nsfc-literature

NSFC Application Literature Search and Citation Generation

Requirements for Literature in the Application

References approximately30 entries, mainly from the past 5 years
Authoritative journals such as CNS are prioritized
Mainly international literature + supplemented by domestic literature + your own work (can be highlighted)
Do not omit key literature in the field (reviewers will notice)
The format must be uniform and standardized
Literature from the current year earns bonus points
Do not omit key references

Literature Search

OpenAlex API (free, no API key required)

Script：scripts/search_literature.py

Basic Usage：

# 搜索关键词，按引用数排序
uv run scripts/search_literature.py "machine learning potential" --limit 20 --sort cited_by_count

# 搜索近3年的文献
uv run scripts/search_literature.py "deep learning molecular dynamics" --year-from 2023

# 按发表日期排序（找最新文献）
uv run scripts/search_literature.py "neural network force field" --sort publication_date

# 紧凑输出（每篇一行）
uv run scripts/search_literature.py "density functional theory" --compact

Returned Information: title, authors, journal, year, DOI, citation count, abstract

Search Strategy Suggestions：

First use broad keywords to search and understand the overall landscape of the field
Then use precise keywords to search for specific directions
Pay attention to highly cited papers (field classics) and the latest papers (frontier developments)
Check whether the work of leading experts in the field has been omitted
When searching with Chinese keywords, English substitutes may be needed

Citation Generation

wenxian

wenxian is an academic citation generation tool that supports generating standard citation formats from identifiers such as DOI, PMID, arXiv ID, etc.

Script：scripts/generate_references.py

Usage：

# 从DOI列表文件生成BibTeX引用
uv run scripts/generate_references.py refs.txt --format bibtex

# 生成纯文本引用
uv run scripts/generate_references.py refs.txt --format text

# 输出到文件
uv run scripts/generate_references.py refs.txt --format bibtex --output refs.bib

refs.txt format(one identifier per line):

10.1103/PhysRevLett.120.143001
10.1038/s41586-020-2242-8
arXiv:2304.09423

NSFC Citation Format

NSFC applications usually usenumbered citation format [1], [2], ...

Format Example：

[1] 作者1, 作者2, 等. 标题. 期刊, 卷(期): 起始页-结束页, 年份.
[2] Author1, Author2, et al. Title. Journal, Volume(Issue): Pages, Year.

Note：

All literature formats must be uniform (name order, journal abbreviations, etc.)
It is recommended to manually enter into the funding agency's achievement system to maintain format consistency
Your own literature can beboldedor highlighted in other ways

Complete Workflow

1. 确定研究方向和关键词
        ↓
2. 用 search_literature.py 搜索相关文献
        ↓
3. 筛选 ~30 条最相关的文献
   - 高引经典 + 近年前沿 + 自己的工作
        ↓
4. 收集所有 DOI，写入 refs.txt
        ↓
5. 用 generate_references.py 生成标准引用
        ↓
6. 检查格式统一性
        ↓
7. 确认没有遗漏关键文献

Frequently Asked Questions

Can't find the literature?

Try different keyword combinations
Use English keywords
Check spelling
OpenAlex has broad coverage but is not 100%, so Google Scholar can be used as a supplement

wenxian reports an error?

Confirm that uvx is installed (uv part of)
Confirm that the DOI format is correct (e.g., 10.1038/s41586-020-2242-8）
Some APIs may require a network proxy; please configure according to your local environment

Inconsistent format?

Use the same tool to generate all citations
Manually check and unify name order and journal abbreviations
It is recommended to do a final unified proofreading pass