# kush-kodes-4/xaio_iit architecture

> Architecture diagram of the GitHub repository kush-kodes-4/xaio_iit, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/kush-kodes-4/xaio_iit
- Repository: https://github.com/kush-kodes-4/xaio_iit

## Overview

This repository contains XAIO, a model-agnostic local-explanation method, plus scripts that benchmark it against LIME. The main workflow runs model and dataset setups, produces explanations, and evaluates latency, stability, faithfulness, and agreement with SHAP; a separate phase-0 script audits baseline LIME on a movie recommender. The excerpts show the benchmark invoking XAIO and LIME, but omit much of the CLI’s setup and orchestration, so those internal links are intentionally limited to demonstrated relationships.

Main entry points: [`benchmark_cli.py`](https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py) (Benchmark CLI), [`phase0.py`](https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py) (Phase-0 audit), [`xaio.py`](https://github.com/kush-kodes-4/xaio_iit/blob/main/xaio.py) (XAIO explainer)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_benchmark["Explainability Benchmarks"]
  node_cli["Benchmark CLI<br/>[benchmark_cli.py]"]
  node_lime_compare["LIME comparison<br/>[benchmark_cli.py]"]
  node_evaluation["Quality evaluation<br/>[benchmark_cli.py]"]
  node_sensitivity["Parameter sweep<br/>[benchmark_cli.py]"]
end

subgraph group_runtime["XAIO Runtime"]
  node_xaio["XAIO explainer<br/>[xaio.py]"]
end

subgraph group_baseline["Recommender Baseline"]
  node_phase_runner["Phase-0 audit<br/>[phase0.py]"]
  node_recommender["Movie recommender<br/>[phase0.py]"]
  node_lime_baseline["Baseline LIME<br/>[phase0.py]"]
end

node_engineer(("Benchmark operator"))

node_engineer -->|"runs"| node_cli
node_cli -->|"invokes"| node_xaio
node_cli -->|"compares with"| node_lime_compare
node_cli -->|"evaluates"| node_evaluation
node_cli -->|"sweeps parameters"| node_sensitivity
node_engineer -->|"runs"| node_phase_runner
node_phase_runner -->|"loads"| node_recommender
node_phase_runner -->|"benchmarks"| node_lime_baseline

click node_cli "https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py"
click node_xaio "https://github.com/kush-kodes-4/xaio_iit/blob/main/xaio.py"
click node_lime_compare "https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py"
click node_evaluation "https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py"
click node_sensitivity "https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py"
click node_phase_runner "https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py"
click node_recommender "https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py"
click node_lime_baseline "https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.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_cli,node_lime_compare,node_evaluation,node_sensitivity toneBlue
class node_xaio toneAmber
class node_phase_runner,node_recommender,node_lime_baseline toneMint
class node_engineer toneIndigo
```

## Components

### Explainability Benchmarks

- [Benchmark CLI](https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py): `benchmark_cli.py`
- [LIME comparison](https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py): `benchmark_cli.py`
- [Quality evaluation](https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py): `benchmark_cli.py`
- [Parameter sweep](https://github.com/kush-kodes-4/xaio_iit/blob/main/benchmark_cli.py): `benchmark_cli.py`

### XAIO Runtime

- [XAIO explainer](https://github.com/kush-kodes-4/xaio_iit/blob/main/xaio.py): `xaio.py`

### Recommender Baseline

- [Phase-0 audit](https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py): `phase0.py`
- [Movie recommender](https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py): `phase0.py`
- [Baseline LIME](https://github.com/kush-kodes-4/xaio_iit/blob/main/phase0.py): `phase0.py`

### Other components

- **Benchmark operator**

## Connections

- Benchmark operator → Benchmark CLI: runs (evidence: `benchmark_cli.py`)
- Benchmark CLI → XAIO explainer: invokes (evidence: `benchmark_cli.py`)
- Benchmark CLI → LIME comparison: compares with (evidence: `benchmark_cli.py`)
- Benchmark CLI → Quality evaluation: evaluates (evidence: `benchmark_cli.py`)
- Benchmark CLI → Parameter sweep: sweeps parameters (evidence: `benchmark_cli.py`)
- Benchmark operator → Phase-0 audit: runs (evidence: `phase0.py`)
- Phase-0 audit → Movie recommender: loads (evidence: `phase0.py`)
- Phase-0 audit → Baseline LIME: benchmarks (evidence: `phase0.py`)
