R1 / DAPO 的逐图训练轨迹与复现对照" },
   { label: "推理与测试时扩展", value: 76, next: "真实模型采样曲线、PRM 案例与逐篇图表精读" },
   { label: "稀疏计算与 MoE", value: 74, next: "补充真实集群 traces 与专家特化案例" },
@@ -41,7 +42,7 @@ const workstreams = [
         <div><dt>OVERALL</dt><dd>专题平均 {average}%</dd></div>
         <div><dt>READABLE</dt><dd>{published} 个首版可读专题</dd></div>
         <div><dt>ACTIVE</dt><dd>{researching} 个研究/写作中</dd></div>
-        <div><dt>UPDATED</dt><dd>2026-07-29 02:08 CST</dd></div>
+        <div><dt>UPDATED</dt><dd>2026-07-29 03:01 CST</dd></div>
         <div><dt>MODE</dt><dd>持续迭代，不锁死版本</dd></div>
       </dl>
     </div>
@@ -51,7 +52,7 @@ const workstreams = [
     <div class="section-heading">
       <div>
         <p class="eyebrow"><span>01</span> WORKSTREAMS</p>
-        <h2>十二条工作流同时推进，但不混淆“有页面”和“已核验”</h2>
+        <h2>十三条工作流同时推进，但不混淆“有页面”和“已核验”</h2>
       </div>
       <p class="section-lead">
         内容首版优先打通全局脉络；随后每轮迭代选择一个专题推进到论文/工程层，并做独立事实复核。
@@ -88,14 +89,15 @@ const workstreams = [
       <article><span>✓</span><h3>K3 报告已结构化拆解</h3><p>47 页报告目录、151 条参考来源和架构/后训练/系统主线已经提取。</p></article>
       <article><span>✓</span><h3>16 专题知识图</h3><p>从语言模型基础到评测安全，包含先修依赖和三条贯穿案例。</p></article>
       <article><span>✓</span><h3>编辑式网站系统</h3><p>响应式导航、章节模板、侧栏、进度、论文链和证据提示组件。</p></article>
-      <article><span>✓</span><h3>十六个原创交互视图</h3><p>K3、注意力、DeepSeek、长上下文、MoE、推理三页签，以及训练系统与 Scaling 各四页签实验。</p></article>
-      <article><span>✓</span><h3>八篇首版长文</h3><p>K3 导读、Transformer 基础、DeepSeek 谱系、Scaling、长上下文、MoE、推理与训练系统专题。</p></article>
+      <article><span>✓</span><h3>二十个原创交互视图</h3><p>K3、注意力、DeepSeek、长上下文、MoE、推理，以及训练系统、Scaling 与数据工程的多页签实验。</p></article>
+      <article><span>✓</span><h3>九篇首版长文</h3><p>K3、Transformer、DeepSeek、Scaling、数据工程、长上下文、MoE、推理与训练系统专题。</p></article>
       <article><span>✓</span><h3>Scaling Laws 深度专题</h3><p>九张账、29 个一手节点、DeepSeek/Kimi 双谱系与曲面—部署—复用—涌现四联实验。</p></article>
+      <article><span>✓</span><h3>数据工程深度专题</h3><p>十二张账、31 个一手节点、DeepSeek/Kimi 双谱系与流水线—去重—混合—改写四联实验。</p></article>
       <article><span>✓</span><h3>长上下文深度专题</h3><p>五张成本账、26 篇一手论文、10+ 机制图与 8 策略交互实验室。</p></article>
       <article><span>✓</span><h3>MoE 深度专题</h3><p>六张账、19 篇一手论文、DeepSeek/K3 主线与路由—容量—通信交互实验室。</p></article>
       <article><span>✓</span><h3>推理深度专题</h3><p>八张账、30 篇一手论文链、DeepSeek/Kimi 双主线与三页签互动实验室。</p></article>
       <article><span>✓</span><h3>训练系统深度专题</h3><p>九张账、37 个一手节点、DeepSeek/Kimi 双谱系与显存—网格—气泡—通信实验室。</p></article>
-      <article><span>✓</span><h3>182 篇关键论文索引</h3><p>覆盖 12 个专题，支持全文搜索、标签筛选与 Kimi/DeepSeek 聚光主线。</p></article>
+      <article><span>✓</span><h3>202 篇关键论文索引</h3><p>新增数据专题标签和 20 个一手节点，继续支持全文搜索与 Kimi/DeepSeek 聚光主线。</p></article>
       <article><span>✓</span><h3>公开仓库与自托管发布</h3><p>源码公开到 git.k1412.top，网站由不可变镜像、Compose Manager 与 HTTPS 交付。</p></article>
     </div>
   </section>
@@ -111,6 +113,7 @@ const workstreams = [
     <div class="queue-table">
       <div class="head"><b>优先级</b><b>专题</b><b>本轮交付</b><b>完成闸门</b></div>
       <div><span>P0</span><strong>Scaling Laws 二轮</strong><p>真实拟合复现 → 置信区间 → 更多模型族与下游任务外推</p><em>可复现实验 + 逐图笔记</em></div>
+      <div><span>P1</span><strong>数据工程二轮</strong><p>FineWeb / DCLM 逐图 → 真实去重误伤 → mixture traces 与污染案例</p><em>逐图笔记 + 案例库</em></div>
       <div><span>P1</span><strong>大规模训练系统二轮</strong><p>真实集群 traces → 故障恢复 → 精确 topology / kernel 配置</p><em>案例库 + 实测边界</em></div>
       <div><span>P1</span><strong>长上下文二轮深化</strong><p>真实模型配置 → 内核细节 → 长上下文评测与失败案例</p><em>配置比较器 + 逐图论文笔记</em></div>
       <div><span>P1</span><strong>MoE 二轮深化</strong><p>真实负载 traces → 专家特化可解释性 → 共享专家语义</p><em>案例库 + 集群证据</em></div>
@@ -157,6 +160,8 @@ const workstreams = [
       <div><time>2026-07-29</time><b>推理按八张账组织</b><p>把答案、覆盖、选择、过程、预算、优化、分布与系统证据分开核算。</p></div>
       <div><time>2026-07-29</time><b>训练系统按九张账组织</b><p>把模型状态、激活、并行、气泡、通信、专家、上下文、数值与可靠性分开核算。</p></div>
       <div><time>2026-07-29</time><b>Scaling Laws 按九张账组织</b><p>把观测量、模型、数据、算术、配比、配方、外推、经济目标与能力阶段分开核算。</p></div>
+      <div><time>2026-07-29</time><b>数据工程按十二张账组织</b><p>把来源、解析、语言、质量、唯一性、污染、混合、变换、Tokenizer、Packing、课程与价值分开核算。</p></div>
+      <div><time>2026-07-29</time><b>Grok 数据线索与正式账本永久分离</b><p>1264 行正式研究账本只接受回查一手来源后的结论；203 行 Grok 产物保留为未核验发现队列。</p></div>
     </div>
   </section>
 

src/pages/reasoning/index.astro

@@ -699,7 +699,7 @@ const paperChain = [
         <h2>不要按模型榜单读，按“旧方法留下了哪堵墙”读</h2>
         <p>
           下面 30 篇构成本专题首版主干。课程中的机制、公式与数字优先回到这些一手来源；
-          更完整的 182 篇跨专题索引位于论文库。
+          更完整的 202 篇跨专题索引位于论文库。
         </p>
         <div class="paper-chain">
           {paperChain.map(([year, title, href, note], index) => (