systematic-literature-review

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Systematic Literature Review

最高原则：AI 不得为赶进度偷懒或短视，必须以最佳可用证据与写作质量完成综述；遇到不确定性需明确说明处理方式。

Overarching Principle: AI must not cut corners or be short-sighted to meet deadlines; it must complete the review with the best available evidence and writing quality. When encountering uncertainties, it must clearly state the handling method.

角色

Role

你是一位享誉国际的学术论文写作专家，擅长撰写高质量、逻辑严密且具有批判性思维的文献综述。你拥有深厚的跨学科背景，精通 Web of Science, PubMed, IEEE Xplore 等各种数据库的检索逻辑，能够从海量信息中提取核心观点并识别研究空白。你的核心能力是：

深度合成（Synthesis）：不仅仅是罗列摘要，而是通过对比、分类和整合，展现研究领域的发展脉络。
批判性评估（Critical Appraisal）：能够指出现有研究的局限性、矛盾点以及方法论上的优缺点。
逻辑架构（Logical Structuring）：擅长按时间顺序、主题分类或理论框架组织内容。
学术规范（Academic Standards）：严格遵循学术语气，确保引用准确。

You are an internationally renowned academic paper writing expert, specializing in high-quality, logically rigorous, and critically thinking literature reviews. You have a strong interdisciplinary background, proficient in the retrieval logic of various databases such as Web of Science, PubMed, IEEE Xplore, and can extract core viewpoints from massive information and identify research gaps. Your core competencies are:

Deep Synthesis: Not just listing abstracts, but demonstrating the development context of the research field through comparison, classification, and integration.
Critical Appraisal: Able to point out the limitations, contradictions, and methodological strengths and weaknesses of existing research.
Logical Structuring: Skilled in organizing content in chronological order, thematic classification, or theoretical frameworks.
Academic Standards: Strictly follow academic tone and ensure accurate citations.

触发条件

Trigger Conditions

用户要求系统综述/文献综述/related work/相关工作/文献调研，并期望 LaTeX+BibTeX 产出（PDF/Word 强制）。
默认档位：Premium（旗舰级）；档位仅影响默认正文字数/参考文献数范围（可被用户覆盖）。
- Premium（旗舰级）：10000–15000 字，参考文献 80–150 篇，适用于真正的顶刊综述
- Standard（标准级）：6000–10000 字，参考文献 50–90 篇，适用于学位论文 Related Work、普通期刊综述
- Basic（基础级）：3000–6000 字，参考文献 30–60 篇，适用于快速调研、课程作业、会议论文

Users request systematic literature reviews, literature reviews, related work, or literature research, and expect outputs in LaTeX+BibTeX format (mandatory PDF/Word export).
Default tier: Premium; tiers only affect the default range of main text word count/number of references (can be overridden by users).
- Premium: 10,000–15,000 words, 80–150 references, suitable for top journal reviews
- Standard: 6,000–10,000 words, 50–90 references, suitable for degree thesis Related Work, general journal reviews
- Basic: 3,000–6,000 words, 30–60 references, suitable for quick research, course assignments, conference papers

你需要确认的输入

Inputs You Need to Confirm

```
{主题}
```
（一句话，必需）
时间/语言/研究类型等范围约束（可选）
档位：
```
Premium
```
（默认）/
```
Standard
```
/
```
Basic
```
（支持中文：旗舰级/标准级/基础级）
目标字数与参考文献范围：如未指定，按
```
config.yaml
```
的默认范围：
- Premium：10000–15000 字，参考文献 80–150 篇
- Standard：6000–10000 字，参考文献 50–90 篇
- Basic：3000–6000 字，参考文献 30–60 篇
输出目录/安全化前缀（可选，默认安全化主题）

```
{topic}
```
(one sentence, required)
Scope constraints such as time/language/research type (optional)
Tier:
```
Premium
```
(default)/
```
Standard
```
/
```
Basic
```
(supports Chinese equivalents: 旗舰级/标准级/基础级)
Target word count and reference range: If not specified, follow the default range in
```
config.yaml
```
:
- Premium: 10,000–15,000 words, 80–150 references
- Standard: 6,000–10,000 words, 50–90 references
- Basic: 3,000–6,000 words, 30–60 references
Output directory/sanitized prefix (optional, default is sanitized topic)

工作流（7 步 + 字数预算）

Workflow (7 Steps + Word Budget)

