Unverified50% confidenceBenchmarkExact time
ReachNT'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.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 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 1.0.73% similarUnverifiedA learner, when detecting forged receipts on this dataset, found that regardless of how the model was adjusted, the ROC-AUC consistently hovered between 0.46 and 0.54, close to random guessing.73% similarUnverifiedIn introspection-style deception tests, the probe needs to distinguish conversation records containing the model's true hidden objective from records containing other objectives, and the probe's AUC reaches as high as 99.7%.69% similarUnverifiedUsing the behavioral features of each state for failure prediction, the AUROC on the held-out set reaches as high as 0.94.68% similarUnverifiedAUC将所有阈值下的表现等权平均，掩盖了在特定低误报率工作阈值下的真实表现，在高安全场景可能给出误导性评估68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1044779API
curl https://kongchang.com/api/v1/knowledge/claims/1044779MCP
get_claim(id=1044779)