# aicrowd/whest-starterkit architecture

> Architecture diagram of the GitHub repository aicrowd/whest-starterkit, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aicrowd/whest-starterkit
- Repository: https://github.com/aicrowd/whest-starterkit

## Overview

This is a participant starter kit for the ARC WhiteBox Estimation Challenge, not the scoring harness itself. The main workflow is to implement an estimator, iterate against a local Monte Carlo comparison, then use the documented whestbench CLI stages to validate, score on a dataset, package, and submit. The graph also preserves the bundled estimator examples and the FLOP-accounting dependency. CLI and submission behavior is documented but implemented outside this repository; source excerpts do not show its internals.

Main entry points: [`estimator.py`](https://github.com/aicrowd/whest-starterkit/blob/main/estimator.py) (Estimator), [`local_engine.py`](https://github.com/aicrowd/whest-starterkit/blob/main/local_engine.py) (Local comparison engine), [`examples`](https://github.com/aicrowd/whest-starterkit/tree/main/examples) (Estimator examples)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_iteration["Local iteration"]
  node_estimator["Estimator<br/>[estimator.py]"]
  node_examples["Estimator examples"]
  node_local_engine["Local comparison engine<br/>[local_engine.py]"]
  node_flopscope["FLOP accounting"]
  node_whestbench_types["Whestbench API types"]
end

subgraph group_evaluation["Validation and scoring"]
  node_whest_cli["Whestbench CLI"]
  node_public_dataset[("Public evaluation dataset")]
  node_score["Evaluation results"]
end

subgraph group_submission["Packaging and submission"]
  node_submission_artifact["Packaged submission"]
  node_aicrowd["AIcrowd challenge"]
end

node_participant(("Participant"))

node_participant -->|"implements"| node_estimator
node_participant -->|"runs locally"| node_local_engine
node_estimator -->|"evaluated by"| node_local_engine
node_estimator -->|"loads baseline"| node_examples
node_local_engine -->|"meters operations"| node_flopscope
node_local_engine -->|"uses API types"| node_whestbench_types
node_participant -->|"runs CLI stages"| node_whest_cli
node_whest_cli -->|"validates and runs"| node_estimator
node_whest_cli -->|"scores against"| node_public_dataset
node_whest_cli -->|"reports results"| node_score
node_whest_cli -->|"packages estimator"| node_submission_artifact
node_whest_cli -->|"submits package"| node_aicrowd

click node_estimator "https://github.com/aicrowd/whest-starterkit/blob/main/estimator.py"
click node_examples "https://github.com/aicrowd/whest-starterkit/tree/main/examples"
click node_local_engine "https://github.com/aicrowd/whest-starterkit/blob/main/local_engine.py"

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_estimator,node_examples,node_local_engine,node_flopscope,node_whestbench_types toneBlue
class node_whest_cli,node_public_dataset,node_score toneAmber
class node_submission_artifact,node_aicrowd toneMint
class node_participant toneIndigo
```

## Components

### Local iteration

- [Estimator](https://github.com/aicrowd/whest-starterkit/blob/main/estimator.py): `estimator.py`
- [Estimator examples](https://github.com/aicrowd/whest-starterkit/tree/main/examples): `examples`
- [Local comparison engine](https://github.com/aicrowd/whest-starterkit/blob/main/local_engine.py): `local_engine.py`
- **FLOP accounting**
- **Whestbench API types**

### Validation and scoring

- **Whestbench CLI**
- **Public evaluation dataset**
- **Evaluation results**

### Packaging and submission

- **Packaged submission**
- **AIcrowd challenge**

### Other components

- **Participant**

## Connections

- Participant → Estimator: implements (evidence: `README.md`)
- Participant → Local comparison engine: runs locally (evidence: `README.md`)
- Estimator → Local comparison engine: evaluated by (evidence: `estimator.py`)
- Estimator → Estimator examples: loads baseline (evidence: `estimator.py`)
- Local comparison engine → FLOP accounting: meters operations (evidence: `local_engine.py`)
- Local comparison engine → Whestbench API types: uses API types (evidence: `local_engine.py`)
- Participant → Whestbench CLI: runs CLI stages (evidence: `README.md`)
- Whestbench CLI → Estimator: validates and runs (evidence: `README.md`)
- Whestbench CLI → Public evaluation dataset: scores against (evidence: `README.md`)
- Whestbench CLI → Evaluation results: reports results (evidence: `README.md`)
- Whestbench CLI → Packaged submission: packages estimator (evidence: `README.md`)
- Whestbench CLI → AIcrowd challenge: submits package (evidence: `README.md`)
