AI Transparency

Explainable AI Analysis & Visualization

Unlock the black box of AI models with our comprehensive XAI toolkit. Visualize, analyze, and understand your model's decision-making process with intuitive explanations and interactive visualizations.

Model Interpretability

Understand how your AI models make decisions with detailed feature importance analysis and decision path visualization.

Local Explanations

Get instance-level insights into model predictions with LIME and SHAP explanations for individual cases.

Performance Metrics

Track model performance with comprehensive metrics and visualizations for accuracy, fairness, and reliability.

Data Formats

Explore the standard data formats used in our system

Feature Vector Format

{
    "messageType": "feature_vector",
    "messageId": 0,
    "data": [-0.4232191175986961, -0.5031443592838056, 0.30497221256679125,
        0.4157550505277444, -0.46174460409303325, -0.12950797668733202,
        0.6323170694189965, 0.20112482321095512, -0.0770502704073328,
        -0.021781132983331605, 0.2855062868586593, -0.11389146262348109,
        -0.4338320677142379, 0.14545007041168245, 0.34325194689681915
    ],
    "score": -2.753245759396493,
    "pfa": 0.0008605957637858228,
    "label": "some_object",
    "bbox": [0.0, 0, 16.0, 0],
    "imageURL": "/media/images/video_frame_9001.jpg",
    "layer": 3,
    "metaData" : {
        "some name" : "some value",
        "optional" : "string name/value pairs that provide additional info"
    }
}

Label Configuration

{
    "messageType": "label_config",
    "wildcards" : {
        "human_.*":"#0000FFFF",
        "human_Original.*":"#FFFF00FF",
        "chatGPT_.*":"#FF0000FF",
        "chatGPT_Original.*":"#00FF00FF"
    },
    "clearAll" : "false"
}