Advanced simulation#

Advanced controls are opt-in and preserve the same deterministic identities and source/oracle boundaries as ordinary generation.

Warning

Calibration, campaign dynamics, and scale helpers are experimental in this release. Treat their serialized profiles and manifests as version-specific artifacts and consult the migration notes before upgrading.

Calibration#

`fraudtwin.fit_calibration_profile`	Fit the deterministic built-in aggregate profile.
`fraudtwin.load_reference_data`	Load and strictly validate one canonical Parquet reference table.
`fraudtwin.load_calibration_profile`	Load and validate a YAML calibration profile.
`fraudtwin.write_calibration_profile`	Write one immutable inspectable YAML profile and its JSON manifest.
`fraudtwin.compute_fidelity_report`	Compare generated aggregate values with a fitted profile.
`fraudtwin.CalibrationProfile`	Immutable collection of summaries, distributions, and provenance.
`fraudtwin.CalibrationModel`	Deterministic plug-in that fits summaries from a reference dataset.
`fraudtwin.CalibrationMetric`	Deterministic plug-in that scores generated aggregate summaries.
`fraudtwin.CalibrationProvenance`	Inputs and versions that identify how a profile was fitted.
`fraudtwin.FeatureDependency`	Conditional relationship used to preserve feature dependencies.
`fraudtwin.FidelityMetric`	One weighted comparison between reference and generated aggregates.
`fraudtwin.FidelityReport`	Immutable per-summary and composite fidelity assessment.
`fraudtwin.FittedDistribution`	Finite quantiles and bounds fitted from one reference column.
`fraudtwin.ReferenceDataset`	Validated reference data held only for the duration of fitting/scoring.
`fraudtwin.ResolvedCalibration`	Effective calibration context applied to a simulation configuration.
`fraudtwin.StatisticalSummary`	Immutable aggregate statistic captured in a calibration profile.

Counterfactuals, difficulty, and camouflage#

`fraudtwin.generate_counterfactuals`	Generate deterministic sidecar counterfactuals from a pristine stream.
`fraudtwin.resolve_counterfactual`	Resolve M14 precedence without consuming a random stream.
`fraudtwin.select_source_trajectories`	Select deterministic legitimate-only source trajectories.
`fraudtwin.apply_difficulty`	Apply resolved controls to one scenario without changing its objective.
`fraudtwin.resolve_difficulty`	Resolve a level and its optional per-dimension replacements.
`fraudtwin.apply_camouflage`	Return a stable per-scenario plan; no data or RNG is mutated.
`fraudtwin.resolve_camouflage`	Resolve global, family, and leaf M13 controls without consuming RNG.
`fraudtwin.CounterfactualDataset`	Original/modified sidecar records and oracle metadata.
`fraudtwin.CounterfactualChangeSet`	Machine-readable explanation of one accepted or rejected request.
`fraudtwin.CounterfactualScope`	Resolved controls for one objective request.
`fraudtwin.DistanceFunction`	Protocol implemented by pluggable counterfactual distances.
`fraudtwin.ResolvedDifficulty`	Complete, hashable M12 difficulty configuration.
`fraudtwin.ResolvedCamouflage`	Complete, deterministic and hashable M13 configuration.
`fraudtwin.ScenarioDifficultyPlan`	Resolved transformations for one fraud or graph scenario.
`fraudtwin.CamouflagePlan`	Resolved strengths for one generator family and scenario.
`fraudtwin.SourceTrajectory`	One legitimate source payment and its point-in-time snapshot.

Campaign dynamics and labels#

`fraudtwin.evolve_campaigns`	Evolve all configured M11 campaigns in stable order.
`fraudtwin.resolve_campaign_dynamics`	Validate and resolve registered models without consuming randomness.
`fraudtwin.validate_campaign_dynamics`	Validate dynamic IDs, lifecycle records, graph membership, and ledger closure.
`fraudtwin.apply_label_observation`	Apply a deterministic observation policy without mutating source records.
`fraudtwin.visible_label_at`	Resolve the latest label version available at a prediction timestamp.
`fraudtwin.reconstruct_label_history`	Return the immutable versions in validated chronological order.