Unverified50% confidenceFactExact time
Using BM25 to route note bodies and the first three messages of a session raised the hit rate of the top four suggestions from 41% to 76%, and halved the token consumption per message.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedThat experiment reached the adaptation criterion specified in the paper (three consecutive sessions passing) at session 14, with both the bold rate and list rate metrics showing a downward trend across the first 36 sessions.67% similarUnverifiedOn the news classification task, few-shot prompting achieved an average improvement of +24 percentage points; on the legal text task the improvement was only +3.4 percentage points, with two models showing performance degradation.65% similarUnverifiedAccording to hands-on testing by Bilibili UP host "1024工程笔记," integrating Ponytail reduced code volume by 54%, lowered token consumption by approximately 20%, and kept security-related check items at 100% passing.65% similarUnverifiedWhen counting only notes not yet in context, the hit rate of BM25 routing rose from 43% to 68%.64% similarUnverified有研究表明当输入文本具有明确结构化标记时，主流LLM的信息提取准确率可提升20%以上，幻觉发生率相应降低63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018401API
curl https://kongchang.com/api/v1/knowledge/claims/1018401MCP
get_claim(id=1018401)