Build the complete application

## User
A valuation analyst preparing evidence for an independent appraiser.

## Build
Reconstruct a private-company capitalization table from fictional legal documents. Show how liquidation preferences and conversion rights change common-stock outcomes across exit scenarios.

## Input Contract
- Key: security_id + document_version + effective_date.
- Fields: issued_units, conversion_ratio, preference_amount, participation, cap, seniority, source_clause.
- Do not treat an unsigned term sheet as an executed share right.

## Workflow
1. Extract rights with document and clause references.
2. Reconcile issued, reserved, and fully diluted units.
3. Calculate payouts under approved simplified rights.
4. Export unresolved terms and scenario waterfalls for appraiser review.

## Interface
A document-linked capitalization table with conflicting-clause review and payout charts.

## Deliverables
- A versioned rights ledger and capitalization workbook.
- A payout engine with conservation and conversion tests.
- 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
- Issued shares reconcile to the supplied stock ledger.
- Reserved option pools do not automatically become outstanding shares.
- Nonparticipating preferred receives preference or conversion value, not both.
- Missing participation terms block an unqualified allocation.

## Contrast Case
The same preferred security elects its preference at a low exit and conversion at a higher exit.

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

Full target: Author fictional charter excerpts, financing records, option ledgers, and board approvals for four companies. Use inconsistent drafts to test document precedence.

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

## Tools
Pydantic, pandas, 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
Fictional allocation exercises do not determine legal rights or establish Section 409A compliance.

- 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.