policy_id: benchmark-selection-v0.1
effective_from: 2026-09-13
selection_count: 5
weights:
  task_relevance: 0.30
  ecological_validity: 0.15
  measurement_reliability: 0.12
  discriminative_power: 0.12
  freshness: 0.10
  execution_profile_similarity: 0.10
  reproducibility: 0.06
  contamination_resistance: 0.05
penalties:
  redundancy: enabled
  known_task_bias: enabled
requirements:
  preserve_benchmark_version: true
  preserve_execution_profile: true
  report_weak_coverage: true
  never_substitute_aggregate_index_for_task_mapping: true