---
title: Glossary
description: The terms used across Avra's documentation, what each one means, and where to read more.
---

The terms you'll meet across these docs, in alphabetical order.

| Term | What it means | Read more |
|------|---------------|-----------|
| **Adaptation** | Self-supervised learning of a copy of Avra RFM on your database. The copy is exclusive to your workspace | [Adaptation and fine-tuning](/rfm/adaptation) |
| **Alias** | A name, such as `production`, that points at one version of a model. Reassigning it promotes or rolls back without code changes | [Model versioning](/core/model-versioning) |
| **API key** | The credential your systems send as a bearer token. Each key belongs to one workspace | [API keys](/dashboard/api-keys) |
| **Avra Core** | Delivers Avra's models into your systems: live predictions, batch inference, embeddings, and the controls around them | [Avra Core](/core) |
| **Avra GFM** | The Graph Foundation Model. Pre-trained on Avra's knowledge graph of the Brazilian economy, it returns embeddings and probabilities of default for Brazilian companies, from Avra's cloud only | [Avra GFM](/gfm) |
| **Avra RFM** | The Relational Foundation Model. Pre-trained on diverse relational data, it predicts over your database without a training project | [Avra RFM](/rfm) |
| **Backfill** | An ingestion run over a window of past snapshot times, which loads history without moving the sources' regular checkpoints | [Time and history](/data-ingestion/time#backfills) |
| **Backtest** | Predictions made at past dates and scored on what happened after them | [Evaluation](/rfm/evaluation) |
| **Batch** | An asynchronous job that scores every record in the files you upload | [Batch inference](/core/batch-inference) |
| **Bitemporal** | Keeping two times for every row: when it was true and when it was recorded | [Time and history](/data-ingestion/time) |
| **Checkpoint** | The position each ingestion source keeps, so a run reads only what arrived since the last one | [Data ingestion](/data-ingestion#runs) |
| **CNPJ** | The Brazilian company registration number, and Avra GFM's input | [Avra GFM](/gfm) |
| **Correlation ID** | The UUID you send in the `X-Correlation-Id` header to trace a request | [Live predictions](/core/predictions#trace-every-call) |
| **Data contract** | The pipeline definition agreed with your Avra team: the sources, their keys and time columns, the checks, and the output | [Data contracts and checks](/data-ingestion/data-contracts) |
| **Data layer** | The Helm charts that run the ingestion pipeline and the Avra agent in your Kubernetes cluster | [Install the data layer](/deployment/data-layer) |
| **Embedding** | A vector that represents a company, from Avra GFM. It has 1024 dimensions and can be shortened | [Build with embeddings](/gfm/embeddings) |
| **Event time** | When a row was true at the source: when the payment happened or the address took effect | [Time and history](/data-ingestion/time) |
| **Fine-tuning** | Learning one task in a copy of Avra RFM. The copy is exclusive to your workspace | [Adaptation and fine-tuning](/rfm/adaptation) |
| **Horizon** | The end of a prediction's window: when its answer is known | [What you can predict](/rfm/what-you-can-predict) |
| **Identity key** | The column or columns that identify one row of a table you send | [Preparing your data](/data-ingestion/preparing-data) |
| **In-context prediction** | Avra RFM reads your history as context when a prediction is made. No weights change | [How predictions work](/rfm/predictions) |
| **Ingestion pipeline** | How your data reaches Avra's models: checked against your data contract, then published as a new version | [Data ingestion](/data-ingestion) |
| **Labelled example** | A past instance of the same prediction, with its known outcome, read as context | [How predictions work](/rfm/predictions) |
| **Leakage** | Information from after a decision reaching the prediction about it | [Time and leakage](/rfm/predictions#time-and-leakage) |
| **Model version** | One immutable version of a model, with its own `model_version_id`. Only active versions serve predictions | [Model versioning](/core/model-versioning) |
| **Organization** | Your company's account in Avra. It holds your workspaces, and models and roles apply across it | [Dashboard](/dashboard) |
| **Prediction date** | The date a prediction is made for. It sees only what was known by then | [What you can predict](/rfm/what-you-can-predict) |
| **Probability of default** (PD) | Avra GFM's credit outputs, at five horizons: `pd_30d`, `pd_60d`, `pd_90d`, `pd_180d`, and `pd_365d` | [Credit](/use-cases/credit-intelligence) |
| **Quality gate** | The ingestion stage that runs your contract's checks before anything is published | [Data contracts and checks](/data-ingestion/data-contracts) |
| **Risk band** | A group of records whose outcomes stay distinct and stable, for setting policy | [Risk bands](/use-cases/credit-intelligence/homogeneous-groups) |
| **Score** | What Avra RFM returns for a yes-or-no outcome. It ranks and compares records, and isn't a calibrated probability | [What you can predict](/rfm/what-you-can-predict#kinds-of-targets) |
| **Shadow** | Running a new version beside the current one on live traffic, with no effect on decisions | [Evaluation](/rfm/evaluation) |
| **Snapshot time** | When your systems recorded a row: the capture of the source it came from | [Time and history](/data-ingestion/time) |
| **Webhook** | A notification Avra sends to your endpoint when an event happens, such as a batch ending | [Webhooks](/core/webhooks) |
| **Workspace** | An isolated area of your organization that holds API keys, batches, files, and logs | [Dashboard](/dashboard) |
