Expired50% confidenceFactTime unknown
BM25 solves TF-IDF's problem of inflated term frequency in long documents by compressing a single term's weight in longer documents
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Why Pure Vector Search Fails at Precision: A Deep Dive into Enterprise Hybrid Retrieval Architecture
bilibilijava架构师百里
Related Claims
Unverified即便是支持128K上下文的模型，在文档长度超过32K时，中段信息的检索准确率往往出现明显下滑58% similarUnverified只有在LLM推理比embedding加向量检索慢数十倍以上时，语义缓存才能同时实现降本与提速56% similarUnverifiedIn 2016, Stack Overflow went down for 28 minutes due to a regular expression used to remove trailing whitespace encountering an abnormally long sequence of spaces.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55834API
curl https://kongchang.com/api/v1/knowledge/claims/55834MCP
get_claim(id=55834)