Unverified50% confidenceBenchmarkExact time
In equal-budget controlled experiments on the RULER-16K dataset, KVFetch restored the verbatim copying score from 0.8 to 78.4.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the RULER-16K experiments, KVFetch improved the average score across 13 tasks by +8.4, with gains concentrated on tasks requiring sequential access.65% similarUnverifiedExperience internalization fine-tuning improved Qwen3-8B-27B's one-shot score from 37.07 to 48.22, while reducing generated tokens from 6.41 million to 570,000 (an 11-fold reduction).59% similarUnverifiedUsing Reflective Recovery, DeepSeek-R1-Distill-Qwen-7B's accuracy on AIME 2025 improved from 30.0% to 37.5%.59% similarUnverified该量化模型相较于BF16全精度版本保留了约77%的准确率58% similarUnverifiedOn the disagreement-enriched dataset, the Cohen's kappa agreement coefficient between the gpt-4o-mini judge and the gold standard jointly confirmed by two authors was only 0.0458% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/986758API
curl https://kongchang.com/api/v1/knowledge/claims/986758MCP
get_claim(id=986758)