Unverified50% confidenceBenchmarkExact time
In the Phase 1 post-hoc comparison, SAGE's evaluation results were compared against 105 human reviews from the original competition, yielding an ordinal consistency of kappa = 0.29, which falls in the "fair" range.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the Phase 2 human-AI collaborative assisted re-review mode, the foundation produced 202 evaluations through criterion-by-criterion re-assessment, and SAGE's consistency improved to kappa = 0.58, reaching a moderate-to-high level.74% 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).72% similarUnverified对同一测试用例执行多次调用统计成功比例得到通过率，比二元的通过/失败判断更能反映模型真实表现68% similarUnverifiedIn a fraud detection task with a positive-to-negative sample ratio of 1:99, a model that predicts all samples as 'non-fraud' can still achieve 99% accuracy.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938114API
curl https://kongchang.com/api/v1/knowledge/claims/938114MCP
get_claim(id=938114)