## Task-Specific Architecture Restrictions

1. You **may not** use any pre-trained models, apart from those provided in [torchvision](https://docs.pytorch.org/vision/main/models.html).
2. You **may not** train your model directly on the validation or test samples in any way. This includes any unsupervised learning technique, calculating statistics over them, running GPT-5 agents etc.
3. You **may not** use any external dataset.
4. You **may not** label the unlabeled sketches or test set with any pre-trained model, e.g. CLIP.

## AICC Contest Rules

- The use of LLMs for writing code or getting task ideas is forbidden.
- Use of the internet, besides the reading of official library documentation and accessing the contest platform, is forbidden.
- Communicating with anyone during the contest is forbidden.
- Only ask questions regarding task statements using the #clarification-requests on the discord server.

We can't enforce these rules, but following them ensures fair play and a more accurate simulation of the IOAI. It is in the best interest of the contestants they follow the rules.