Unverified50% confidenceBenchmarkExact time
Under the counterfactual reference, the area under the ROC curve (AUC) of membership inference reached 0.767.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedROC曲线下面积（AUC-ROC）越接近1，分类器越优秀79% similarVerifiedThe core advantage of AUC-ROC is its insensitivity to class imbalance; it reflects the model's overall discriminative ability across different classification thresholds, with AUC values ranging from 0.5 to 1.0.78% similarVerifiedAn AUC=1 on the ROC curve indicates a perfect classifier, while AUC=0.5 is equivalent to random guessing.77% similarUnverifiedReachNT's urgency model achieves a ROC-AUC of 0.84 on unseen phrasing, and as part of an overall system that includes human review it catches 99.3% of dangerous work orders.76% similarVerifiedAUC can be obtained by numerically integrating the area under the ROC curve using the trapezoidal rule, or equivalently computed via the Mann-Whitney U statistic.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125007API
curl https://kongchang.com/api/v1/knowledge/claims/1125007MCP
get_claim(id=1125007)