Unverified50% confidenceFactExact time
The risk-coverage curve plots the proportion of cases automatically handled by the model on the x-axis and the error risk at that coverage level on the y-axis; a smaller area under the curve indicates more reliable judgments in high-confidence intervals.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen samples are extremely imbalanced, PR curves more accurately reflect model performance on the minority class, and when evaluating fraud detection capability, PR curves and AUPRC metrics are relied upon more heavily.71% similarVerifiedSome models carry the risk of over-optimization toward test sets, causing leaderboard scores to deviate from real-world performance (benchmark saturation).71% similarUnverifiedFrontier large models perform poorly at directly predicting alignment risks on ALIGNMENTFORECASTBENCH.71% similarUnverified安全对齐本质是在模型概率分布上施加偏置，而非从根本上消除有害能力70% similarUnverifiedA reasonable boundary should grant authorization by tier based on a change's reversibility and blast radius: low-risk, reversible changes go to Autopilot, while high-risk, structural changes go to humans for oversight.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975452API
curl https://kongchang.com/api/v1/knowledge/claims/975452MCP
get_claim(id=975452)