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

# How scoring works

> Repetitions, evaluations, score layers, and the image-only ablation.

Kettio scores creative with an SSR (Semantic Similarity Rating) pipeline. An asset is presented
to a persona built from the audience you supplied, and the resulting response distribution is
converted into a score.

## Repetitions and evaluations

The unit that matters for both accuracy and billing is the **scoring evaluation**.

One scoring evaluation runs **three independent repetitions**. Each repetition scores a
two-model pair, and the three pair scores are averaged. That means a single evaluation makes six
generator samples while consuming one ranking credit.

```
1 scoring evaluation
├── repetition 1  ──┐
├── repetition 2  ──┼── averaged → score
└── repetition 3  ──┘
   (2 generator samples each → 6 total)
```

You can see all of this in the response:

| Field                                       | Meaning                                          |
| ------------------------------------------- | ------------------------------------------------ |
| `confidence_details.repetition_count`       | Repetitions behind this score (3)                |
| `confidence_details.generator_sample_count` | Generator samples behind this score (6)          |
| `details.repetitionScores`                  | The individual repetition scores                 |
| `details.repetitionScoreRange`              | Spread between the highest and lowest repetition |

<Note>
  Credits are deducted per **successful scoring evaluation** — not per repetition, not per model
  call. Three repetitions cost the same as one.
</Note>

## Score layers

An asset is scored at one of two layers, reported as `score_layer`:

<CardGroup cols={2}>
  <Card title="image-only" icon="image">
    The default. The persona sees the creative with no ad copy attached.
  </Card>

  <Card title="full-ad-package" icon="rectangle-list">
    Used when you send `copy_context`. The persona sees the creative *and* the words.
  </Card>
</CardGroup>

## The image-only ablation and copy lift

When you attach `copy_context`, Kettio does not just score the full package. It also re-scores
the same creative with the copy stripped out, then reports the difference.

| Field              | Meaning                                                 |
| ------------------ | ------------------------------------------------------- |
| `score`            | Score at the layer named in `score_layer`               |
| `image_only_score` | Score for the same creative with the copy removed       |
| `copy_lift`        | `score` minus `image_only_score` — what the words added |

This is why a copy-context asset can cost two evaluations instead of one: the ablation is a
second evaluation. If the ablation fails, `image_only_score` and `copy_lift` are absent and the
asset costs one.

<Warning>
  `copy_lift` is a within-batch, within-audience quantity. A positive lift means the copy helped
  *this* creative for *this* persona in *this* run. It is not a general claim that the copy is
  good, and it is not a CTR estimate.
</Warning>

## What a score is not

This is the part worth being precise about, because it determines whether you build something
useful or something misleading.

<AccordionGroup>
  <Accordion title="Not a conversion probability" icon="percent">
    A score of 4.24 does not mean 4.24% of anything, and does not map to a purchase rate.
  </Accordion>

  <Accordion title="Not comparable across batches" icon="arrow-right-arrow-left">
    Scores are calibrated relative to the assets in the submitted batch. Two assets that scored
    4.1 in different batches did not necessarily perform equally.
  </Accordion>

  <Accordion title="Not comparable across goals or audiences" icon="filter">
    Changing `goal` or `audience` changes what is being measured. Hold both fixed for any
    comparison you intend to act on.
  </Accordion>

  <Accordion title="Not a forecast" icon="chart-line">
    Kettio does not predict CPA, ROAS, or causal lift. It is a prioritization signal for
    deciding what to test, not a substitute for testing.
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="Reading confidence" icon="scale-balanced" href="/concepts/confidence">
    Deciding when a gap between two scores is real.
  </Card>

  <Card title="Limits and billing" icon="gauge" href="/concepts/limits-and-billing">
    How evaluations translate into credits and rate limits.
  </Card>
</CardGroup>