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

# E0206 — OutputShapeMismatch (harness)

> The backend under test returned an output raster with different dimensions than the reference on a specific sample.

<Warning>E0206: backend output shape mismatch on sample N</Warning>

## What happened

During a conformance harness run, the backend under test returned an output raster for sample `N` with different dimensions than the reference simulator output. The reference output was `[ref_t × ref_n]`, the backend returned `[got_t × got_n]`.

## Why

The backend implementation does not produce the correct output shape for this sample. Possible causes:

* Off-by-one in T unrolling
* The backend silently skips empty input timesteps
* The backend trims trailing zero-spike timesteps

## How to fix

1. In your backend's `run_batch` implementation, ensure the output tensor has shape `[batch, T, N_out]` where `T` and `N_out` are taken from the artifact — not from the input data.
2. The output shape must be fixed by the model, not by the input activity.

## Example

```
E0206: backend output shape mismatch on sample 7 — reference [100×20], backend [99×20]
Why: the backend returned a different number of timesteps or output neurons
Fix: verify the backend runs exactly T=100 timesteps and produces N_out=20 neurons per the artifact
Docs: https://docs.thrindex.com/errors/E0206
```