azr:
  iterations: 50
  tasks_per_iteration: 5
  random_seed: 42
  proposer:
    base_temperature: 0.7
    max_program_loc: 40
    difficulty_step: 0.05
    min_difficulty: 0.2
    max_difficulty: 1.0
  solver:
    base_temperature: 0.6
    accuracy_floor: 0.35
    accuracy_ceiling: 0.95
    improvement_rate: 0.08
  buffers:
    max_size_per_type: 40
  rewards:
    learnability_weight: 1.0
    correctness_weight: 1.0
    econ_weight: 0.2
    format_penalty: 0.5
  market:
    human_hour_value_usd: 85.0
    baseline_completion_minutes: 15
    ai_completion_minutes: 0.5
    complexity_bonus_weight: 12.0
  guardrails:
    target_success_rate: 0.55
    target_valid_rate: 0.85
    diversity_floor: 0.35
    max_iterations_per_run: 500
  telemetry:
    report_path: reports/absolute_zero_reasoner_report.md
    json_path: reports/absolute_zero_reasoner_metrics.json
    mermaid_theme: forest