draft-survey

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Draft Survey

调研草稿

Two deliverables from one topic: a ranked reading list (what to read, best first, with a one-line why) and a two-column, arXiv-ready survey draft that synthesizes the area in original prose with verified citations. Composes

find-papers

verify-citations

study-exemplars

, and

draft-related-work

从一个主题生成两个交付成果：一份排名阅读列表（包含应该阅读的内容、优先推荐的论文及一行推荐理由），以及一份符合arXiv规范的双栏调研草稿，该草稿以原创文字结合已验证的引用对该领域进行综述。整合了

find-papers

、

verify-citations

、

study-exemplars

和

draft-related-work

这些Skill。

When to use vs. literature-review

与literature-review的使用场景区别

```
literature-review
```
builds the related-work for your own paper — scoped to your contribution.
```
draft-survey
```
produces a standalone survey/review document (a reading list + a publishable 2-column draft) of a whole area. Use it to learn a field fast or to draft a survey paper for arXiv.

```
literature-review
```
用于构建你自己论文的相关工作部分——范围聚焦于你的研究贡献。
```
draft-survey
```
生成一份独立的调研/综述文档（阅读列表 + 可发表的双栏草稿），覆盖整个领域。可用于快速了解某个领域，或为arXiv撰写调研论文草稿。

Inputs

输入

The topic (e.g. "geospatial data conflation"), optionally a sub-scope and a target length (default 5–6 two-column pages).
Optional: a venue/format (default: generic two-column
```
article
```
, which compiles on arXiv).

主题（例如“地理空间数据融合”），可选子范围和目标长度（默认5–6页双栏）。
可选：会议/期刊格式（默认：通用双栏
```
article
```
格式，可在arXiv上编译）。

Process

流程

Gather candidates broadly. Run
```
find-papers
```
across DBLP + Crossref + Semantic Scholar + arXiv for the topic and its synonyms; then run its citation-graph expansion so seminal anchors and direct lineages are not missed (a survey that omits the foundational papers is a weak survey).
Rank them. Run
```
python3 scripts/rank_papers.py candidates.json
```
— a composite of normalized citation count, venue tier, recency, and citation-graph centrality (weights documented in references/ranking-criteria.md). Output the ranked reading list: rank, title, authors, year, venue, a citation/impact signal, and a one-line why read this (seminal / survey / SOTA / dataset / contrarian). Keep seminal and recent both represented.
Verify every entry. Route the list through
```
verify-citations
```
so each has a real DOI/arXiv id; drop or flag anything unresolved. A survey with a fabricated reference is disqualifying.
Build a taxonomy. Cluster the verified papers into 3–6 themes/sub-problems (the survey's section structure), each with its lineage (foundational → recent).
Draft the survey, in original prose. Write a two-column
```
.tex
```
: abstract, introduction (scope + why a survey now), one section per theme (synthesize and contrast methods — never copy source sentences), a cross-cutting comparison (a table helps), open problems / future directions, conclusion, and
```
\bibliography
```
. Every claim cites a verified paper. Target the requested length.
Make it arXiv-ready. Ensure it compiles (
```
latexmk
```
), uses a portable two-column class, and the
```
.bib
```
is clean. arXiv has no peer-review desk-reject, but it expects a compilable source and a real abstract;
```
preflight-check
```
can sanity-check length/structure.

广泛收集候选论文：针对主题及其同义词，在DBLP + Crossref + Semantic Scholar + arXiv中运行
```
find-papers
```
；然后运行其引用图扩展功能，确保不会遗漏开创性的核心论文和直接研究脉络（遗漏基础论文的调研是不合格的）。
对论文进行排名：运行
```
python3 scripts/rank_papers.py candidates.json
```
——综合标准化引用量、期刊/会议层级、时效性和引用图中心性（权重记录在references/ranking-criteria.md中）。输出排名阅读列表：排名、标题、作者、年份、期刊/会议、引用/影响力指标，以及一行“为何阅读该论文”的说明（开创性/调研/当前最优/数据集/相反观点）。同时兼顾开创性和近期的论文。
验证每一项条目：将列表传入
```
verify-citations
```
，确保每篇论文都有真实的DOI/arXiv编号；剔除或标记无法验证的条目。包含伪造参考文献的调研会被直接否决。
构建分类体系：将已验证的论文聚类为3–6个主题/子问题（作为调研的章节结构），每个主题都包含其研究脉络（基础→近期）。
以原创文字撰写调研草稿：撰写双栏
```
.tex
```
文档：摘要、引言（范围+为何现在需要该调研）、每个主题对应一个章节（综述并对比方法——绝不复制源文本句子）、跨主题对比（表格辅助）、开放问题/未来方向、结论，以及
```
\bibliography
```
。每个论点都引用已验证的论文。符合要求的长度。
确保符合arXiv规范：确保文档可编译（使用
```
latexmk
```
），采用可移植的双栏类，且
```
.bib
```
文件格式规范。arXiv没有同行评审的初审拒绝，但要求可编译的源文件和真实的摘要；
```
preflight-check
```
可以对长度/结构进行合理性检查。

Output

输出

```
reading-list.md
```
— the ranked, verified, annotated reading list.
```
survey.tex
```
+
```
refs.bib
```
— the two-column, arXiv-ready draft (original prose, verified citations).
Both written to
```
paper-workspace/research/
```
or a path the user names.

```
reading-list.md
```
——经过排名、验证并带有注释的阅读列表。
```
survey.tex
```
+
```
refs.bib
```
——符合arXiv规范的双栏草稿（原创文字，已验证引用）。
两者均保存至
```
paper-workspace/research/
```
或用户指定的路径。

Guardrails

约束规则

Real citations only. Every reference is resolved via
```
verify-citations
```
; never invent a paper, DOI, author, or year to fill a gap.
Original synthesis, not copying. Summarize and contrast in your own words; do not paste sentences from abstracts or papers. No paper content is bundled (fetch on demand, process transiently).
No completeness theater. State the search scope and that a survey is never exhaustive; flag themes where coverage is thin rather than padding.
Copilot, not pilot: the author reviews the reading list and the draft, and is the author of any submission.

仅使用真实引用：每篇参考文献都通过
```
verify-citations
```
验证；绝不编造论文、DOI、作者或年份来填补空白。
原创综述，而非复制：用自己的话总结和对比；不要粘贴摘要或论文中的句子。不捆绑论文内容（按需获取，临时处理）。
不做虚假的完整性宣称：说明搜索范围，明确调研不可能穷尽所有内容；对于覆盖不足的主题进行标记，而非填充无关内容。
是助手，而非主导者：用户负责审阅阅读列表和草稿，是任何提交内容的作者。

Source verification

来源验证

Citation impact and venue facts come from live scholarly APIs, not memory, and each cited paper carries a resolvable identifier the user can open.

引用影响力和期刊/会议信息来自实时学术API，而非记忆；每篇被引用的论文都带有用户可打开的可解析标识符。

Memory

记忆功能

Uses

.paper-memory/

as described by

paper-memory-convention.md

: read prior reading lists/lessons for the topic at start; append the topic, the chosen taxonomy, and any coverage gaps at end (deduped).

按照

paper-memory-convention.md

的描述使用

.paper-memory/

：在开始时读取该主题的过往阅读列表/经验；结束时追加该主题、所选分类体系以及任何覆盖不足的内容（去重）。