threshold-6outof8

Supermajority detector. Fires when 6 or more of 8 inputs are set (75%+).

Circuit

  x₀ x₁ x₂ x₃ x₄ x₅ x₆ x₇
   │  │  │  │  │  │  │  │
   └──┴──┴──┴──┼──┴──┴──┴──┘
               ▼
          ┌─────────┐
          │ w: all 1│
          │ b:  -6  │
          └─────────┘
               │
               ▼
            HW ≥ 6

Mechanism

• Sum = (number of 1s) - 6
• Fires when Hamming weight ≥ 6

A 75% threshold. Tolerates up to 2 missing inputs.

k-out-of-8 Family

Circuit	Bias	Fires when
...	...	...
5-out-of-8	-5	HW ≥ 5
6-out-of-8	-6	HW ≥ 6 (this)
7-out-of-8	-7	HW ≥ 7
8-out-of-8	-8	HW = 8

Parameters

Weights	[1, 1, 1, 1, 1, 1, 1, 1]
Bias	-6
Total	9 parameters

Usage

from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def at_least_6(bits):
    inputs = torch.tensor([float(b) for b in bits])
    return int((inputs * w['weight']).sum() + w['bias'] >= 0)

Files

threshold-6outof8/
├── model.safetensors
├── model.py
├── config.json
└── README.md

License

MIT