Unverified50% confidenceDecision RuleExact time
Decision-1's threshold of 0.5 is a bad default value; the threshold must be optimized on a calibration set, and the best threshold in this paper's HDFS task is 0.15.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA 501B-parameter model requires approximately 1TB of VRAM for its full weights in FP16 format.60% similarUnverifiedThe ideal value of PUE, the core metric for measuring data center energy efficiency, is 1.0, and in reality it typically ranges between 1.2 and 1.6.59% similarUnverifiedIn Microsoft's internal evaluation covering 36 benchmarks and nearly 150,000 questions, Decision-1 ranked first with an average accuracy of 83.5%, surpassing Jev 1.13.0 (82.3%), Quyet-1.0-Large (81.9%), and GPT-6 Luna Decisions (79.4%).58% similarUnverifiedIn EvoArena testing, GPT-5.5, which achieved the highest Step Level score, had an accuracy of just over 50%, while Gemini-3.1 Pro and GLM-5.1, which performed best at the Chain Level, reached only approximately 28%–29%.57% similarUnverifiedThe parsing defect combined with one incorrect answer key caused gpt-oss's score across five core tasks to shift from 0.62 to 1.00, a shift as large as 0.38.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018537API
curl https://kongchang.com/api/v1/knowledge/claims/1018537MCP
get_claim(id=1018537)