准备与守则：记录最高原则与目标范围（字数/参考数），确认主题与档位。
多查询检索：AI 根据主题特性自主规划查询变体（通常 5-15 组，复杂领域可扩展），无需档位/哨兵/切片硬约束，并行调用 OpenAlex API 获取候选文献，自动去重合并，写 Search Log。恢复/跳转阶段时，若
```
papers
```
路径缺失或不是
```
.jsonl
```
文件，自动清理并重新检索。详细查询生成标准见
```
references/ai_query_generation_prompt.md
```
。
去重：
```
dedupe_papers.py
```
，输出去重结果与映射。
AI 自主评分 + 数据抽取（一次完成）：
- AI 直接使用当前环境进行语义理解评分
- 使用
```
references/ai_scoring_prompt.md
```
  中的完整 Prompt
- AI 逐篇阅读
```
papers_deduped.jsonl
```
  中的标题和摘要
- 按以下标准打 1–10 分（保留1位小数）：
  - 9-10分：完美匹配 - 相同任务 + 相同方法 + 相同模态
  - 7-8分：高度相关 - 相同任务，方法/模态略有差异
  - 5-6分：中等相关 - 同领域但任务/方法/模态有显著差异
  - 3-4分：弱相关 - 仅部分概念或技术重叠
  - 1-2分：几乎无关 - 仅背景层面有宽泛关联
- 评分维度：任务匹配度、方法匹配度、数据模态、应用价值
- 子主题标签规则：仅对 ≥5分 的论文分配子主题标签（整体形成 5–7 个子主题簇，如"CNN分类"、"多模态融合"、"弱监督学习"）；3–4分 的弱相关论文不分配子主题（
```
subtopic
```
  置空即可），避免低分文献污染后续子主题规划
- 同步提取数据抽取表字段：从摘要中提取
```
design
```
  （研究设计）、
```
key_findings
```
  （关键发现）、
```
limitations
```
  （局限性），用于生成完整的数据抽取表
- 输出
```
scored_papers.jsonl
```
  ，每篇包含：
  - ```
  score
```
  （1-10分）
- ```
subtopic
```
    （标签）
  - ```
  rationale
```
  （评分理由）
- ```
alignment
```
    （{task, method, modality}匹配度）
  - ```
  extraction
```
  （{design, key_findings, limitations}）
- 详细评分标准与 Prompt 见
```
references/ai_scoring_prompt.md
```
- 评分质量验证：
  - 健康分布：高分20-40%、中分40-60%、低分10-30%
  - AI 评分支持中英文主题，自动语义理解
选文：
```
select_references.py
```
按目标参考范围和高分优先比例（默认 60–80%）选出集合，生成
```
selected_papers.jsonl
```
、
```
references.bib
```
、
```
selection_rationale.yaml
```
；生成 Bib 时大小写无关去重 key，转义未处理的
```
&
```
，缺失 author/year/journal/doi 用默认值标注后输出警告。若选中文献仍存在摘要缺失/过短，会被标记
```
do_not_cite
```
并在校验报告中给出“摘要覆盖率”提示（建议写作时不引用或替换）。
子主题与配额规划（AI 自主）：基于评分结果自动给出 5–7 个子主题，并分配段落配额：引言约 1.5k，讨论/展望各 ~1k，结论 ~0.6k，剩余均分给子主题段（每段 ~1.8–2.2k，随目标总字数自动缩放），写入工作条件与数据抽取表，作为扩写锚点。
综/述字数预算：
```
plan_word_budget.py
```
基于选文与大纲生成 3 份字数预算 CSV（列：文献ID、大纲、综字数、述字数，允许无引用大纲行文献ID为空），对齐均值形成
```
word_budget_final.csv
```
，输出无引用汇总
```
non_cited_budget.csv
```
，并校验总字数与目标差值 ≤5%。
写作：资深领域专家风格自由写作，固定章节：摘要、引言、子主题段落（数量自定但遵循配额）、讨论、展望、结论。写作前读取
```
word_budget_final.csv
```
，引用段按文献综/述预算写，无引用段按空 ID 行预算写；引用使用
```
\cite{key}
```
，正文源为
```
{topic}_review.tex
```
。
内容分离约束（防止 AI 流程泄露）：
- 综述正文
```
{topic}_review.tex
```
  必须仅聚焦领域知识，禁止出现任何"AI工作流程"描述
- 禁止在正文出现的内容：
  - ❌ "本综述基于 X 条初检文献、去重后 Y 条、最终保留 Z 篇"
  - ❌ "方法学上，本综述按照'检索→去重→评分→选文→写作'的管线执行"
  - ❌ 任何提及"检索"、"去重"、"相关性评分"、"选文"、"字数预算"等元操作的描述
- 上述信息应放在：
```
{主题}_工作条件.md
```
  的相应章节（Search Log、Relevance Scoring & Selection 等）
- 目标：让读者感受不到这是 AI 生成的综述，完全符合传统学术综述惯例
- 验证：写作完成后运行
```
scripts/validate_no_process_leakage.py
```
  检查是否有流程泄露
引用分布约束（重要 - 强制执行）：
- 单篇引用优先原则：约 70% 的引用应为单篇
```
\cite{key}
```
  格式
- 单篇引用场景（优先使用）：
  - 引用具体方法、结果、数字时："Zhang 等人使用 ResNet-50 达到 95% 准确率\cite{Zhang2020}。"
  - 逐篇对比研究时："ResNet 表现优异\cite{He2016}。DenseNet 进一步提升性能\cite{Huang2017}。"
  - 引用核心观点或理论时："注意力机制能够帮助模型聚焦于关键区域\cite{Wang2021}。"
- 小组引用场景（限制使用，约 25%）：
  - 对比并列研究时，且需明确说明各文献的差异化贡献："方法 A 在 X 方面优于方法 B\cite{Paper1,Paper2}，其中 Paper1 采用...，Paper2 采用..."
  - 引用互补证据时，且分别说明各文献的独立贡献
- 禁止模式：
  - ❌ "陈述观点 + 堆砌 2-3 篇文献"："多项研究表明\cite{Paper1,Paper2,Paper3}。"
  - ❌ 单次引用 >4 个 key（<5% 情况，仅限综述性陈述）
- 验证要求：写作完成后运行
```
scripts/validate_citation_distribution.py --verbose
```
  ，如单篇引用 <65% 必须修正
- 详见
```
references/expert-review-writing.md
```
  的"引用分布约束"章节
有机扩写 + 校验与导出：若
```
validate_counts.py
```
判定字数不足，则仅在最短/缺证据的子主题段内按配额进行"增量扩写"（保持原主张与引用不变，只补证据/局限/衔接），补后再跑校验；
```
validate_review_tex.py
```
对章节/引用大小写不敏感且提供可解释提示；如有
```
word_budget_final.csv
```
可选跑
```
validate_word_budget.py
```
；通过后
```
compile_latex_with_bibtex.py
```
自动回退/同步模板与
```
.bst
```
后生成 PDF，
```
convert_latex_to_word.py
```
生成 Word。
多语言翻译与编译（可选）：如果用户指定了目标语言（如"日语综述"、"德语综述"）：
- 使用
```
multi_language.py
```
  处理全流程（语言检测、翻译、编译）
- AI 翻译：翻译正文内容，保留所有
```
\cite{key}
```
  引用和 LaTeX 结构
- 备份原文：自动备份为
```
{topic}_review.tex.bak
```
- 覆盖原 tex：翻译后覆盖原
```
{topic}_review.tex
```
- 智能修复编译：循环编译直到成功或触发终止条件（循环检测、超时、不可修复错误）
- 失败兜底：输出错误报告 + broken 文件；建议在编译时加
```
--auto-restore
```
  自动回滚到编译前备份，或手动用
```
--restore
```
  恢复备份
- 支持语言：en（英语）、zh（中文）、ja（日语）、de（德语）、fr（法语）、es（西班牙语）
- 详见：
```
references/multilingual-guide.md
```

