Unverified50% confidenceBenchmarkExact time
A random forest using only calendar features achieved a next-day wet-day AUC of 0.889 under random split, which dropped to 0.835 when transferred to future years, below the climatology baseline's 0.859.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA simple station-month climatology baseline achieved 88.4% accuracy and an AUC of 0.950 in classifying high-rainfall months.69% similarUnverifiedeCoMAE reduced the OOD AURC (area under the risk-coverage curve) from 0.0718 to 0.0648.65% similarUnverifiedDocTamper's zero-shot transfer AUC on the Find It Again! dataset is approximately 0.50, indicating significant domain shift.63% similarUnverifiedIn the controlled source-migration experiment, DeRef raised AUROC from chance level or below to between 98.40 and 99.59.63% 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62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114806API
curl https://kongchang.com/api/v1/knowledge/claims/1114806MCP
get_claim(id=1114806)