{
  "version": 1,
  "date": "2026-10-20",
  "task": "single_digit_addition",
  "split": {
    "train": [
      [
        0,
        0
      ],
      [
        0,
        1
      ],
      [
        0,
        6
      ],
      [
        0,
        7
      ],
      [
        0,
        8
      ],
      [
        1,
        0
      ],
      [
        1,
        1
      ],
      [
        1,
        2
      ],
      [
        1,
        3
      ],
      [
        1,
        5
      ],
      [
        1,
        7
      ],
      [
        1,
        8
      ],
      [
        1,
        9
      ],
      [
        2,
        1
      ],
      [
        2,
        2
      ],
      [
        2,
        4
      ],
      [
        2,
        5
      ],
      [
        2,
        6
      ],
      [
        2,
        7
      ],
      [
        2,
        8
      ],
      [
        2,
        9
      ],
      [
        3,
        1
      ],
      [
        3,
        4
      ],
      [
        3,
        9
      ],
      [
        4,
        2
      ],
      [
        4,
        3
      ],
      [
        4,
        4
      ],
      [
        4,
        5
      ],
      [
        4,
        6
      ],
      [
        4,
        7
      ],
      [
        4,
        8
      ],
      [
        4,
        9
      ],
      [
        5,
        1
      ],
      [
        5,
        2
      ],
      [
        5,
        4
      ],
      [
        5,
        5
      ],
      [
        5,
        7
      ],
      [
        5,
        8
      ],
      [
        6,
        0
      ],
      [
        6,
        2
      ],
      [
        6,
        4
      ],
      [
        6,
        6
      ],
      [
        6,
        7
      ],
      [
        6,
        9
      ],
      [
        7,
        0
      ],
      [
        7,
        1
      ],
      [
        7,
        2
      ],
      [
        7,
        4
      ],
      [
        7,
        5
      ],
      [
        7,
        6
      ],
      [
        8,
        0
      ],
      [
        8,
        1
      ],
      [
        8,
        2
      ],
      [
        8,
        4
      ],
      [
        8,
        5
      ],
      [
        8,
        8
      ],
      [
        8,
        9
      ],
      [
        9,
        1
      ],
      [
        9,
        2
      ],
      [
        9,
        3
      ],
      [
        9,
        4
      ],
      [
        9,
        6
      ],
      [
        9,
        8
      ]
    ],
    "dev": [
      [
        0,
        2
      ],
      [
        0,
        4
      ],
      [
        0,
        5
      ],
      [
        0,
        9
      ],
      [
        1,
        6
      ],
      [
        2,
        0
      ],
      [
        3,
        3
      ],
      [
        3,
        8
      ],
      [
        4,
        0
      ],
      [
        5,
        0
      ],
      [
        5,
        9
      ],
      [
        6,
        1
      ],
      [
        7,
        8
      ],
      [
        8,
        3
      ],
      [
        8,
        7
      ],
      [
        9,
        0
      ],
      [
        9,
        5
      ],
      [
        9,
        9
      ]
    ],
    "test": [
      [
        0,
        3
      ],
      [
        1,
        4
      ],
      [
        2,
        3
      ],
      [
        3,
        0
      ],
      [
        3,
        2
      ],
      [
        3,
        5
      ],
      [
        3,
        6
      ],
      [
        3,
        7
      ],
      [
        4,
        1
      ],
      [
        5,
        3
      ],
      [
        5,
        6
      ],
      [
        6,
        3
      ],
      [
        6,
        5
      ],
      [
        6,
        8
      ],
      [
        7,
        3
      ],
      [
        7,
        7
      ],
      [
        7,
        9
      ],
      [
        8,
        6
      ],
      [
        9,
        7
      ]
    ]
  },
  "seeds": [
    11,
    22,
    33
  ],
  "vocab": "0123456789+=~_",
  "eos": "~",
  "pad": "_",
  "embedding": 24,
  "hidden": 48,
  "threads": 1,
  "sft_steps": 200,
  "sft_batch": 16,
  "sft_lr": 0.003,
  "rl_steps": 240,
  "prompts_per_step": 8,
  "group_size": 8,
  "updates_per_rollout": 2,
  "rl_lr": 0.0005,
  "clip": 0.2,
  "kl_beta": 0.03,
  "max_new_tokens": 6,
  "temperature": 1.0,
  "eval_samples": 16,
  "gradient_clip": 1.0,
  "arms": [
    "strict",
    "substring"
  ],
  "loss_reduction": "mean over all valid response tokens, including EOS",
  "advantage": "group population std + 1e-8; no dynamic resampling",
  "kl": "exact categorical KL at old-policy sampled histories",
  "selection": "fixed last checkpoint; no tuning or seed selection",
  "rewards": {
    "strict": "terminated, nonempty ASCII digits, integer equals a+b; leading zeros allowed",
    "substring": "decimal str(a+b) occurs anywhere, even without EOS"
  }
}