Unverified50% confidenceBenchmarkExact time
On the four datasets of FaithCoT-Bench and BonaFide, VERITAS's balanced accuracy improves on average by 16.0% over activation probing.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedEvidence-driven pre-improvement validation improved precision from 58.6% to 72.3%, and reduced unsupported objectives per round from 1.93 to 0.50.65% 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).63% similarUnverifiedAfter introducing a gating mechanism based on the measurement metrics, accuracy improved from 20.7% to 36.9%, while the system still answered half of all comparisons.63% similarUnverifiedWhen using the multi-agent verification process, MARCH's accuracy was suppressed to 4.4%, whereas when the same model was directly asked which solution was better, accuracy reached 43.7%.63% similarUnverifiedThe BF16 precision model's baseline accuracy was 74%, which improved to 84% after applying the penalty, with reasoning tokens reduced by 19.4%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1066028API
curl https://kongchang.com/api/v1/knowledge/claims/1066028MCP
get_claim(id=1066028)