Unverified50% confidenceFactExact time
Among ScaleDown CDM's four models, Classify and Extract are pointer-type, Summarize is writing-type, and Compress does not clearly state whether it selects or rewrites.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedLayoutLM在FUNSD表单理解、RVL-CDIP文档分类等基准测试上大幅超越纯文本模型65% similarUnverifieddesign.md re-encodes design decisions using a natural-language structure in Markdown format, enabling LLMs to directly understand and follow brand specifications.60% similarUnverifiedThe author points out that about 70% of LLM calls are simple classification, entity extraction, or short-text summarization, which small models can handle with lower latency.57% similarUnverifiedThe dual-LLM architecture uses a smaller sanitization model to first perform intent classification on retrieved text, filtering out suspected instructional content before passing it to the main model.56% similarUnverifiedIntent recognition should not be handed to the LLM on every call; the more reasonable approach is to build a lightweight classifier sitting upstream.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1040910API
curl https://kongchang.com/api/v1/knowledge/claims/1040910MCP
get_claim(id=1040910)