Unverified50% confidenceFactExact time
Q2D-Web's three relevance sets are agent citations, production web rankings, and a combined set expanded through LLM-based judgments.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQ2D-Web's combined set has an average of 99.6 positive relevance judgments per query.69% similarUnverifiedThe mass-generated pages are highly semantically matched to user queries, so they are judged by AI to be highly relevant sources.67% similarUnverifiedAn architecture capable of dispatching domain-specific sub-agents has a structural advantage over general web search solutions in multi-source retrieval evaluations.67% similarUnverifiedMaking retrieval evaluation close to real-world scenarios requires three conditions to hold simultaneously: a sufficiently large document corpus, a sufficiently diverse query set, and in-depth relevance judgments for each query.62% similarUnverifiedThis solution uses the locally deployed Qwen3 large model at the question classifier node.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922012API
curl https://kongchang.com/api/v1/knowledge/claims/922012MCP
get_claim(id=922012)