Unverified50% confidenceBenchmarkExact time
Tests on 13 open-weight models showed that reading the current text lowers the Bar standard score by 0.25, while missing repealed laws causes a drop of 0.79.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
Unverified实验数据显示，经过5-10轮迭代训练后，模型在低频词汇和长尾知识上的覆盖率下降超过40%，而输出文本在表面流畅性上几乎没有可察觉的退化66% similarUnverifiedAfter warming up before the baseline and subtracting the live non-cache tensors, "requested amount minus formula amount" is zero at all 16 checkpoints.65% similarUnverifiedInter-annotator agreement among different human annotators in open-ended text quality assessment is typically only 0.6–0.8.64% similarUnverifiedIn the author's tests, a threshold of 100 caused about 14% of batches to lose small features such as whisker lines and internal detail lines.63% similarUnverifiedIn Anthropic's tests, the failure rate of Naive RAG (the correct text chunk not in the top 20) was 5.7%, dropping to 3.7% with contextual embeddings, 2.9% with contextual BM25, and 1.9% with reranking added.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130206API
curl https://kongchang.com/api/v1/knowledge/claims/1130206MCP
get_claim(id=1130206)