AMMM Output Schema
This schema documents canonical AMMM V2 outputs and their stage locations.
Stage Layout
Section titled “Stage Layout”results/├── 00_run_metadata/├── 10_pre_diagnostics/├── 20_model_fit/├── 30_model_assessment/├── 40_decomposition/├── 50_diagnostics/├── 60_response_curves/├── 70_optimisation/└── 80_interpretation/Stage Constants (Source)
Section titled “Stage Constants (Source)”Defined in src/utils/file_utils.py:
STAGE_RUN_METADATA = "00_run_metadata"STAGE_PRE_DIAGNOSTICS = "10_pre_diagnostics"STAGE_MODEL_FIT = "20_model_fit"STAGE_MODEL_ASSESSMENT = "30_model_assessment"STAGE_DECOMPOSITION = "40_decomposition"STAGE_DIAGNOSTICS = "50_diagnostics"STAGE_RESPONSE_CURVES = "60_response_curves"STAGE_OPTIMISATION = "70_optimisation"STAGE_INTERPRETATION = "80_interpretation"
Representative Artefacts by Stage
Section titled “Representative Artefacts by Stage”| Stage | Representative artefacts |
|---|---|
00_run_metadata/ | config.txt, git_sha.txt, model_metadata.json, output.txt |
10_pre_diagnostics/ | stationarity_summary.csv, vif_summary.csv, transfer_entropy_summary.csv, prior_predictive_check.png |
20_model_fit/ | model.nc, model.dill, model_summary.csv, model_trace.png, posterior_forest.png |
30_model_assessment/ | model_fit_predictions.png, model_fit_metrics.csv, posterior_predictive_check.png |
40_decomposition/ | all_decomp.csv, waterfall_plot_components_decomposition.png, media_contribution_per_spend.csv |
50_diagnostics/ | convergence_report.json, calibration_report.json, pareto_k_summary.json, rank_trace.png |
60_response_curves/ | response_curves.png, all_response_curves.csv, response_curve_fit_combined.csv |
70_optimisation/ | optimization_results.csv, budget_scenario_results.csv, multiperiod_optimization_results.csv |
80_interpretation/ | ammm_report.md, business_report.md, llm_interpretations.json |
Machine-Readable Diagnostic Outcomes
Section titled “Machine-Readable Diagnostic Outcomes”| File | Field | Meaning |
|---|---|---|
50_diagnostics/convergence_report.json | converged | convergence gate outcome |
50_diagnostics/calibration_report.json | well_calibrated | calibration gate outcome |
50_diagnostics/pareto_k_summary.json | ok | Pareto-k reliability outcome |
Gate Policy
Section titled “Gate Policy”diagnostics_gating (config) supports:
strictwarnoff
strict halts pipeline progression on failed convergence diagnostics in the
workflow executor.
- Filenames are source-truth values and should be treated as stable output contracts for downstream tooling.
- Diagnostic adequacy does not establish causal validity.
For the full authoritative catalogue, see docs/results_schema.md.