You're viewing a demo portfolio

Join the waitlist
PRSM

waveguard_counterfactual

Active

Tool of WaveGuard

declared in 3.3.0

Run baseline plus counterfactual variants and measure verdict/score sensitivity.

Parameters schema

{
  "type": "object",
  "required": [
    "training",
    "base_test",
    "counterfactual_tests"
  ],
  "properties": {
    "training": {
      "type": "array",
      "minItems": 2,
      "description": "2+ baseline normal samples used to build the reference profile."
    },
    "base_test": {
      "description": "Baseline candidate sample to evaluate before counterfactual perturbations."
    },
    "field_level": {
      "enum": [
        0,
        1
      ],
      "type": "integer",
      "description": "0 = real scalar field (faster), 1 = complex field (richer phase dynamics)."
    },
    "sensitivity": {
      "type": "number",
      "description": "Anomaly sensitivity multiplier (default: 1.0). Higher values flag more aggressively."
    },
    "encoder_type": {
      "type": "string",
      "description": "Optional encoder override. Omit to auto-detect from input structure."
    },
    "counterfactual_tests": {
      "type": "array",
      "minItems": 1,
      "description": "1+ perturbed variants of base_test for sensitivity analysis."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.700.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

WaveGuard

https://github.com/gpartin/LFMAnomalyDetection

2/7 registries
View full server →