{
  "checkpoint": "short/checkpoint-36000",
  "baseline": "short/checkpoint-31000",
  "teacher_stage_started": false,
  "eval_loss": 2.37972832,
  "eval_token_acc": 0.55962285,
  "ordinary_eos": 3,
  "ordinary_total": 8,
  "code_basic_pass": 4,
  "code_basic_total": 4,
  "code_expanded_pass": 4,
  "code_expanded_total": 5,
  "thinking_closed": 1,
  "thinking_eos": 1,
  "thinking_correct": 0,
  "thinking_total": 2,
  "thinking_budget": 512,
  "comparison": "CPU rerun of four step36000 cases compared with preserved step31000 CPU outputs; original step31000 weights were rotated away."
}