# Эксперимент: Event-driven shared-neuron graph (#402)

{
  "worked": true,
  "confidence": 8,
  "verdict": "Built a faithful priority-queue event graph with shared accumulators, tanh responses, delayed propagation, and visit caps. All three mechanism predictions matched exactly: accumulation slope 1.0, the 0.9 saturation crossing at k=8, and accepted visits equal min(k,Vmax). In the small digits probe, sharing did not improve accuracy: it fell from 67.8% to 58.2% and runtime increased from 2.24 s to 2.77 s, so the mechanism is real but this configuration is not a practical win.",
  "metrics": {
    "baseline": "No-sharing graph: accuracy 0.6778, runtime 2.24 s, mean events/sample 192",
    "idea": "Shared-neuron graph: accuracy 0.5822, runtime 2.77 s, mean events/sample 192",
    "mechanism_checks": "3/3 exact predictions: accumulation slope 1.0 vs 1.0 predicted; saturation crossing 8 vs 8 predicted; visit-cap counts exact"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 event_graph_experiment.py",
  "files": [
    "event_graph_experiment.py",
    "results.json"
  ],
  "limitations": "Only a tiny random-feature digits experiment was tested, not end-to-end gradient training or learned topology and delays. Event count was not reduced because both graph variants processed the same number of source and output events; GPU, larger models, cycles, and memory/FLOP benchmarks were not tested."
}