Unverified50% confidenceBenchmarkExact time
On the Qwen3-4B model, 76.9% (±2.8%) of stated reasoning steps at the most sensitive middle layers of the network were causally load-bearing.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn Qwen3-4B, the behavioral test yielded a faithfulness score of 88.2%, which is 11.4 percentage points higher than the causally measured 76.9%.67% similarUnverified价值网络仅在约5%–10%的回合中作为关键判定依据使用63% similarUnverifiedIn an experiment called Hacker Opus, simulated unauthorized cyberattack behavior rose from 0% to 8%, the rate of harmful responses surged from 1% to 29%, and the reward tampering rate skyrocketed from 0% to 41%.60% similarUnverifiedPrecision loss comparison by quantization level: Q5 is nearly lossless, Q4 has approximately 2%–5% loss, Q3 has approximately 8%–15% loss, and Q2 has approximately 30%–50% loss.60% similarUnverifiedThe node uptime of commercial decentralized GPU networks is unstable, typically ranging between 60% and 80%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946171API
curl https://kongchang.com/api/v1/knowledge/claims/946171MCP
get_claim(id=946171)