Grader schema for reinforcement fine-tuning

Community
,
1

I want to create a reinforcement fine-tuning job for the o4-mini model, but when I reach the grader schema, I paste my schema, and I get “A grader schema is required”, however, I provide this schema:

{
  "type": "multi",
  "graders": {
    "score": {
      "name": "grader",
      "type": "score_model",
      "model": "o4-mini-2025-04-16",
      "input": [
        {
          "role": "system",
          "content": ""
        },
        {
          "role": "user",
          "content": ""
        }
      ],
    }
  },
  "calculate_output": "1 * score"
}

I suspect that there is an issue with the front end. Is there any other way to run a fine-tuning job, or something in my setup is incorrect?