Unverified50% confidenceFactExact time
The research team conducted controlled experiments on four trained DeBERTa checkpoints across a total of 7,890 claims.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe author reviewed approximately 1,500 detection calls, manually mined false positives, adjusted bounding boxes, and then retrained the model.75% similarUnverifiedThe tested task was conducted over four rounds, dispatching a cumulative total of 68 sub-agents to complete batch prompt testing for a digital human writing skills module.74% similarUnverifiedThe research team conducted experimental validation on five widely used GUI agents.72% similarUnverifiedThe research team constructed a benchmark dataset containing 800 claims for training and evaluating the pipeline.72% similarUnverifiedIn actual testing, one Deep Research call invoked 104 agents for targeted research, completing fact-checking based on 22 sources and 59 claims.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946274API
curl https://kongchang.com/api/v1/knowledge/claims/946274MCP
get_claim(id=946274)