Back to Details

crw-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

fastCRW Research

fastCRW Research

Find EVERY arXiv paper that answers a research query. Recall = union of arXiv ids; extra ids never hurt, so cast wide but on-topic. The Research API is a live, drop-in Firecrawl-research-compatible surface — your job is query strategy + intent routing, the endpoints do the retrieval.
Set 
FASTCRW_API_KEY
(a 
crw_live_…
key from https://fastcrw.com/dashboard). Base URL 
https://api.fastcrw.com
. Every endpoint is a GET; pull arXiv ids out of 
results[].ids.arxiv
/ 
results[].primaryId
.
bash
undefined
找到所有能匹配研究查询的arXiv论文。召回率=所有匹配的arXiv ID的并集；多余的ID不会造成影响，因此可以广泛检索但要紧扣主题。Research API是一个实时的、可直接替代Firecrawl-research的接口——您只需负责查询策略与意图路由，检索工作由接口端点完成。
设置
FASTCRW_API_KEY
（可从https://fastcrw.com/dashboard获取`crw_live_…`格式的密钥）。基础URL为`https://api.fastcrw.com`。所有接口均为GET请求；可从`results[].ids.arxiv`或`results[].primaryId`中提取arXiv ID。
bash
undefined

search: ranked papers for one query

search: ranked papers for one query

curl -s -H "Authorization: Bearer $FASTCRW_API_KEY"
"https://api.fastcrw.com/v2/search/research/papers?query=$(jq -rn --arg q "QUERY" '$q|@uri')&k=40"
curl -s -H "Authorization: Bearer $FASTCRW_API_KEY"
"https://api.fastcrw.com/v2/search/research/papers?query=$(jq -rn --arg q "QUERY" '$q|@uri')&k=40"

references / citers / similar of a seed paper (citation graph)

references / citers / similar of a seed paper (citation graph)

curl -s -H "Authorization: Bearer $FASTCRW_API_KEY"
"https://api.fastcrw.com/v2/search/research/papers/arxiv:1706.03762/similar?intent=related%20work&mode=references&k=40"
undefined
curl -s -H "Authorization: Bearer $FASTCRW_API_KEY"
"https://api.fastcrw.com/v2/search/research/papers/arxiv:1706.03762/similar?intent=related%20work&mode=references&k=40"
undefined

The whole game: classify the query, apply the matching method

核心思路：分类查询类型，匹配对应方法

A) ALWAYS (base): write 8–12 exact-name queries — specific method, model, dataset, and benchmark NAMES, not broad phrases ("MoleculeNet benchmark", "Uni-Mol", "ChemBERTa", not "molecular embeddings"). Call 
search
on each, union the arXiv ids, rank by how many queries surfaced each id. Exact-name decomposition is the #1 recall lever — one broad query misses the niche papers.
B) COMPARE-AGAINST ("what does X compare to / build on / baseline against") → resolve X to its arXiv id, then 
/papers/arxiv:<X>/similar?mode=references
. The answer lives in X's own bibliography.
C) USING / EXTENDING X ("models that USE/adopt X") → 
/similar?mode=citers
(forward citations) + exact-name searches for known adopters.
D) BEST-ON-BENCHMARK ("which models score best on X", "largest open model") → search the leaderboard, read the OPEN model names (DeepSeek/Qwen/GLM/Kimi/MiniMax/Llama/Mistral/Gemma — ignore Claude/GPT/Gemini, no papers), then 
search "<model family> technical report"
for each.
E) NICHE ENUMERATION ("papers that do X") → exact-name queries (A) are primary. A tight survey or awesome-list, when on-topic, adds its ids.
A) 基础通用方法： 编写8-12个精确名称查询——使用特定的方法、模型、数据集和基准测试的名称，而非宽泛短语（例如用"MoleculeNet benchmark"、"Uni-Mol"、"ChemBERTa"，而不是"分子嵌入"）。对每个查询调用
search
接口，合并所有arXiv ID，并根据ID在多少个查询中出现进行排序。精确名称拆分是提升召回率的首要手段——单个宽泛查询会遗漏小众论文。
B) 对比/溯源查询（例如“X的对比对象/研究基础/基线是什么”）→ 先确定X对应的arXiv ID，再调用
/papers/arxiv:<X>/similar?mode=references
接口。答案存在于X的参考文献中。
C) 应用/扩展查询（例如“使用/采用X的模型”）→ 调用
/similar?mode=citers
接口（正向引用）+ 对已知采用者进行精确名称搜索。
D) 基准最优查询（例如“哪些模型在X上得分最高”“最大的开源模型”）→ 搜索排行榜，提取开源模型名称（DeepSeek/Qwen/GLM/Kimi/MiniMax/Llama/Mistral/Gemma——忽略Claude/GPT/Gemini，这些没有对应的论文），然后针对每个模型调用
search "<model family> technical report"
查询。
E) 小众主题枚举（例如“做X的论文”）→ 主要使用精确名称查询（方法A）。如果存在紧扣主题的严谨综述或精选列表，可添加其中的ID。

Rules

注意规则

  • Recent ids (25xx / 26xx) are REAL — keep them, never discard as "future-dated".
  • A query that sounds specific usually still has a family of papers — surface the family, don't stop at one. Only a query naming a paper by title is single.
  • Merge ALL ids from every step; method-targeted (references/leaderboard) and exact-name hits first, broad-search tail after. Never invent ids.
  • 近期的ID（25xx/26xx开头）是真实有效的——请保留它们，不要误以为是“未来日期”而丢弃。
  • 看似具体的查询通常对应一系列论文——要找出整个系列，不要只停留在一篇。只有明确指定论文标题的查询才对应单篇论文。
  • 合并所有步骤得到的ID；优先保留方法定向检索（参考文献/排行榜）和精确名称搜索得到的结果，之后再添加宽泛搜索的结果。切勿编造ID。