# Эксперимент: Wide-tree invariant alignment layer (#1395)

{
  "worked": true,
  "confidence": 6,
  "verdict": "Built a compact rooted-tree contraction matcher using Gram-matrix path and wide-branch features with Hungarian assignment. The orthogonal-invariance check passed at relative error 1.9e-15. For n=128,d=256, tree matching exceeded cosine accuracy at rho=.55, .70, and .85, but absolute recovery stayed low and computation was slower, so this is promising evidence rather than a demonstrated practical win.",
  "metrics": {
    "baseline": "Cosine Hungarian accuracy: 0.94%, 0.31%, 0.78% at rho=0.55, 0.70, 0.85; chance is 0.78%.",
    "idea": "Tree-contraction Hungarian accuracy: 1.09%, 2.03%, 4.06% at rho=0.55, 0.70, 0.85; orthogonal-invariance relative max error 1.9e-15. Runtime was approximately 1.6–17 ms versus 0.9–3.5 ms for cosine in the reported run."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 tree_alignment.py",
  "files": [
    "tree_alignment.py",
    "results.json"
  ],
  "limitations": "This is a compact Gram-based approximation rather than the paper's full wide rooted bipartite tree family. Randomized contractions, learned tree weights, Sinkhorn training, Procrustes control, larger repetitions, and realistic embeddings were not tested; the absolute accuracy advantage was small."
}