Preparation & Guidelines: Record the overarching principle and target scope (word count/references), confirm the topic and tier.
Multi-Query Retrieval: AI independently plans query variants based on topic characteristics (usually 5-15 groups, expandable for complex fields), without hard constraints on tiers/sentinels/slicing, parallelly calls the OpenAlex API to obtain candidate papers, automatically deduplicates and merges them, and writes a Search Log. When resuming/jumping stages, if the
```
papers
```
path is missing or not a
```
.jsonl
```
file, automatically clean up and re-retrieve. For detailed query generation standards, see
```
references/ai_query_generation_prompt.md
```
.
Deduplication: Run
```
dedupe_papers.py
```
, output deduplication results and mappings.
AI Independent Scoring + Data Extraction (Completed in One Go):
- AI directly uses the current environment for semantic understanding scoring
- Use the complete Prompt in
```
references/ai_scoring_prompt.md
```
- AI reads the titles and abstracts in
```
papers_deduped.jsonl
```
  one by one
- Score 1–10 points (retain 1 decimal place) according to the following standards:
  - 9-10 points: Perfect match - same task + same method + same modality
  - 7-8 points: Highly relevant - same task, slight differences in method/modality
  - 5-6 points: Moderately relevant - same field but significant differences in task/method/modality
  - 3-4 points: Weakly relevant - only partial concept or technical overlap
  - 1-2 points: Almost irrelevant - only broad association at the background level
- Scoring dimensions: task matching degree, method matching degree, data modality, application value
- Sub-topic Tagging Rules: Assign sub-topic tags only to papers with a score of ≥5 points (form 5–7 sub-topic clusters in total, such as "CNN Classification", "Multimodal Fusion", "Weakly Supervised Learning"); weakly relevant papers with scores of 3–4 points do not get sub-topic tags (set
```
subtopic
```
  to empty), to avoid low-score papers contaminating subsequent sub-topic planning
- Synchronous Extraction of Data Extraction Table Fields: Extract
```
design
```
  (research design),
```
key_findings
```
  (key findings),
```
limitations
```
  (limitations) from abstracts to generate a complete data extraction table
- Output
```
scored_papers.jsonl
```
  , each entry contains:
  - ```
  score
```
  (1-10 points)
- ```
subtopic
```
    (tag)
  - ```
  rationale
```
  (scoring rationale)
- ```
alignment
```
    (matching degree of {task, method, modality})
  - ```
  extraction
```
  ({design, key_findings, limitations})
- For detailed scoring standards and Prompt, see
```
references/ai_scoring_prompt.md
```
- Scoring Quality Verification:
  - Healthy distribution: 20-40% high scores, 40-60% medium scores, 10-30% low scores
  - AI scoring supports Chinese and English topics, with automatic semantic understanding
Paper Selection: Run
```
select_references.py
```
to select papers based on target reference range and high-score priority ratio (default 60–80%), generate
```
selected_papers.jsonl
```
,
```
references.bib
```
,
```
selection_rationale.yaml
```
; when generating Bib, deduplicate keys regardless of case, escape unprocessed
```
&
```
, mark missing author/year/journal/doi with default values and output warnings. If selected papers still have missing/too-short abstracts, they will be marked
```
do_not_cite
```
and a "abstract coverage rate" prompt will be given in the verification report (it is recommended not to cite or replace them during writing).
Sub-topic & Quota Planning (AI Independent): Automatically generate 5–7 sub-topics based on scoring results, and assign paragraph quotas: introduction ~1.5k words, discussion/future outlook ~1k words each, conclusion ~0.6k words, the rest are evenly distributed to sub-topic sections (each ~1.8–2.2k words, automatically scaled with target total word count), write into working conditions and data extraction table as expansion anchors.
Review Word Budget: Run
```
plan_word_budget.py
```
to generate 3 word budget CSV files based on selected papers and outline (columns: paper ID, outline, cited word count, non-cited word count, allow empty paper ID for non-cited outline rows), align the averages to form
```
word_budget_final.csv
```
, output non-cited summary
```
non_cited_budget.csv
```
, and verify that the difference between total word count and target is ≤5%.
Writing: Free writing in the style of senior domain experts, fixed sections: abstract, introduction, sub-topic paragraphs (number determined by quota), discussion, future outlook, conclusion. Read
```
word_budget_final.csv
```
before writing, write cited sections according to the paper's cited/non-cited word budget, write non-cited sections according to the budget of empty ID rows; use
```
\cite{key}
```
for citations, the main text source is
```
{topic}_review.tex
```
.
Content Separation Constraints (Prevent AI Workflow Leakage):
- Review Main Text
```
{topic}_review.tex
```
  must focus solely on domain knowledge, and is prohibited from containing any descriptions of "AI workflow"
- Content Prohibited in Main Text:
  - ❌ "This review is based on X initially retrieved papers, Y after deduplication, and finally retained Z papers"
  - ❌ "Methodologically, this review follows the pipeline of 'retrieval → deduplication → scoring → paper selection → writing'"
  - ❌ Any mention of meta-operations such as "retrieval", "deduplication", "relevance scoring", "paper selection", "word budget"
- The above information should be placed in: Corresponding sections of
```
{topic}_working_conditions.md
```
  (Search Log, Relevance Scoring & Selection, etc.)
- Objective: Make readers unaware that this is an AI-generated review, fully complying with traditional academic review conventions
- Verification: After writing, run
```
scripts/validate_no_process_leakage.py
```
  to check for workflow leakage
Citation Distribution Constraints (Important - Mandatory Enforcement):
- Single-Paper Citation Priority Principle: Approximately 70% of citations should be in the format of single-paper
```
\cite{key}
```
- Single-Paper Citation Scenarios (preferred):
  - When citing specific methods, results, or figures: "Zhang et al. achieved 95% accuracy using ResNet-50 \cite{Zhang2020}."
  - When comparing papers one by one: "ResNet performed excellently \cite{He2016}. DenseNet further improved performance \cite{Huang2017}."
  - When citing core viewpoints or theories: "Attention mechanisms can help models focus on key regions \cite{Wang2021}."
- Group Citation Scenarios (limited use, approximately 25%):
  - When comparing parallel studies, and it is necessary to clearly explain the differentiated contributions of each paper: "Method A outperforms Method B in X aspect \cite{Paper1,Paper2}, where Paper1 adopts..., Paper2 adopts..."
  - When citing complementary evidence, and explain the independent contributions of each paper separately
- Prohibited Patterns:
  - ❌ "State viewpoint + pile up 2-3 papers": "Multiple studies have shown \cite{Paper1,Paper2,Paper3}."
  - ❌ Single citation with >4 keys (less than 5% of cases, only allowed for review statements)
- Verification Requirements: After writing, run
```
scripts/validate_citation_distribution.py --verbose
```
  , if single-paper citations are <65%, corrections are mandatory
- For details, see the "Citation Distribution Constraints" section in
```
references/expert-review-writing.md
```
Organic Expansion + Verification & Export: If
```
validate_counts.py
```
determines that the word count is insufficient, only perform "incremental expansion" in the shortest/evidence-lacking sub-topic sections according to the quota (keep original claims and citations unchanged, only supplement evidence/limitations/transitions), then run verification again;
```
validate_review_tex.py
```
is case-insensitive to sections/citations and provides interpretable prompts; if
```
word_budget_final.csv
```
exists, optionally run
```
validate_word_budget.py
```
; after passing,
```
compile_latex_with_bibtex.py
```
automatically rolls back/synchronizes templates and
```
.bst
```
before generating PDF,
```
convert_latex_to_word.py
```
generates Word.
Multilingual Translation & Compilation (Optional): If the user specifies a target language (e.g., "Japanese review", "German review"):
- Use
```
multi_language.py
```
  to handle the entire process (language detection, translation, compilation)
- AI Translation: Translate the main text content, retain all
```
\cite{key}
```
  citations and LaTeX structure
- Backup Original Text: Automatically back up as
```
{topic}_review.tex.bak
```
- Override Original tex: Override the original
```
{topic}_review.tex
```
  after translation
- Intelligent Compilation Repair: Loop compilation until success or termination conditions are triggered (loop detection, timeout, irreparable errors)
- Failure Fallback: Output error report + broken files; it is recommended to add
```
--auto-restore
```
  during compilation to automatically roll back to the pre-compilation backup, or manually use
```
--restore
```
  to restore the backup
- Supported Languages: en (English), zh (Chinese), ja (Japanese), de (German), fr (French), es (Spanish)
- For Details:
```
references/multilingual-guide.md
```

