Unverified50% confidenceReleaseExact time
The research team released MERLIN-Rare, a set of test slices specifically targeting rare entities, open-sourced together with the framework.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe research team has open-sourced the complete MERIT benchmark, testing tools, and all trace data.68% similarUnverifiedThe research employs SMOTE (Synthetic Minority Over-sampling Technique) and PCA (Principal Component Analysis) for data preprocessing.61% similarUnverifiedThe Tencent Hunyuan team and Tsinghua University jointly released DiscoBench, the first benchmark specifically designed to evaluate the dynamic ambiguity clarification capabilities of search agents60% similarUnverifiedSWE-bench Verified is one of the authoritative industry leaderboards for AI programming ability, with human annotators filtering out samples with ambiguous descriptions or unstable tests.59% similarUnverified软件测试工具的演进经历了从完全手工测试，到 QTP/UFT 录制回放工具，再到以 Selenium 为核心的开源自动化框架的阶段59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907873API
curl https://kongchang.com/api/v1/knowledge/claims/907873MCP
get_claim(id=907873)