src/submission/check_validity.py

import json
import os

def already_submitted_models(requested_models_dir: str) -> set[str]:
    """Gather a list of already submitted models to avoid duplicates"""
    depth = 1
    file_names = []

    for root, _, files in os.walk(requested_models_dir):
        current_depth = root.count(os.sep) - requested_models_dir.count(os.sep)
        if current_depth == depth:
            for file in files:
                if not file.endswith(".json"):
                    continue
                with open(os.path.join(root, file), "r") as f:
                    info = json.load(f)
                    file_names.append(f"{info['model_name']}_{info['training_dataset']}_{info['testing_type']}_{info['precision']}")

    return set(file_names)