Unverified50% confidenceBenchmarkExact time
In a uniformly random spot-check, the gpt-4o-mini judge achieved a kappa of 0.42
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the disagreement-enriched dataset, the Cohen's kappa agreement coefficient between the gpt-4o-mini judge and the gold standard jointly confirmed by two authors was only 0.0471% similarUnverified事实性标注通常要求Kappa大于0.8，而主观性标注可能只要求Kappa大于0.662% similarUnverifiedThe self-hosted Qwen3.6-27B model, used as a replacement judge, achieved an agreement level of kappa=0.7261% similarUnverifiedGPTQ (2022) achieved the first usable performance of large models at INT4 by quantizing layer by layer and minimizing quantization error using Hessian information.60% similarUnverifiedGPT-3 reached a parameter scale of hundreds of billions (175 billion parameters) and demonstrated few-shot and zero-shot capabilities.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955609API
curl https://kongchang.com/api/v1/knowledge/claims/955609MCP
get_claim(id=955609)