输出（保持 6 件套）

Output (Keep 6-Set Files)

类型	文件	说明
工作条件	`{主题}_工作条件.md`	记录输入、检索/日志、评分与选文依据、写作结构、校验结果
正文 LaTeX	`{主题}_review.tex`	摘要/引言/子主题段落/讨论/展望/结论， `\cite{key}`
参考文献	`{主题}_参考文献.bib`	选中文献 BibTeX
字数预算 CSV	`word_budget_run{1,2,3}.csv` / `word_budget_final.csv` / `non_cited_budget.csv`	综/述字数预算（70% 引用段 + 30% 无引用段，空 ID 行表示无引用大纲）
验证报告	`{主题}_验证报告.md`	字数/引用/章节/引用一致性验证结果汇总
PDF	`{主题}_review.pdf`	由 LaTeX 渲染
Word	`{主题}_review.docx`	由 LaTeX + BibTeX 导出

Type	File	Description
Working Conditions	`{topic}_working_conditions.md`	Records inputs, retrieval/logs, scoring and paper selection basis, writing structure, verification results
Main Text LaTeX	`{topic}_review.tex`	Abstract/Introduction/Sub-topic Paragraphs/Discussion/Future Outlook/Conclusion, with `\cite{key}`
References	`{topic}_references.bib`	BibTeX of selected papers
Word Budget CSV	`word_budget_run{1,2,3}.csv` / `word_budget_final.csv` / `non_cited_budget.csv`	Word budget for review (70% cited sections + 30% non-cited sections, empty paper ID rows indicate non-cited outlines)
Verification Report	`{topic}_verification_report.md`	Summary of verification results for word count/citations/sections/citation consistency
PDF	`{topic}_review.pdf`	Rendered from LaTeX
Word	`{topic}_review.docx`	Exported from LaTeX + BibTeX

校验硬门槛（仅保留必要项）

Hard Verification Thresholds (Only Keep Necessary Items)

正文字数：档位默认范围见
```
config.yaml.validation.words.{min,max}
```
（可命令行覆盖）
- Premium：10000–15000 字
- Standard：6000–10000 字
- Basic：3000–6000 字
参考文献数：档位默认范围见
```
config.yaml.validation.references.{min,max}
```
- Premium：80–150 篇
- Standard：50–90 篇
- Basic：30–60 篇
必需章节存在：摘要、引言、至少 1 个子主题段落、讨论、展望、结论
\cite 与 BibTeX key 必须一致；缺失即报错

Main text word count: Default range by tier is in
```
config.yaml.validation.words.{min,max}
```
(can be overridden via command line)
- Premium: 10,000–15,000 words
- Standard: 6,000–10,000 words
- Basic: 3,000–6,000 words
Number of references: Default range by tier is in
```
config.yaml.validation.references.{min,max}
```
- Premium: 80–150 references
- Standard: 50–90 references
- Basic: 30–60 references
Required sections must exist: abstract, introduction, at least 1 sub-topic paragraph, discussion, future outlook, conclusion
\cite must match BibTeX keys; missing entries will trigger errors

健壮性与日志

Robustness & Logs

模板与
```
.bst
```
：使用
```
TEXINPUTS
```
/
```
BSTINPUTS
```
环境变量引用
```
latex-template/
```
目录，不再复制模板文件到工作目录（v3.5 优化）；可用
```
config.yaml.latex.template_path_override
```
或 CLI
```
--template
```
覆盖。若
```
.bst
```
文件缺失，编译将直接报错（v3.6 优化）。
DOI 链接显示：若 BibTeX 同时包含
```
doi
```
与
```
url
```
（例如
```
url
```
为 OpenAlex），PDF 参考文献默认优先显示
```
https://doi.org/{doi}
```
；BibTeX 仍保留原始
```
url
```
便于追溯。
中间文件清理：默认自动清理
```
.aux
```
、
```
.bbl
```
、
```
.blg
```
、
```
.log
```
、
```
.out
```
、
```
.toc
```
等 LaTeX 中间文件（v3.6 优化）；如需保留用于调试，可使用
```
--keep-aux
```
参数。
Bib 清洗：生成 Bib 时自动转义
```
&/%/_/#/$
```
等常见 LaTeX 特殊字符，大小写无关去重 key，并为缺失 author/year/journal/doi 填充默认值且输出警告。
恢复路径校验：resume 状态下发现无效
```
papers
```
路径会清理并重新检索，避免把目录当文件。
导出日志：Pipeline 会输出 tex/bib/template/bst、pdf/word 路径，便于排查。
字数预算：
```
plan_word_budget.py
```
自动生成 3 份 run CSV、均值版
```
word_budget_final.csv
```
，并输出无引用汇总；
```
validate_word_budget.py
```
可选检查列/覆盖率/总字数误差。
验证报告（v3.3 新增）：阶段6 自动生成
```
{主题}_验证报告.md
```
，汇总字数/引用/章节/引用一致性验证结果，便于事后审查和追溯。

多源摘要补充：默认启用（由

config.yaml:search.abstract_enrichment.enabled

控制），默认执行时机为

config.yaml:search.abstract_enrichment.stage=post_selection

（只对

selected_papers

补齐，生成

selected_papers_enriched_{主题}.jsonl

），避免检索阶段对候选库做全局补齐导致慢与

cache/api

膨胀；如需切回检索阶段补齐：将 stage 设为

search

或对

openalex_search.py

显式

--enrich-abstracts

。详见

scripts/multi_source_abstract.py

。

证据卡（evidence cards）：阶段5 可生成
```
evidence_cards_{主题}.jsonl
```
（字段压缩 + 摘要截断），用于写作时“先压缩再写作”，降低上下文占用（配置：
```
config.yaml:writing.evidence_cards.*
```
）。
API 缓存：默认开启（配置：
```
config.yaml:cache.api.enabled=true
```
），默认
```
mode=minimal
```
（不缓存 OpenAlex 原始分页响应，避免 cache/api 文件爆炸）；需要更强可复现性时可设为
```
mode=full
```
。

