=== REAL cross-check A: Sonnet->Haiku, gate=OFF, rollouts_k=2, brief-writer (exercises new paths) ===
{
  "benchmark": "gbrain-evals/skillopt-v1",
  "backend": "target=claude/optimizer=claude",
  "model": "(default)",
  "n_seeds": 1,
  "n_improved": 1,
  "tokens_used": 11271,
  "results": [
    {
      "seed": "brief-writer",
      "held_out_before": 0.0,
      "held_out_after": 1.0,
      "improved": true,
      "nights": 1,
      "trace": [
        {
          "night": 0,
          "test_hard": 0.0,
          "action": "baseline"
        },
        {
          "night": 1,
          "val_hard": 1.0,
          "test_hard": 1.0,
          "action": "greedy_improved",
          "accepted": true,
          "edits": [
            "Every brief MUST include a section with the exact heading '## Key Risks' that lists the primary risks relevant to the recommendation. This section is required in every output regardless of topic.",
            "Every brief MUST include a 'Confidence:' label (satisfying /[Cc]onfidence\\s*[:=]/) that states the confidence level in the recommendation (e.g., 'Confidence: Medium'). Place it near the answer/recommendation line or at the end of the brief."
          ]
        }
      ],
      "slow_update": null,
      "final_skill_tail": "at lists the primary risks relevant to the recommendation. This section is required in every output regardless of topic.\n- Every brief MUST include a 'Confidence:' label (satisfying /[Cc]onfidence\\s*[:=]/) that states the confidence level in the recommendation (e.g., 'Confidence: Medium'). Place it near the answer/recommendation line or at the end of the brief.\n<!-- SKILLOPT-SLEEP:LEARNED END -->\n"
    }
  ]
}