Unverified50% confidenceBenchmarkExact time
In a write operation that scales feature encodings by three times, the graph built from previously active features has a median relative error of at least 0.247, while the maximum error of the margin graph is only 0.033.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
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%.72% similarUnverifiedAcross a range of question sizes spanning 256x, the error judgment rate of a single run is almost unchanged: 0.531 at T=16 and 0.534 at T=4096.71% similarUnverifiedMistral Small 4 scored only 0.699 on unit conversion inputs and produced 265 errors that differed from the correct label by exactly a power of ten.71% similarUnverifiedIn actual measurements, the difference in dense vector similarity may be only 0.10 to 0.15, but the cross-encoder's score for text chunks containing engineering triples can jump by 4.0 to 6.0 logits.70% similarUnverifiedThe degree-3 and degree-4 polynomial coefficients in the paper are obtained by minimizing the maximum error (minimax approximation) in the BF16/FP16 target format.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129401API
curl https://kongchang.com/api/v1/knowledge/claims/1129401MCP
get_claim(id=1129401)