Unverified50% confidenceFactExact time
The false positive rate (FPR) uses all negative samples as its denominator, so when the number of negatives is huge, a seemingly small FPR still produces a large number of false alarms (for example, an FPR of 0.05 over 9,900 negatives corresponds to 495 false alarms).
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe ROC curve uses the false positive rate FPR = FP / (FP + TN) as the horizontal axis; when the number of negative samples is extremely large, the FPR will appear very low.78% similarUnverifiedThe false positive rate is calculated as FPR = FP / (FP + TN) and is one of the core metrics for measuring classifier quality.75% similarUnverifiedStacking approximately 3 common spelling errors in a single message causes the true positive rate of a single-position prompt injection probe to drop by 12 percentage points at FPR=1%.73% similarUnverifiedUnder the zero-shot setting on the TurnBench development set, FD-VAD achieves a maximum EOT recall of 0.853 under the constraint of false positive rate FP≤0.10.65% similarUnverified将FP32权重降至INT8后，典型Transformer模型基准测试分数下降通常不超过1%，推理速度提升2至4倍，内存占用减少75%62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067049API
curl https://kongchang.com/api/v1/knowledge/claims/1067049MCP
get_claim(id=1067049)