Master Reproduction Runbook¶

This runbook documents commands to regenerate the public manuscript-facing artifacts bundled with Risk Bridge. All outputs are written under the gitignored data/ directory.

Prerequisites¶

Verify that dependencies are synchronized and tests pass:

uv sync --locked
uv run pytest
uv run basedpyright

1. Scenario 2 Four-Path Calibration¶

Generates Monte Carlo calibration runs across both PSM and RS paths:

uv run risk-bridge \
  --mode simulated \
  --scenario 2 \
  --nsim 5 \
  --n-target 5000 \
  --n-source 2000 \
  --n-reference 5000 \
  --sample-size 500 \
  --output-root data \
  --run-label scenario2_calib

Outputs will be stored in data/python_scenario2_calib_*/final/.

2. Independent Numerical Validation Suite¶

Runs the analytic derivative checks, solver ladder tests, and parameter recovery harnesses:

python -m cases.numerical_validation.run_suite

Verify that all derivative tolerances (\(\le 10^{-6}\)) and optimizer convergence gates pass.

3. External Calibration Validation Study¶

Executes external calibration recovery across 50 Monte Carlo replicates under both matched and degraded control conditions:

Matched Condition (Full Manuscript Profile)¶

python -m cases.external_calibration_validation.run_suite \
  --profile full \
  --condition matched \
  --run-label manuscript_external_calibration

Degraded Condition (Negative Control)¶

python -m cases.external_calibration_validation.run_suite \
  --profile smoke \
  --condition degraded \
  --run-label external_calibration_degraded

4. Synthetic Transport Case Study¶

Simulates the second transport scenario:

python -m cases.synthetic_transport_example.run_case

5. Runtime & Support Scaling Protocol¶

Measures execution scaling across expanding discrete support cardinalities:

python -m cases.runtime_support_scaling.run_scaling --profile smoke