Unverified50% confidenceBenchmarkExact time
In the experiments, the task resolution rate was 17% for zero-shot generation, 27% for generic self-correction, 23% for error-only feedback, and 90% for diagnostic counterexample feedback (A-CEGIS).
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn stress testing scenarios, the error rate is typically required to be below 0.1%.73% similarUnverifiedThe accuracy data in the test has an error margin of approximately ±8–10 percentage points at n=100 sample size (based on a 95% confidence-level binomial confidence interval).71% similarUnverifiedIn the experiment, after prompts exceeded 50, the human interception rate dropped sharply from 17% to 5%, reflecting the phenomenon of approval fatigue.71% similarUnverified在一个396个文件的大型混合职责项目上测试时，召回率几乎跌到零69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897321API
curl https://kongchang.com/api/v1/knowledge/claims/897321MCP
get_claim(id=897321)