> ## Documentation Index
> Fetch the complete documentation index at: https://docs.repli5.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quality Evaluation & Review

> Platform-wide automated rubric scoring, manual review statuses, and single-image regeneration across all augmentation workflows.

## Overview

**Quality Evaluation & Review** is a built-in quality assurance feature available across **all augmentation workflows** on the Repli5 platform.

Whenever an augmentation job finishes generating an image, an automated vision-language evaluator compares the generated output (`rgb_out`) against the source image (`rgb_raw`)—and, for localized edits, close-up crops of the modified region—using the **Evaluation Rubric Set** selected for that job.

***

## Workflow-Specific Evaluation Rubrics

Because each workflow has different quality criteria, each workflow defaults to its own dedicated **Evaluation Rubric Set** (which you can also customize or switch in Card **3 — Summary** before launching a job):

| Workflow | Default Rubric Set | Evaluated Metrics | What It Checks |
| :- | :- | :- | :- |
| **[Defect Generation](https://docs.repli5.com/workflows/defect-generation.md)** | **Defect generation** (`default_defect_generation`) | `Defect Realism` `Surface Continuity` `Scale & Geometry` | Evaluates whether the synthesized defect looks physically authentic on a close-up crop, blends seamlessly into the surrounding material grain without paste borders, and preserves the part's underlying geometry. |
| **[Variation Generator](https://docs.repli5.com/workflows/variation-generator.md)** | **Defect variation** (`default_defect_variation`) | `Preserves original defect` | Verifies that the requested color, material, or lighting variation is applied while existing scratches, dents, and surface wear from the source image remain intact. |

***

## Scoring Scale & Attention Flags

* **1–5 Scoring Scale:** Each metric in the active rubric set is scored from `1` (severe artifact or missing requirement) to `5` (excellent fidelity), accompanied by a short written explanation from the evaluator.
* **Needs Attention (`Score < 3`):** Any image where at least one metric scores below `3` is automatically flagged in the **Augment History** so reviewers can inspect problem candidates first instead of paging through entire batches manually.

***

## Reviewing & Regenerating Images in Augment History

In the **Augment History** panel at the bottom of any workflow page:

1. **Filter by Score or Review Status:** Filter the batch by *Needs Attention (`< 3`)*, *Unreviewed*, *Approved*, or *Rejected*.
2. **Side-by-Side Comparison:** Click any image to open the interactive comparator (with synchronized zoom/pan, split curtain, and rubric score breakdown).
3. **Approve or Reject:** Mark individual images as **Approved** or **Rejected**, or override a metric score with a human verdict.
4. **In-Place Single-Image Regeneration:**
   * If an image has an artifact or low rubric score, click **Regenerate** directly on that image.
   * You can re-run with the same preset/prompt or adjust the prompt for that specific image.
   * When the new image completes, it is automatically re-evaluated and replaces the previous image in the output dataset (`superseded = true`), keeping your dataset count and annotations clean.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.