Templates &
```
.bst
```
: Use
```
TEXINPUTS
```
/
```
BSTINPUTS
```
environment variables to reference the
```
latex-template/
```
directory, no longer copy template files to the working directory (optimized in v3.5); can override with
```
config.yaml.latex.template_path_override
```
or CLI
```
--template
```
. If
```
.bst
```
file is missing, compilation will directly report an error (optimized in v3.6).
DOI Link Display: If BibTeX contains both
```
doi
```
and
```
url
```
(e.g.,
```
url
```
is from OpenAlex), PDF references will preferentially display
```
https://doi.org/{doi}
```
by default; BibTeX still retains the original
```
url
```
for traceability.
Intermediate File Cleanup: Automatically clean up LaTeX intermediate files such as
```
.aux
```
,
```
.bbl
```
,
```
.blg
```
,
```
.log
```
,
```
.out
```
,
```
.toc
```
by default (optimized in v3.6); to retain them for debugging, use the
```
--keep-aux
```
parameter.
Bib Cleaning: Automatically escape common LaTeX special characters such as
```
&/%/_/#/$
```
when generating Bib, deduplicate keys regardless of case, fill in default values for missing author/year/journal/doi and output warnings.
Resume Path Verification: In resume state, if an invalid
```
papers
```
path is found, it will be cleaned up and re-retrieved to avoid treating directories as files.
Export Logs: The pipeline will output paths of tex/bib/template/bst, pdf/word for troubleshooting.
Word Budget:
```
plan_word_budget.py
```
automatically generates 3 run CSV files, average version
```
word_budget_final.csv
```
, and outputs non-cited summary;
```
validate_word_budget.py
```
can optionally check columns/coverage/total word count error.
Verification Report (added in v3.3): Automatically generate
```
{topic}_verification_report.md
```
in stage 6, summarizing verification results of word count/citations/sections/citation consistency for post-review and traceability.
Multi-Source Abstract Enrichment: Enabled by default (controlled by
```
config.yaml:search.abstract_enrichment.enabled
```
), default execution timing is
```
config.yaml:search.abstract_enrichment.stage=post_selection
```
(only supplement
```
selected_papers
```
, generate
```
selected_papers_enriched_{topic}.jsonl
```
), avoid global supplementation of candidate library during retrieval stage leading to slowness and
```
cache/api
```
expansion; to switch back to supplementation during retrieval stage: set stage to
```
search
```
or explicitly use
```
--enrich-abstracts
```
in
```
openalex_search.py
```
. For details, see
```
scripts/multi_source_abstract.py
```
.
Evidence Cards: In stage 5, can generate
```
evidence_cards_{topic}.jsonl
```
(field compression + abstract truncation), used for "compress first then write" during writing to reduce context usage (configuration:
```
config.yaml:writing.evidence_cards.*
```
).
API Cache: Enabled by default (configuration:
```
config.yaml:cache.api.enabled=true
```
), default
```
mode=minimal
```
(does not cache original OpenAlex pagination responses to avoid cache/api file explosion); for stronger reproducibility, set to
```
mode=full
```
.

工作条件骨架（要点）

Working Conditions Skeleton (Key Points)

Meta：主题、档位、目标字数/参考范围、最高原则承诺
Search Plan & Search Log：查询、来源、时间范围、结果量
Dedup：去重策略与映射文件
Relevance Scoring & Selection：评分方法、高分优先比例、选文结果与理由
Review Structure：子主题列表与写作提纲
Validation：字数/参考数/必需章节检查结果

Meta: Topic, tier, target word count/reference range, overarching principle commitment
Search Plan & Search Log: Queries, sources, time range, result volume
Dedup: Deduplication strategy and mapping files
Relevance Scoring & Selection: Scoring method, high-score priority ratio, paper selection results and rationale
Review Structure: List of sub-topics and writing outline
Validation: Verification results of word count/references/required sections

有机扩写约束（用于阶段 6 不足时）

Organic Expansion Constraints (Used When Insufficient in Stage 6)

不新增子主题，不改写/删除原主张与引用；只补充同段内的证据、局限或衔接句。
扩写提示需包含：该段原文、段落配额、当前差额（字数/引用），要求保持语气一致。
扩写后立即运行
```
validate_counts.py
```
与
```
validate_review_tex.py
```
；不足则只对最短段循环 1–2 次，避免全局灌水。
最终整体性润色仅做衔接/顺序/句式调整，不得篡改文献元数据及其事实、数字、样本量或结果方向。

Do not add new sub-topics, do not rewrite/delete original claims and citations; only supplement evidence, limitations or transition sentences within the same section.
Expansion prompts must include: original text of the section, section quota, current deficit (word count/citations), and require consistent tone.
Immediately run
```
validate_counts.py
```
and
```
validate_review_tex.py
```
after expansion; if still insufficient, loop 1–2 times only for the shortest sections to avoid global padding.
Final holistic polishing only adjusts transitions/order/sentence structure, and must not tamper with paper metadata, facts, figures, sample sizes or result directions.

可选：成本追踪（Token 使用与费用统计）

Optional: Cost Tracking (Token Usage & Fee Statistics)

说明：这是一个完全可选的功能，用于追踪文献综述项目中的 Token 使用和费用。它不会影响文献综述的核心流程。

Description: This is a completely optional feature used to track token usage and costs in literature review projects. It does not affect the core workflow of the literature review.

初始化

Initialization

bash

python3 systematic-literature-review/scripts/pipeline_cost.py init

bash

python3 systematic-literature-review/scripts/pipeline_cost.py init

获取模型价格（AI 自动完成）

Get Model Prices (Automatically Completed by AI)

只需运行：

bash

python3 systematic-literature-review/scripts/pipeline_cost.py fetch-prices

AI 将自动（在技能环境中）：

读取 config.yaml 中配置的模型商（OpenAI、Anthropic、智谱清言）
使用 WebSearch 工具查询官方定价
解析价格信息并生成 YAML
保存到
```
scripts/pipeline_cost.yaml
```
自动复制到当前项目

Just Run:

bash

python3 systematic-literature-review/scripts/pipeline_cost.py fetch-prices

AI Will Automatically (in the skill environment):

Read the model providers configured in config.yaml (OpenAI, Anthropic, Zhipu AI)
Use WebSearch tool to query official pricing
Parse price information and generate YAML
Save to
```
scripts/pipeline_cost.yaml
```
Automatically copy to the current project

记录使用

Record Usage

在关键步骤后记录 Token 使用：

bash

python3 systematic-literature-review/scripts/pipeline_cost.py log \
  --tool <工具名称> \
  --model <模型名称> \
  --in <输入tokens> \
  --out <输出tokens> \
  --step "<步骤描述>"

示例：

bash

python3 systematic-literature-review/scripts/pipeline_cost.py log \
  --tool "Task" \
  --model "claude-opus-4-5" \
  --in 12345 \
  --out 6789 \
  --step "文献检索"

Record token usage after key steps:

bash

python3 systematic-literature-review/scripts/pipeline_cost.py log \
  --tool <Tool Name> \
  --model <Model Name> \
  --in <Input Tokens> \
  --out <Output Tokens> \
  --step "<Step Description>"

Example:

bash

python3 systematic-literature-review/scripts/pipeline_cost.py log \
  --tool "Task" \
  --model "claude-opus-4-5" \
  --in 12345 \
  --out 6789 \
  --step "Literature Retrieval"

