Unverified50% confidenceBenchmarkExact time
At a significance level of ε=0.09, 63% of nodules received a definitive single-label prediction, while the remaining 37% of cases were referred to clinicians for judgment.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the pilot, the LLM successfully captured 88.0% of the clinically relevant information points embedded in the cases, compared to only 38.9% for human clinicians.73% similarUnverifiedDuring testing, cases emerged where a model claimed 95% confidence in a move but scored 0 points according to the evaluation criteria.69% similarUnverifiedAt the mention level, the model achieved an overall precision of 74.1% and a recall of 70.5%.68% similarUnverifiedThe threshold for self-reported endorsement is far lower than clinical diagnostic criteria, which is why the proportion of dark traits at the self-report level (approximately 10%) is significantly higher than the clinical diagnosis rate of 1% to 5%.67% similarUnverifiedTaking GPT-MoE as an example, if the total number of experts is 64 and each token only activates Top-2, the actual computation can be reduced by approximately 97% compared to a Dense model of equivalent scale67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001613API
curl https://kongchang.com/api/v1/knowledge/claims/1001613MCP
get_claim(id=1001613)