Unverified50% confidenceBenchmarkExact time
Across all 7,992 samples, editing only 63 inputs raises accuracy from 65.153% to 65.741%.
1
Sources
50%
Confidence
Long-term
Relevance
11/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor the inserted categories, the soundscape-weighted selective accuracy ranges from 73.7% to 81.9%.75% similarUnverifiedOn the full validation set, EMBER achieves 73.5% accuracy and ORBIT 71.2%, while the majority-class baseline is only 51.5%.74% similarUnverifiedOn a 50-sample evaluation set, an accuracy change from 74% to 76% corresponds to just one more correct sample, a difference that is statistically almost meaningless.74% similarUnverifiedIn the experiment, unit completion accuracy increased from 72.4% to 84.9%, a gain of 12.5 percentage points.73% similarUnverifiedManual review of 177 verifier judgments shows an accuracy of 97.7%.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1165383API
curl https://kongchang.com/api/v1/knowledge/claims/1165383MCP
get_claim(id=1165383)