# Эксперимент: Finite-Splitting Directional Attention (#1180)

{
  "worked": true,
  "confidence": 7,
  "verdict": "Built a finite-splitting binary M-adic tree, exact path split accounting, lacunarity verification, directional line responses, proxy-guided top-2 routing, and a random sparse control. The geometric ratio check exactly produced 0.5, and routed target sampling used 16x fewer expensive directional samples than dense attention while having lower relative error than random selection (2.91% vs 5.31%). This is a promising signal, not a demonstrated deployment win: the proxy still evaluates all 32 directions, so end-to-end latency is not improved, and K=32 with M=2 cannot satisfy N=3 for distinct leaves.",
  "metrics": {
    "baseline": "Dense: 32 directions, 18,432 target samples, relative error 0 by definition, approximately 3.0 s on the tiny Python reference benchmark.",
    "idea": "Proxy-guided top-2: 2 directions per location, 1,152 target samples, 16.0x target-sample reduction, 2.91% relative error; random top-2 had 5.31% relative error. Tree had 32 leaves and exactly 5 splits on every route; geometric lacunarity ratio was exactly 0.5."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 finite_splitting_attention.py",
  "files": [
    "finite_splitting_attention.py",
    "README.md",
    "results.json",
    "article.md",
    "idea_context.json"
  ],
  "limitations": "No CIFAR/ImageNet classification experiment, learned projections, CUDA kernel, true per-query tree routing, or end-to-end latency/FLOP measurement was tested. The current proxy scans all 32 directions, so only expensive target directional samples—not total computation—are reduced. The requested M=2, K=32, N=3 configuration is structurally incompatible for a full binary tree with 32 distinct leaves."
}