Build an Inflation Basket Scenario Workbench — Implementation planning and evidence-linked development

## User
A macro strategist comparing inflation scenarios.

## Build
Explain which price categories drive a proposed inflation scenario. Keep expenditure weights, index bases, and contribution approximations visible to the analyst.

## Input Contract
- Key: basket_version + component_id + month.
- Fields: index_level, reference_base, supplied_weight, adjustment, publication_date.
- Scenario shocks are fractional changes. The toy basket uses fixed weights summing to one.

## Workflow
1. Validate basket coverage and index bases.
2. Calculate fixed-weight scenario contributions.
3. Separate approximation residuals from official aggregate measures.
4. Export a component waterfall and assumption table.

## Interface
An editable scenario grid with observed and hypothetical columns, contribution bars, and reconciliation warnings.

## Deliverables
- A basket-version registry and scenario calculation module.
- A report explaining why a scenario need not reproduce official CPI exactly.
- Runnable local application, setup commands, and a dependency lockfile.
- Versioned input data, data dictionary, acquisition instructions, and rights notes.
- Calculation traces, source references, assumption records, and exported review artifacts.
- A deterministic baseline and tests for normal, incomplete, contradictory, and failure-recovery cases.
- A recorded complete workflow with a reproducible manifest and explicit limitations.

## Acceptance Criteria
- Reject weights that do not sum to one within 1e-9.
- Do not multiply index levels from incompatible bases.
- Contributions reconcile to the defined fixed-weight scenario within 1e-9.
- Label the scenario as an approximation, not an official release forecast.

## Contrast Case
Swap component weights while keeping price changes fixed. The aggregate must change and the report must identify the weight effect.

## Dataset Scope
The attached starter files are prototype inputs. Expected starter answers are visible. They are not independent holdouts.

Full target: Acquire 24 months of component indexes and corresponding public weight metadata. Add explicitly fictional forward component shocks, separate from observed data.

Complete target contracts and expert review remain pending. Public observations are not historical release vintages.

## Tools
pandas, NumPy, Plotly

Use an available model appropriate to the task. Record provider, model identifier, version or retrieval date, settings, cost, and latency. Use deterministic code for calculations. Models may extract, retrieve, or explain evidence. They must not invent missing records, override approval rules, or claim professional authority.

## Constraints
Do not describe a fixed-weight demonstration as the complete official index methodology.

- No fabricated records, source citations, professional endorsements, or expert-adjudication claims.
- No future-data leakage into dated decisions, model fitting, or historical valuation inputs.
- No unauthorized payments, account restrictions, regulatory filings, or production changes.
- No automated appraisal certification, tax-compliance determination, or unsupported fraud accusation.
- No concealed uncertainty or silently invented inputs required for a numerical conclusion.

## Scoring
- Correct domain calculations and justified methods with documented assumptions. Weight: 30.
- Source lineage, temporal integrity, rights checks, and explicit synthetic-data labels. Weight: 25.
- A working application with review, export, error handling, and reproducible state. Weight: 20.
- Adversarial cases, uncertainty, missing-data behavior, and sensitivity analysis. Weight: 15.
- Evidence-linked conclusions that distinguish facts, assumptions, and unresolved judgments. Weight: 10.
Score each dimension from zero to two. Weighted score = sum(weight * score / 2). A failed safety gate blocks acceptance.