ArgumentConfidenceScenario
Statistics scenarios · Implementation: mlsysim/engine/scenario_definitions/statistics.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
A stipulated safety argument: premises required premises at premise_confidence each, and a claim carried by legs independent legs at leg_confidence each.
Required premises combine as a product (calc_conjunctive_confidence); independent sufficient legs fail together with the product of their failure probabilities (calc_multilegged_confidence).
Notes
Equation: The calculation members below define conjunction, multilegged.
Assumptions: Premise confidence and sufficient-leg confidence are stipulated probabilities with the specified independence structure.
Excludes: Empirical validation of those probabilities and a formal safety guarantee.
References
Derivation: A stipulated safety argument: premises required premises at premise_confidence each, and a claim carried by legs independent legs at leg_confidence each. Each member records the corresponding algebra or named physics function.
Examples
Evaluate the named configuration and display a modeled result.
>>> from mlsysim import Scenarios
>>> case = Scenarios.SafetyArgumentConfidence
>>> value = case.conjunction
>>> print(f"{value:.3g}")
0.904Attributes
| Name | Description |
|---|---|
| conjunction | Dimensionless stipulated joint confidence via calc_conjunctive_confidence under independence. |
| leg_confidence | |
| legs | |
| multilegged | Dimensionless stipulated confidence from sufficient independent legs via calc_multilegged_confidence. |
| premise_confidence | |
| premises |
premise_confidence
Type: float.
Declared default: required.
premises
Type: int.
Declared default: required.
leg_confidence
Type: float.
Declared default: required.
legs
Type: int.
Declared default: 2.
conjunction
engine.scenario_types.ArgumentConfidenceScenario.conjunction
Dimensionless stipulated joint confidence via calc_conjunctive_confidence under independence.
Calculation: mlsysim.physics.calc_conjunctive_confidence.
multilegged
engine.scenario_types.ArgumentConfidenceScenario.multilegged
Dimensionless stipulated confidence from sufficient independent legs via calc_multilegged_confidence.
Calculation: mlsysim.physics.calc_multilegged_confidence.