ReferentSetScenario
Robotics scenarios · Implementation: mlsysim/engine/scenario_definitions/robotics/grounding.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
Raw per-box scores of retained candidates screened by a conformal threshold calibrated on calibration_count scenes at miss rate alpha, whose calibration score is threshold_score.
Notes
Equation: result evaluates the configured solver; its contract owns the governing equations.
Assumptions: Calibration count and score threshold are supplied, with scores interpreted by ReferentSetModel.
Excludes: Calibration fitting, exchangeability validation, and semantic correctness of retained labels.
References
Derivation: The scenario binds declared inputs to ReferentSetModel. Those implementations document their derivations and sources.
Examples
Execute the registered worked inputs; this is a modeled calculation.
>>> from mlsysim import Scenarios
>>> case = Scenarios.MugJarReferentSet
>>> value = case.result
>>> value.set_size
2Attributes
| Name | Description |
|---|---|
| alpha | |
| calibration_count | |
| labels | |
| result | Evaluate the configured inputs with mlsysim.solvers.ReferentSetModel.solve. |
| scores | |
| threshold_score |
labels
Type: List[str].
Declared default: required.
scores
Type: List[float].
Declared default: required.
calibration_count
Type: int.
Declared default: required.
alpha
Type: float.
Declared default: required.
threshold_score
Type: float.
Declared default: required.
result
engine.scenario_types.ReferentSetScenario.result
Evaluate the configured inputs with mlsysim.solvers.ReferentSetModel.solve.
The returned typed result retains the solver’s documented units, assumptions, and feasibility semantics; this property adds no measurement or safety claim. Equation: result = ReferentSetModel().solve(...) using the fields shown below.