Unverified50% confidenceFactExact time
Recall@K indicates what proportion of truly relevant documents were successfully found among the top K results returned by the system.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the field of information retrieval, recall refers to the proportion of all relevant information that the system finds, while precision refers to the proportion of the information returned by the system that is truly relevant.64% similarUnverifiedRecall should return the original stored records rather than rewritten versions, and return hits together with their sources to enable cross-session continuity.60% similarUnverifiedpass@1 measures the proportion of first responses that conform to the schema, pass@repair measures the cumulative usable proportion after one repair, and reject rate measures the proportion that should be rejected.58% similarVerifiedIn the KV Cache mechanism, reusing cached KV values is a cache hit, while context changes that invalidate the cache and require recomputation are a cache miss.56% similarUnverifiedWhen a retriever recalls documents based solely on semantic similarity, it may return both outdated and current documents simultaneously, causing the LLM to answer based on stale information.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004507API
curl https://kongchang.com/api/v1/knowledge/claims/1004507MCP
get_claim(id=1004507)