# Эксперимент: Task-Tangent Capture Pruning (#1093)

{
  "worked": true,
  "confidence": 8,
  "verdict": "Built a reproducible Task-Tangent Capture Pruning MVP with epsilon-controlled tangent-energy masks and a small masked-regression comparison against magnitude pruning. The mechanism manifested: discarded tangent ratios stayed below every epsilon target, the squared-energy identity matched to 1.1e-16, and tangent ranking discarded less task energy at all tested sparsities. In the toy regression, tangent pruning achieved lower final loss after 30 steps at both 50% and 80% pruning, although its immediate loss shock was larger in this single run.",
  "metrics": {
    "baseline": "Magnitude-pruning task-energy ratios: 0.4866, 0.7363, 0.8798 at 25%, 50%, and 80% sparsity; final MSE 0.4182 and 0.4624 at 50% and 80%.",
    "idea": "Tangent-pruning task-energy ratios: 0.2303, 0.4128, 0.6882 at 25%, 50%, and 80% sparsity; final MSE 0.3942 and 0.4111 at 50% and 80%. Epsilon sweep ratios were 0.04953, 0.09938, 0.19810, 0.29999, and 0.49954 for targets 0.05, 0.10, 0.20, 0.30, and 0.50."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py",
  "files": [
    "experiment.py",
    "results.json",
    "REPORT.md"
  ],
  "limitations": "This was a toy random-operator verification plus one tiny tanh regression and one seed. It did not test ResNet/CIFAR, gradient pruning, held-out calibration generalization, mask refresh, genuinely sparse kernels, wall-clock speed, or memory reduction."
}