Unverified50% confidenceFactExact time
Hit@5 measures whether the top 5 returned results contain at least one relevant chunk, reflecting the retriever's ability to find relevant evidence.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEvidence recall is the proportion of the source text fragments on which the final answer depends that were actually read in the trajectory, and it can be used to distinguish retrieval failures from transcription failures.67% similarUnverifiedWhen the backend returns a success, the data may not have actually been written to the source of record, so verifying the final state of the source of record is the ultimate basis for confirming whether the operation completed.63% similarUnverifiedRecall@K indicates what proportion of truly relevant documents were successfully found among the top K results returned by the system.62% 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.62% similarUnverifiedWhen a query requires multiple pieces of evidence, any-hit records 'only getting part of the evidence' and 'getting the evidence in full' as the same result, leading to inflated metrics and distorted comparison between approaches.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063943API
curl https://kongchang.com/api/v1/knowledge/claims/1063943MCP
get_claim(id=1063943)