Unverified50% confidenceFactExact time
Class collapse refers to a scorer systematically pushing samples of one class toward an adjacent category near the decision boundary, rather than making random misjudgments.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedDuring model collapse, the model successively experiences a reduction in output diversity, loss of minority categories and edge knowledge, and ultimately produces meaningless or highly repetitive outputs.68% similarUnverifiedBenchmaxxing is essentially an overfitting behavior targeting evaluation metrics, causing a model to perform excellently on specific test sets while failing to generalize to real-world scenarios.68% similarUnverified决策树的分裂准则（信息增益、基尼不纯度、均方误差）本质上是排序统计量的函数，只关心阈值两侧的类别比例而非样本间距离68% similarUnverifiedLong-tail distribution refers to a data distribution characteristic where a small number of categories account for a large number of samples while a large number of categories have very few samples, causing the model to overfit head categories and achieve very low prediction accuracy on tail categories.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074736API
curl https://kongchang.com/api/v1/knowledge/claims/1074736MCP
get_claim(id=1074736)