# Models and Training:
- Participants may use pre-trained models as long as they are open-source and appropriately licensed. 
- Fine-tuning of models is permitted.
- **API usage of any kind is strictly prohibited.** (i.e. OpenAI or Claude).
- Using external infrastructure for model training is allowed.

# Translation
- Although a Bengali pipeline is highly encouraged, translation  is allowed.
- Translation must be done using a model to which the aforementioned rules also apply.
- Translation model and training code must be submitted.
- Translation on the test set must be done in the inference notebook.

# Use of External Data:

- Participants are allowed to use external data only if one of the following following is applicable-
-- The data is publicly available.
-- The data is curated from publicly available sources.
-- The data is created by the participants during the competition runtime.
- Any external data used must be declared and made public at the time of submission, with appropriate citations.

# Submission:
- Participants must submit the code for their training and inference pipeline.
- Participants must submit their entire training methodology and ensure reproducibility. 
- The submitted inference notebook must be runnable on kaggle (CPU or GPU) within kaggle runtime [limits](https://www.kaggle.com/docs/notebooks) and reproduce the same results.
- Submissions will be rerun on the public test set and on the hidden test set after the Phase I concludes.
- Participants must ensure their final submission is well-documented and can be replicated for scoring.
- Participants must make their final submission notebooks public.
- Participants need to submit a paper in IEEE format describing their solution.

# Submission Limits:

- Each participant or team can submit up to 5 entries per day during the competition.
- Submissions are evaluated on the leaderboard using 100 problems in the public test set.
- After the competition, the final score will be determined by evaluating submissions on both public test set and the hidden test set.

# Evaluation Metric:

- Submissions will be evaluated based on accuracy. The answer to each problem must be predicted to be an integer.
- Partial credit will not be given; the prediction must exactly match the true answer.

# Eligibility:

- The competition is open to individuals and teams. However, participants must comply with all legal requirements and competition rules.
- Participants must register for the competition with a valid account on the Kaggle.

# Originality and Plagiarism:

- All submitted code and models must be the original work of the participant or team.
- Participants may not use, copy or share any part of another participant’s code or solution, unless made public before the end of the competition.


# Team Formation:
- Teams may consist of up to 5 members. 
- At most 1 member of each team can be a professional or expert.
- The remaining members must be undergraduate students.
- Merging of teams is allowed until the team merge deadline of the competition. After this point, no new team merges will be accepted.

# Code of Conduct:
- Participants are expected to uphold the spirit of the competition by following the rules and ensuring fairness and transparency.
- Any attempts to manipulate the leaderboard or exploit system vulnerabilities will result in disqualification.
- Violations of these rules may result in disqualification from the competition.