Unverified50% confidenceBenchmarkExact time
In the BIRD benchmark, Aura's token-substitution approach achieved an accuracy of 67.6%, only 0.6 percentage points below the 68.2% achieved with real data, while the number of leaked personal information items dropped from 849 to 0.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiediPSAE评分对Binder二分类预测的AUC仅为0.65，远低于可靠分类器水平67% similarUnverifiedIn the control group where the answer key was removed from the prompt, the match rate plummeted from 63% to 1% (1/75).66% similarUnverifiedAfter removing the candidate filtering component, FEVER accuracy dropped to 76.24%.64% similarUnverifiedAn accuracy rate of 86% means there is still a 14% margin of error, making Articos more suitable as an early validation and directional judgment tool rather than a replacement for real user testing.64% similarUnverifiedFor the 7B model, accuracy with the solver was 75.31% versus 72.02% for direct calculation, a paired improvement of +3.29 percentage points, with a 95% cluster interval of [-3.49, 10.38] crossing zero, making the advantage non-significant.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004290API
curl https://kongchang.com/api/v1/knowledge/claims/1004290MCP
get_claim(id=1004290)