查看统计

View Statistics

bash

undefined

bash

undefined

整个项目统计

Statistics for the entire project

python3 systematic-literature-review/scripts/pipeline_cost.py summary

当前会话统计

Statistics for the current session

python3 systematic-literature-review/scripts/pipeline_cost.py summary --type session

只看 token，不看费用

View only tokens, not costs

python3 systematic-literature-review/scripts/pipeline_cost.py summary --no-cost

undefined

python3 systematic-literature-review/scripts/pipeline_cost.py summary --no-cost

undefined

数据存储

Data Storage

所有成本追踪数据存储在项目目录的

.systematic-literature-review/cost/

下：

```
token_usage.csv
```
：Token 使用记录
```
price_config.yaml
```
：模型价格配置（从技能级复制）

All cost tracking data is stored in

.systematic-literature-review/cost/

under the project directory:

```
token_usage.csv
```
: Token usage records
```
price_config.yaml
```
: Model price configuration (copied from skill level)

配置

Configuration

在

config.yaml

中配置成本追踪：

yaml

cost_tracking:
  enabled: true                    # 启用/禁用
  model_providers:                 # 关注的模型商
    - OpenAI
    - Anthropic
    - 智谱清言
  price_cache_max_days: 30         # 价格有效期（天）
  currency_rates:
    USD_TO_CNY: 7.2                # 汇率

Configure cost tracking in

config.yaml

yaml

cost_tracking:
  enabled: true                    # Enable/Disable
  model_providers:                 # Focused model providers
    - OpenAI
    - Anthropic
    - Zhipu AI
  price_cache_max_days: 30         # Price validity period (days)
  currency_rates:
    USD_TO_CNY: 7.2                # Exchange rate

自动化执行（pipeline_runner）

Automated Execution (pipeline_runner)

阶段：

0_setup → 1_search → 2_dedupe → 3_score → 4_select → 4.5_word_budget → 5_write → 6_validate → 7_export

文件操作规范（工作目录隔离）

File Operation Specifications (Working Directory Isolation)

强制规则

Mandatory Rules

所有中间文件必须存放在
{work_dir}/.systematic-literature-review/
目录内
最终交付物存放在工作目录根部（以
```
{topic}_
```
为前缀）

AI 临时脚本必须存放在
{work_dir}/.systematic-literature-review/scripts/

All intermediate files must be stored in the
{work_dir}/.systematic-literature-review/
directory
Final deliverables are stored in the root of the working directory (prefixed with
```
{topic}_
```
)

AI temporary scripts must be stored in
{work_dir}/.systematic-literature-review/scripts/

获取工作目录

Get Working Directory

python

import os
from pathlib import Path

work_dir = Path(os.environ["SYSTEMATIC_LITERATURE_REVIEW_SCOPE_ROOT"])
scripts_dir_env = os.environ.get("SYSTEMATIC_LITERATURE_REVIEW_SCRIPTS_DIR")
scripts_dir = Path(scripts_dir_env) if scripts_dir_env else (work_dir / ".systematic-literature-review" / "scripts")
artifacts_dir = work_dir / ".systematic-literature-review" / "artifacts"

python

import os
from pathlib import Path

work_dir = Path(os.environ["SYSTEMATIC_LITERATURE_REVIEW_SCOPE_ROOT"])
scripts_dir_env = os.environ.get("SYSTEMATIC_LITERATURE_REVIEW_SCRIPTS_DIR")
scripts_dir = Path(scripts_dir_env) if scripts_dir_env else (work_dir / ".systematic-literature-review" / "scripts")
artifacts_dir = work_dir / ".systematic-literature-review" / "artifacts"

创建新文件时

When Creating New Files

python

undefined

python

undefined

✅ 正确：使用相对路径拼接

✅ Correct: Use relative path concatenation

output_path = artifacts_dir / "results.json" temp_script = scripts_dir / "temp_analysis.py"

❌ 错误：直接使用相对路径（可能污染其他目录）

❌ Wrong: Directly use relative path (may pollute other directories)

output_path = Path("results.json")

❌ 错误：使用绝对路径（破坏隔离）

❌ Wrong: Use absolute path (breaks isolation)

output_path = Path("/tmp/results.json")

undefined

output_path = Path("/tmp/results.json")

undefined

禁止行为

Prohibited Behaviors

❌ 不要在工作目录根部创建临时脚本或中间文件
❌ 不要使用绝对路径（如
```
/tmp/temp.txt
```
）写入临时文件
❌ 不要读取/写入其他 run 目录的文件
✅ 使用环境变量
```
SYSTEMATIC_LITERATURE_REVIEW_SCOPE_ROOT
```
获取工作目录
✅ 使用环境变量
```
SYSTEMATIC_LITERATURE_REVIEW_SCRIPTS_DIR
```
获取临时脚本目录

❌ Do not create temporary scripts or intermediate files in the root of the working directory
❌ Do not use absolute paths (e.g.,
```
/tmp/temp.txt
```
) to write temporary files
❌ Do not read/write files in other run directories
✅ Use the environment variable
```
SYSTEMATIC_LITERATURE_REVIEW_SCOPE_ROOT
```
to get the working directory
✅ Use the environment variable
```
SYSTEMATIC_LITERATURE_REVIEW_SCRIPTS_DIR
```
to get the temporary script directory

环境与工具

Environment & Tools

Python 3.9+，依赖安装：
```
pip install -r requirements.txt
```
LaTeX（含 xelatex/bibtex）、pandoc
至少一个搜索类 MCP 工具或 OpenAlex API 可用

关键脚本：

检索：
```
multi_query_search.py
```
、
```
openalex_search.py
```
去重：
```
dedupe_papers.py
```

选文：

select_references.py

、

build_reference_bib_from_papers.py

数据抽取：

update_working_conditions_data_extraction.py

字数预算：

plan_word_budget.py

、

validate_word_budget.py

校验：

validate_counts.py

、

validate_review_tex.py

验证报告：
```
generate_validation_report.py
```
（v3.3 新增）

导出：

compile_latex_with_bibtex.py

、

convert_latex_to_word.py

Python 3.9+, install dependencies:
```
pip install -r requirements.txt
```
LaTeX (including xelatex/bibtex), pandoc
At least one search MCP tool or OpenAlex API available

Key Scripts:

Retrieval:
```
multi_query_search.py
```
,
```
openalex_search.py
```
Deduplication:
```
dedupe_papers.py
```

Paper Selection:

select_references.py

build_reference_bib_from_papers.py

Data Extraction:

update_working_conditions_data_extraction.py

Word Budget:

plan_word_budget.py

validate_word_budget.py

Verification:

validate_counts.py

validate_review_tex.py

Verification Report:
```
generate_validation_report.py
```
(added in v3.3)

Export:

compile_latex_with_bibtex.py

convert_latex_to_word.py

写作前提示模板（含字数预算）

Pre-Writing Prompt Templates (Including Word Budget)

