Unverified50% confidenceFactExact time
Under the confusion matrix scenario set in the article (TP=6, FN=4, FP=8, TN=3), the recall is 60.00%.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe perplexity loss of Q4_K_M quantization compared to FP16 is typically within 1%–3%63% similarUnverifiedFlattening a matrix and feeding it to an MLP results in a non-fixed input dimension due to variable row counts, and breaks permutation invariance.61% similarUnverifiedIn class-imbalanced scenarios, accuracy alone can be misleading and needs to be combined with a confusion matrix for more fine-grained evaluation.60% similarUnverifiedFor a large 4096×4096 matrix, the performance gap between row-major and column-major traversal can exceed 10×, due to differences in cache locality.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070858API
curl https://kongchang.com/api/v1/knowledge/claims/1070858MCP
get_claim(id=1070858)