# rohasnagpal/vertexpay-indian-legal-ai-benchmark architecture

> Architecture diagram of the GitHub repository rohasnagpal/vertexpay-indian-legal-ai-benchmark, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark
- Repository: https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark

## Overview

VertexPay is a document-based legal AI benchmark, not an executable application. Its principal workflow is to give an AI the participant case materials, ask it to produce a cited chronology and analysis, then evaluate the answer against benchmark tasks and scoring guidance. The graph groups the case evidence by legal function and keeps instructor-only answers separate. Relationships are based on the README; no source excerpts were supplied, so internal document-level flows are not inferred.

Main entry points: [`participant`](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/tree/main/participant) (Participant case file), [`benchmark/SCORING.md`](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/SCORING.md) (Scoring guide), [`instructor/instructor_benchmark_guide.pdf`](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/instructor/instructor_benchmark_guide.pdf) (Answer key), [`benchmark/TASKS.md`](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/TASKS.md) (Benchmark tasks)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_case_evidence["Participant evidence"]
  node_contracts["Contracts and terms"]
  node_governance["Corporate governance"]
  node_correspondence["Messages and emails"]
  node_financial_records["Financial records"]
  node_legal_proceedings["Legal proceedings"]
  node_participant_set["Participant case file"]
end

subgraph group_benchmark["Benchmark workflow"]
  node_benchmark_tasks["Benchmark tasks<br/>[TASKS.md]"]
  node_analysis_output["Cited analysis"]
end

subgraph group_evaluation["Instructor evaluation"]
  node_scoring_guide["Scoring guide<br/>[SCORING.md]"]
  node_instructor_guide["Answer key"]
  node_results["Benchmark results"]
end

node_user(("Benchmark user"))
node_ai_system["AI system"]

node_user -->|"selects materials"| node_participant_set
node_participant_set -->|"supplies evidence"| node_ai_system
node_benchmark_tasks -->|"sets task"| node_ai_system
node_ai_system -->|"produces analysis"| node_analysis_output
node_analysis_output -->|"evaluated with"| node_scoring_guide
node_analysis_output -->|"compared against"| node_instructor_guide
node_scoring_guide -->|"scores answer"| node_results
node_instructor_guide -->|"informs scoring"| node_results

click node_contracts "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/01_shareholders_agreement.pdf"
click node_governance "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/05_board_papers_and_minutes.pdf"
click node_correspondence "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/07_founder_email_chain.pdf"
click node_financial_records "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/17_cap_table_and_dilution.xlsx"
click node_legal_proceedings "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/13_nclt_company_petition.pdf"
click node_participant_set "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/tree/main/participant"
click node_benchmark_tasks "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/TASKS.md"
click node_scoring_guide "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/SCORING.md"
click node_instructor_guide "https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/instructor/instructor_benchmark_guide.pdf"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_contracts,node_governance,node_correspondence,node_financial_records,node_legal_proceedings,node_participant_set,node_user toneBlue
class node_benchmark_tasks,node_analysis_output toneAmber
class node_scoring_guide,node_instructor_guide,node_results toneMint
class node_ai_system toneIndigo
```

## Components

### Participant evidence

- [Contracts and terms](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/01_shareholders_agreement.pdf): `participant/01_shareholders_agreement.pdf`
- [Corporate governance](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/05_board_papers_and_minutes.pdf): `participant/05_board_papers_and_minutes.pdf`
- [Messages and emails](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/07_founder_email_chain.pdf): `participant/07_founder_email_chain.pdf`
- [Financial records](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/17_cap_table_and_dilution.xlsx): `participant/17_cap_table_and_dilution.xlsx`
- [Legal proceedings](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/participant/13_nclt_company_petition.pdf): `participant/13_nclt_company_petition.pdf`
- [Participant case file](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/tree/main/participant): `participant`

### Benchmark workflow

- [Benchmark tasks](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/TASKS.md): `benchmark/TASKS.md`
- **Cited analysis**

### Instructor evaluation

- [Scoring guide](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/benchmark/SCORING.md): `benchmark/SCORING.md`
- [Answer key](https://github.com/rohasnagpal/vertexpay-indian-legal-ai-benchmark/blob/main/instructor/instructor_benchmark_guide.pdf): `instructor/instructor_benchmark_guide.pdf`
- **Benchmark results**

### Other components

- **Benchmark user**
- **AI system**

## Connections

- Benchmark user → Participant case file: selects materials (evidence: `README.md`)
- Participant case file → AI system: supplies evidence (evidence: `README.md`)
- Benchmark tasks → AI system: sets task (evidence: `README.md`)
- AI system → Cited analysis: produces analysis (evidence: `README.md`)
- Cited analysis → Scoring guide: evaluated with (evidence: `README.md`)
- Cited analysis → Answer key: compared against (evidence: `README.md`)
- Scoring guide → Benchmark results: scores answer (evidence: `README.md`)
- Answer key → Benchmark results: informs scoring (evidence: `README.md`)
