# What is Label? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Foundational AI  
> **Canonical Citation:** [https://spidits.com/ai-glossary/label](https://spidits.com/ai-glossary/label)

## Definition
A Label is the target output or correct outcome variable associated with a training example in supervised learning (e.g. labeling a picture as a "dog" or marking an email as "spam").

## Architectural Mechanics & Deep Dive
A label (or target) is the ground-truth value or category assigned to a data point in a supervised learning dataset. In classification, the label represents the class (e.g., "spam" or "inbox"); in regression, it is a continuous value (e.g., house price). The training goal of supervised learning is to predict this label given the input features, using loss functions to measure error.

## Industry Applications & Real-World Use Cases
Dataset tagging, annotation operations, and supervised training metrics

## Frequently Asked Questions

### How does a label differ from a feature?
A feature is the input variable fed into the model. A label is the target output variable that the model is trying to predict.

### How are labels created?
Typically manually by human annotators, or automatically in self-supervised datasets by masking parts of the raw input.

## Related Terminology
- [feature](https://spidits.com/ai-glossary/feature)
- [supervised-learning](https://spidits.com/ai-glossary/supervised-learning)
- [synthetic-data](https://spidits.com/ai-glossary/synthetic-data)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*