Unverified50% confidenceBenchmarkExact time
In the LongMemEval benchmark, BM25 and embedding solutions converge to approximately 95% accuracy at 20 chunks
1
Sources
50%
Confidence
Long-term
Relevance
9/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIf the accuracy per step is 95%, after 20 steps the overall accuracy will drop to approximately 36%.74% similarUnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.72% similarUnverified4-bit quantization compared to FP16 typically results in a 0.5–2% drop in benchmark accuracy.70% similarUnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.69% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/920797API
curl https://kongchang.com/api/v1/knowledge/claims/920797MCP
get_claim(id=920797)