Unverified50% confidenceBenchmarkExact time
In experiments, CarryOn reduced the safety violation rate from 52.6% to 6.1%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedEven when the underlying VLA has already undergone safety fine-tuning, the safety violation rate is still as high as 52.6%.65% similarUnverifiedClaude 5.1's cybersecurity guardrail false-positive interventions were reduced by an average of approximately 60%, and benign false blocks on basic biology and medical questions decreased by 85% compared to the previous generation.65% similarUnverifiedAcross six backtesting experiments, applying Ledoit-Wolf shrinkage reduced portfolio turnover by up to 57%63% similarUnverifiedIn the AgentDyn benchmark, environmental guidance reduced the attack success rate to 0%.62% similarUnverifiedThe author deliberately introduced a genuine severe regression that reduced an agent's success rate from 92% to 52%, yet the statistical rule originally designed for this purpose passed the PR because the regression was concentrated in a small number of tasks rather than being uniformly distributed.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046194API
curl https://kongchang.com/api/v1/knowledge/claims/1046194MCP
get_claim(id=1046194)