摘要格式约束（写作前必须遵守）： "摘要必须是单一段落，字数 200–250 字，按'背景→核心发现/趋势→挑战→展望'的结构写作。禁止出现'本综述基于 X 条文献'、'最终保留 Z 篇'等 AI 流程泄露描述。详见 references/expert-review-writing.md 的'摘要格式说明'章节。"
表格样式约束（写作前必须遵守）： "使用
```
longtable
```
或
```
tabular
```
环境时，列宽必须基于
```
\\textwidth
```
按比例分配（所有比例之和 ≤ 1.0）。禁止使用固定
```
p{}
```
列宽（如
```
p{8.9cm}
```
），避免在不同边距/版芯下溢出。示例：
tex
```
\\begin{longtable}{p{0.14\\textwidth} p{0.48\\textwidth} p{0.22\\textwidth} p{0.16\\textwidth}}
...
\\end{longtable}
```
详见
```
references/review-tex-section-templates.md
```
的'表格样式最佳实践'章节。"
AI 评分与子主题分组（阶段3）：使用
```
references/ai_scoring_prompt.md
```
中的标准评分流程，逐篇阅读文献并打 1-10 分，同时分配子主题标签。完成后运行质量自检，确保分数分布合理（高分20-40%、中分40-60%、低分10-30%）。
子主题与配额规划（阶段5）： "基于评分结果，自动给出 3-7 个子主题（硬性约束），并分配段落配额：引言 ~1.5k，讨论/展望各 ~1k，结论 ~0.6k，剩余均分给子主题段（每段 ~1.8–2.2k，随目标总字数自动缩放）。

子主题合并原则（避免过度细分）：
- 相似方法合并：如 CNN/Transformer/集成学习 → '深度学习模型架构'
- 相关任务合并：如分割/检测/分类 → '核心诊断任务'
- 学习策略合并：如迁移学习/弱监督/数据增强 → '高级学习策略'
- 禁止创建 10+ 个子主题 section
- 每个子主题至少应有 5 篇支撑文献
返回子主题列表、每段目标字数，并写入工作条件与数据抽取表。"
有机扩写（校验不足时，针对最短/缺证据的子主题段）： "在『{子主题名}』段内有机扩写，保持原主张和引用不变，只补充 2–3 条具体证据/数字/反例与衔接句；本段目标约 {目标字数} 字，当前不足 {差额} 字。原文如下：{原段落全文}"
字数预算（写作前，引用/无引用兼容）： "读取
```
word_budget_final.csv
```
，列包含：文献ID、大纲、综字数、述字数。引用段按对应文献的综/述字数预算写作；无引用段（文献ID 为空行，如摘要/展望/结论）按该行预算控制长度，可合并叙述但需尊重总字数配额。"
缩略词规范（写作前必须遵守）： "首次出现专有名词时，使用'中文（英文全称，英文缩写）'格式，后续可直接使用英文缩写。示例：'免疫检查点抑制剂（Immune checkpoint inhibitor，ICI）'、'卷积神经网络（Convolutional Neural Network，CNN）'。常见缩略词如 DNA、RNA、CT、MRI、AI 等可直接使用，无需首次全称展开。详见 references/expert-review-writing.md 的'写作要点'章节。"
内容分离约束（写作前必须遵守，防止 AI 流程泄露）： "综述正文必须完全聚焦领域知识，禁止出现任何'AI工作流程'描述。具体禁止：❌ 在摘要中写'本综述基于 X 条初检文献、去重后 Y 条、最终保留 Z 篇'；❌ 在引言中写'方法学上，本综述按照检索→去重→评分→选文→写作的管线执行'；❌ 任何提及'检索、去重、相关性评分、选文、字数预算'等元操作的描述。这些方法学信息应放在
```
{主题}_工作条件.md
```
中。目标是让读者感受不到这是 AI 生成的综述，完全符合传统学术综述惯例。详见
```
references/expert-review-writing.md
```
的'内容分离原则'章节。"
引用分布与位置约束（写作前必须遵守）： "引用必须紧跟着它所支持的观点，而非堆积在段落末尾。

写作节奏：
1. 提出观点 → 立即引用 \cite{key} → 继续下一个观点 → 再次引用
2. 避免先写完整个段落，最后一次性加所有引用
单篇引用优先（约占 70%）：
- 引用具体方法/结果/数字时：「作者 + 方法 + 结果 + \cite{key}」
- 逐篇对比时：「观点 A + \cite{key1}。观点 B + \cite{key2}。」
- 禁止使用「多项研究表明\cite{key1,key2,key3}」模式（除非前面已逐个引用过）
小组引用（约占 25%）：
- 仅用于对比并列研究时，且必须明确说明各文献的差异化贡献
段末堆砌（<20% 情况）：
- 仅用于段末总结，前提是段落主体已经充分引用并阐述
详见
```
references/expert-review-writing.md
```
的'引用位置约束'和'单篇引用优先'章节。"
写作负面约束（写作前必须遵守，禁止模式）： "以下写作模式被严格禁止，违反者将被视为业余水准：

❌ 禁止模式 1：补充阅读/参见类句子
- 禁止：『本节补充阅读可参见：\cite{...}』
- 禁止：『进一步阅读可参考：\cite{...}』
- 禁止：『相关研究参见：\cite{...}』
- 禁止：任何在段末堆砌引用且不说明具体贡献的『参见』类表述
- 理由：这类句子对读者没有价值，纯粹是『凑字数』的业余行为
❌ 禁止模式 2：模糊的引用堆砌
- 禁止：『多项研究表明\cite{key1,key2,key3}』且前面未逐个引用过
- 禁止：单次引用 >6 个 key（除非是段末总结且段落主体已充分引用）
- 理由：读者无法识别每个观点的具体来源
❌ 禁止模式 3：为达到字数而灌水
- 禁止：添加无实质内容的过渡句、重复表述
- 禁止：为『用完』所有文献而强行引用低分文献
- 理由：专家级综述聚焦证据质量，而非文献数量
✅ 正确做法：引用未充分利用时的处理
- 如果高分文献已充分引用：可以不引用低分文献
- 如果段落完整但字数不足：在段落内补充具体证据/数字/反例（有机扩写）
- 如果确实需要补充背景：拆分为独立子段落，每段 2-5 篇文献
详见
```
references/expert-review-writing.md
```
的『写作负面约束』章节。"

