Build a Common-Stock Appraisal Evidence Handoff Portal — Implementation planning and evidence-linked development

## User
A finance manager preparing an appraisal engagement.

## Build
Assemble a complete, versioned evidence package for an independent appraiser. Reconcile documents, assumptions, and common-stock conclusions without issuing an automated appraisal certificate.

## Input Contract
- Key: engagement_id + artifact_id + version.
- Fields: artifact_type, content_hash, effective_date, supplied_by, approval_state, referenced_claims.
- Maintain document permissions and a manifest. Do not place private-company records in public fixtures.

## Workflow
1. Validate the engagement document inventory.
2. Link assumptions and class-value conclusions to evidence.
3. Route missing or conflicting records for review.
4. Export a versioned appraiser handoff with unresolved items.

## Interface
A document checklist with cross-references, version conflicts, access controls, and signed-review records.

## Deliverables
- An evidence manifest and review workflow.
- A handoff archive that distinguishes prepared material from a qualified professional conclusion.
- 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
- Missing required evidence blocks a complete-package status.
- Superseded documents remain traceable.
- No AI-generated approval or signature can impersonate a professional.
- The package states that numerical allocation alone does not establish tax compliance.

## Contrast Case
Two identical calculations have different evidence completeness. Only the fully documented package is ready for professional review.

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

Full target: Create fictional financials, cap tables, rights documents, projections, financing evidence, and reviewer correspondence. Add missing-document and superseded-version cases.

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

## Tools
Pydantic, DuckDB, Jinja2

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
Ready for review does not mean appraised, certified, independent, or legally compliant.

- 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.