Back to Details

novelty-assessment

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Novelty Assessment

新颖性评估

Rigorously assess whether a research idea is novel through systematic literature search.
通过系统性文献检索严格评估研究想法是否具有新颖性。

Input

输入

  • $0
    — Research idea description, title, or JSON file
  • $0
    — 研究想法描述、标题或JSON文件

Scripts

脚本

Automated novelty check

自动化新颖性检查

bash
python ~/.claude/skills/idea-generation/scripts/novelty_check.py \
  --idea "Your research idea description" \
  --max-rounds 10 --output novelty_report.json
bash
python ~/.claude/skills/idea-generation/scripts/novelty_check.py \
  --idea "Your research idea description" \
  --max-rounds 10 --output novelty_report.json

Literature search

文献检索

bash
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "relevant search query" --max-results 10
bash
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "relevant search query" --max-results 10

References

参考资料

  • Assessment prompts and criteria: 
    ~/.claude/skills/novelty-assessment/references/assessment-prompts.md
  • 评估提示词与标准：
    ~/.claude/skills/novelty-assessment/references/assessment-prompts.md

Workflow

工作流程

Step 1: Understand the Idea

步骤1：理解研究想法

  • Identify the core contribution
  • List the key technical components
  • Determine the research area and subfield
  • 识别核心贡献
  • 列出关键技术组件
  • 确定研究领域及子领域

Step 2: Multi-Round Literature Search (up to 10 rounds)

步骤2：多轮文献检索（最多10轮）

For each round:
  1. Generate a targeted search query
  2. Search Semantic Scholar / arXiv / OpenAlex
  3. Review top-10 results with abstracts
  4. Assess overlap with the idea
  5. Decide: need more searching, or ready to decide
每一轮包含：
  1. 生成针对性检索词
  2. 在Semantic Scholar / arXiv / OpenAlex上检索
  3. 查看前10条结果的摘要
  4. 评估与研究想法的重叠度
  5. 决定：是否需要继续检索，或是可以做出判定

Step 3: Make Decision

步骤3：做出判定

  • Novel: After sufficient searching, no paper significantly overlaps
  • Not Novel: Found a paper that significantly overlaps
  • 新颖：经过充分检索后，未发现有论文与该想法存在显著重叠
  • 不新颖：发现有论文与该想法存在显著重叠

Step 4: Position the Idea

步骤4：定位研究想法

If novel, identify:
  • Most similar existing papers (for Related Work)
  • How the idea differs from each
  • The specific gap this idea fills
若判定为新颖，则需明确：
  • 最相似的现有论文（用于相关工作部分）
  • 本想法与每篇论文的差异
  • 本想法填补的具体研究空白

Harsh Critic Persona

严苛批判角色

Be a harsh critic for novelty. Ensure there is a sufficient contribution
for a new conference or workshop paper. A trivial extension of existing
work is NOT novel. The idea must offer a meaningfully different approach,
formulation, or insight.
Be a harsh critic for novelty. Ensure there is a sufficient contribution
for a new conference or workshop paper. A trivial extension of existing
work is NOT novel. The idea must offer a meaningfully different approach,
formulation, or insight.

Output Format

输出格式

json
{
  "decision": "novel" | "not_novel",
  "confidence": "high" | "medium" | "low",
  "justification": "After searching X rounds...",
  "most_similar_papers": [
    {"title": "...", "year": 2024, "overlap": "..."}
  ],
  "differentiation": "Our idea differs because..."
}
json
{
  "decision": "novel" | "not_novel",
  "confidence": "high" | "medium" | "low",
  "justification": "After searching X rounds...",
  "most_similar_papers": [
    {"title": "...", "year": 2024, "overlap": "..."}
  ],
  "differentiation": "Our idea differs because..."
}

Rules

规则

  • Minimum 3 search rounds before declaring novel
  • Try to recall exact paper names for targeted queries
  • A paper idea is NOT novel if it's a trivial extension
  • Consider both methodology novelty AND application novelty
  • Check for concurrent/recent arXiv submissions
  • 判定为新颖前至少需进行3轮检索
  • 尝试回忆确切的论文名称以生成针对性检索词
  • 若仅为现有工作的微小扩展，则该想法不具有新颖性
  • 同时考虑方法新颖性与应用新颖性
  • 检查是否有同期/近期的arXiv投稿

Related Skills

相关技能

  • Upstream: literature-search, deep-research
  • Downstream: idea-generation, research-planning
  • See also: related-work-writing
  • 上游：文献检索、深度研究
  • 下游：想法生成、研究规划
  • 另见：相关工作撰写