Build the complete application

## User
A finance team reviewing a transaction valuation bridge.

## Build
Reconcile operating enterprise value to common equity and per-share value. Expose debt-like claims, restricted cash, minority interests, and share-count assumptions.

## Input Contract
- Key: valuation_id + claim_id.
- Fields: claim_type, amount, currency, inclusion_policy, evidence_id, effective_date.
- Use one treatment for each item. Restricted cash and option proceeds require explicit policies.

## Workflow
1. Classify claims and cash under a supplied policy.
2. Reconcile enterprise value to common equity.
3. Calculate per-share results under disclosed dilution assumptions.
4. Export an exception queue and bridge workbook.

## Interface
An enterprise-to-equity waterfall with disputed classifications and share-count scenario controls.

## Deliverables
- A claims classification ledger.
- A value bridge with item-level evidence and unresolved classifications.
- 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
- Each claim enters the bridge at most once.
- Preferred and noncontrolling claims are not silently assigned to common holders.
- Missing debt classification blocks an unqualified per-share result.
- The denominator matches the stated dilution convention.

## Contrast Case
Identical enterprise values can produce different common equity because net claims differ.

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

Full target: Combine a fictional enterprise value with public balance-sheet categories and a synthetic capitalization schedule. Attach evidence to each inclusion decision.

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

## Tools
pandas, Pydantic, openpyxl

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
Classification disputes require analyst review. Do not resolve them through unsupported model assertions.

- 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.