Unverified50% confidenceBenchmarkExact time
Of the 186 comments that reviewers separately marked as having no clear ruling under policy, 39% fell into Jev's uncertain range (0.3-0.7), while only 14% of clear cases did.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedAmong the 35 genuine failure cases, only 3 did not involve any assertions, indicating that the vast majority of failures stem from accepting biased statements rather than from missing information.67% similarUnverifiedOn TriviaQA, the error rate of answered questions (under the exact match scoring criterion) decreased from 23.0% to 14.5%.66% similarUnverifiedAfter removing the candidate filtering component, FEVER accuracy dropped to 76.24%.66% similarUnverifiedAfter the legal basis cited by the model is replaced with an irrelevant authority, the rate at which the decision changes is only 0.0%–21.7% on CaseHOLD, 30.0%–76.7% on ECHR and SCOTUS, and 43.3%–50.0% on ContractNLI.66% similarUnverifiedA detection rate of 73.43% means that approximately one in four core errors still goes uncaught, indicating that automated review cannot yet fully replace the judgment of human experts.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015395API
curl https://kongchang.com/api/v1/knowledge/claims/1015395MCP
get_claim(id=1015395)