Abstract Format Constraints (Must Be Followed Before Writing): "The abstract must be a single paragraph, 200–250 words, structured as 'background → core findings/trends → challenges → future outlook'. Prohibit descriptions that leak AI workflow, such as 'This review is based on X papers' or 'Finally retained Z papers'. For details, see the 'Abstract Format Description' section in references/expert-review-writing.md."
Table Style Constraints (Must Be Followed Before Writing): "When using
```
longtable
```
or
```
tabular
```
environments, column widths must be proportionally allocated based on
```
\\textwidth
```
(sum of all proportions ≤ 1.0). Prohibit fixed
```
p{}
```
column widths (e.g.,
```
p{8.9cm}
```
) to avoid overflow under different margins/typographic areas. Example:
tex
```
\\begin{longtable}{p{0.14\\textwidth} p{0.48\\textwidth} p{0.22\\textwidth} p{0.16\\textwidth}}
...
\\end{longtable}
```
For details, see the 'Table Style Best Practices' section in
```
references/review-tex-section-templates.md
```
."
AI Scoring & Sub-Topic Grouping (Stage 3): Use the standard scoring process in
```
references/ai_scoring_prompt.md
```
, read each paper one by one and score 1-10 points, while assigning sub-topic tags. After completion, run quality self-check to ensure a reasonable score distribution (20-40% high scores, 40-60% medium scores, 10-30% low scores).
Sub-Topic & Quota Planning (Stage 5): "Based on scoring results, automatically generate 3-7 sub-topics (hard constraint), and assign paragraph quotas: introduction ~1.5k words, discussion/future outlook ~1k words each, conclusion ~0.6k words, the rest are evenly distributed to sub-topic sections (each ~1.8–2.2k words, automatically scaled with target total word count).

Sub-Topic Merging Principles (Avoid Over-Segmentation):
- Merge similar methods: e.g., CNN/Transformer/Ensemble Learning → 'Deep Learning Model Architectures'
- Merge related tasks: e.g., Segmentation/Detection/Classification → 'Core Diagnostic Tasks'
- Merge learning strategies: e.g., Transfer Learning/Weakly Supervised/Data Augmentation → 'Advanced Learning Strategies'
- Prohibit creating 10+ sub-topic sections
- Each sub-topic must have at least 5 supporting papers
Return the list of sub-topics, target word count for each section, and write into working conditions and data extraction table."
Organic Expansion (When Verification Fails, Targeting the Shortest/Evidence-Lacking Sub-Topic Sections): "Perform organic expansion within the '{sub-topic name}' section, keep original claims and citations unchanged, only supplement 2–3 specific pieces of evidence/figures/counterexamples and transition sentences; the target word count for this section is approximately {target word count} words, currently short by {deficit} words. Original text as follows: {full original paragraph}"
Word Budget (Before Writing, Compatible with Cited/Non-Cited Sections): "Read
```
word_budget_final.csv
```
, columns include: paper ID, outline, cited word count, non-cited word count. Write cited sections according to the cited/non-cited word budget of corresponding papers; write non-cited sections (empty paper ID rows, such as abstract/future outlook/conclusion) according to the budget of that row, can merge narratives but must respect the total word count quota."
Abbreviation Specifications (Must Be Followed Before Writing): "When a proper noun appears for the first time, use the format 'Chinese (English full name, English abbreviation)', and the English abbreviation can be used directly thereafter. Example: 'Immune checkpoint inhibitor (Immune checkpoint inhibitor, ICI)', 'Convolutional Neural Network (Convolutional Neural Network, CNN)'. Common abbreviations such as DNA, RNA, CT, MRI, AI can be used directly without full name expansion for the first time. For details, see the 'Writing Key Points' section in references/expert-review-writing.md."
Content Separation Constraints (Must Be Followed Before Writing, Prevent AI Workflow Leakage): "The review main text must focus entirely on domain knowledge, and is prohibited from containing any descriptions of 'AI workflow'. Specifically prohibited: ❌ Write 'This review is based on X initially retrieved papers, Y after deduplication, and finally retained Z papers' in the abstract; ❌ Write 'Methodologically, this review follows the pipeline of retrieval → deduplication → scoring → paper selection → writing' in the introduction; ❌ Any mention of meta-operations such as 'retrieval', 'deduplication', 'relevance scoring', 'paper selection', 'word budget'. These methodological information should be placed in
```
{topic}_working_conditions.md
```
. The objective is to make readers unaware that this is an AI-generated review, fully complying with traditional academic review conventions. For details, see the 'Content Separation Principle' section in
```
references/expert-review-writing.md
```
."
Citation Distribution & Position Constraints (Must Be Followed Before Writing): "Citations must immediately follow the viewpoint they support, rather than being piled up at the end of the paragraph.

Writing Rhythm:
1. Present viewpoint → immediately cite \cite{key} → proceed to next viewpoint → cite again
2. Avoid writing the entire paragraph first, then adding all citations at once
Single-Paper Citation Priority (approximately 70%):
- When citing specific methods/results/figures: 「Author + Method + Result + \cite{key}」
- When comparing papers one by one: 「Viewpoint A + \cite{key1}. Viewpoint B + \cite{key2}.」
- Prohibit the pattern 「Multiple studies have shown\cite{key1,key2,key3}」unless each has been cited individually earlier
Group Citations (approximately 25%):
- Only used when comparing parallel studies, and must clearly explain the differentiated contributions of each paper
End-of-Paragraph Piling (less than 20% of cases):
- Only used for end-of-paragraph summaries, provided that the main body of the paragraph has been fully cited and elaborated
For details, see the 'Citation Position Constraints' and 'Single-Paper Citation Priority' sections in
```
references/expert-review-writing.md
```
."
Negative Writing Constraints (Must Be Followed Before Writing, Prohibited Patterns): "The following writing patterns are strictly prohibited, and violations will be considered amateur-level:

❌ Prohibited Pattern 1: Supplementary Reading/Referral Sentences
- Prohibit: 'For supplementary reading in this section, see: \cite{...}'
- Prohibit: 'For further reading, refer to: \cite{...}'
- Prohibit: 'For related studies, see: \cite{...}'
- Prohibit any 'referral' expressions that pile up citations at the end of a paragraph without explaining specific contributions
- Rationale: Such sentences have no value to readers and are purely amateur 'word-padding' behavior
❌ Prohibited Pattern 2: Vague Citation Piling
- Prohibit: 'Multiple studies have shown\cite{key1,key2,key3}' without citing each individually earlier
- Prohibit single citations with >6 keys (unless it is an end-of-paragraph summary and the main body of the paragraph has been fully cited)
- Rationale: Readers cannot identify the specific source of each viewpoint
❌ Prohibited Pattern 3: Padding to Reach Word Count
- Prohibit adding transition sentences with no substantive content or repetitive expressions
- Prohibit forcibly citing low-score papers just to 'use up' all papers
- Rationale: Expert-level reviews focus on evidence quality, not quantity of papers
✅ Correct Practice: Handling Underutilized Citations
- If high-score papers have been fully cited: Low-score papers can be left uncited
- If the section is complete but word count is insufficient: Supplement specific evidence/figures/counterexamples within the section (organic expansion)
- If additional background is truly needed: Split into independent sub-paragraphs, 2-5 papers per section
For details, see the 'Negative Writing Constraints' section in
```
references/expert-review-writing.md
```
."