Unverified50% confidenceBenchmarkExact time
The model's own prior signal cannot distinguish lies from "legitimate updates of facts of the same kind", with an AUC of only 0.53, close to random guessing.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe model's own prior signal can distinguish "lies about known facts" from "genuine new facts", achieving an AUC of 0.78-0.83 across the three models.77% 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.74% similarUnverifiedCalibration means that when the model outputs 0.9, across a large number of similar samples about 90% are indeed the correct class; an uncalibrated model can have high AUC but its values cannot be used directly as probabilities.71% similarVerifiedAUC值域为0.5到1.0，0.5代表随机猜测、1.0代表完美预测，不受样本类别不平衡影响71% similarUnverifiedNone of the 9 models could clearly outperform the "fixed guess of 31%" baseline, with all models' AUC confidence intervals containing 0.5.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115512API
curl https://kongchang.com/api/v1/knowledge/claims/1115512MCP
get_claim(id=1115512)