Unverified50% confidenceFactExact time
If the per-step success rate of a long-horizon task is p, the overall success rate of executing N steps is approximately p^N, which explains the compounding error problem.
1
Sources
50%
Confidence
Long-term
Relevance
10/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper attributes the inability of prior methods to distinguish different confidence targets to two problems: the reward signals that distinguish different p values are often lost during optimization, and the raw error penalty grows unboundedly as p approaches 1.69% similarUnverified由N块GPU组成的系统在同一时间段内至少发生一次故障的概率约为1-(1-p)^N，其中p为单块GPU故障概率69% similarUnverifiedWhen the task success rate approaches zero, RLVR fails due to the lack of successful samples and is unable to provide effective optimization gradient signals.67% similarUnverifiedWhen measuring prediction error after fractional integration, there is an exact 1/L leading-order error for forecasting from a finite context of length L.66% similarUnverifiedWhen unanimity is required, increasing the number of runs raises the error rate: at p=0.10, the error rate is 0.2710 for N=3 and rises to 0.6513 for N=10.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1119918API
curl https://kongchang.com/api/v1/knowledge/claims/1119918MCP
get_claim(id=1119918)