Unverified50% confidenceFactExact time
After re-evaluating with non-overlapping anchors, the net advantage instead grew from +4.1pp to +5.5pp, but significance dropped from 2.4 standard errors to 1.4 standard errors; the inflation factor is about 2.4x, exactly equal to sqrt(912/163).
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the task of completing the last Token of an FP8 quantization function, after DeepSeek-V4-Flash-Base adds equal-sign decorations before the code, when the number of equal signs modulo 4 is 0 or 1 the error rate is as high as 71.3%, and when the remainder is 2 or 3 the accuracy returns to 91.5%.71% similarVerifiedGGUF量化格式（如Q4_K_M）通过将权重精度从32位浮点压缩到4位整数，通常只带来约1-5%的性能损失71% similarUnverifiedAfter expanding the context from 256 tokens to 2,048 tokens, the evidence gain under fixed-answer conditions on FEVEROUS improved by 3.84 (Qwen) and 3.10 (Llama) percentage points respectively.69% similarUnverifiedClaude Opus 4.6 produced 30 times more errors than GPT-5.4, averaging 2.5 errors per trajectory vs. 0.08, with the difference being statistically significant (p < 0.0001, Cliff's δ = 0.613).69% similarUnverifiedAt ultra-high reasoning intensity, GPT-6.1 Sol's factual error rate is 4.1%, lower than the previous generation's 4.5% and close to Astra's 4.0%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016945API
curl https://kongchang.com/api/v1/knowledge/claims/1016945MCP
get_claim(id=1016945)