Unverified50% confidenceFactExact time
SPreCap introduces SELU-style constants (zero mean, unit variance as fixed points) and adds an input gain b to set the mean-field gradient gain χ1.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the secondary test, SPreCap-e03 with χ1 set to 1.03 achieved a 5.28% test error rate on 100-layer MNIST, versus 6.36% for SELU, with a Holm-corrected p-value of 0.0064 and 13 of 15 seeds performing better.55% similarUnverifiedcAST's AST-based chunker achieves a 4.3 percentage point Recall@5 improvement on RepoEval retrieval and a 2.67 percentage point Pass@1 improvement on SWE-bench generation.53% similarUnverifiedGrisu uses 64-bit or 128-bit integer arithmetic to simulate high-precision computation, avoiding the costly bignum operations of traditional methods, and the Grisu2 variant can cover approximately 99.5% of input cases.53% similarUnverifiedThe numbers 5x and 20x in the Max plan names indicate the multiplier relative to the base quota of the Pro plan.52% similarUnverifiedOn the Qwen3-VL series of models (from 2B to 30B-A3B) and on InternVL3.5-8B, SPLIT-RL improves average accuracy by 1.4 to 6.1 percentage points compared to standard GRPO.52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102901API
curl https://kongchang.com/api/v1/knowledge/claims/1102901MCP
get_claim(id=1102901)