evaluation:
  split: val
  threshold:
    strategy: fixed
    value: 0.5

metrics:
  classification:
    - map
    - macro_f1
    - micro_f1
    - per_attribute_ap
    - per_attribute_f1
  calibration:
    enabled: false
    bins: 15
    metrics:
      - ece
  embedding:
    enabled: true
    retrieval_k:
      - 1
      - 5
      - 10
    compute_silhouette: true

visualization:
  umap:
    enabled: true
    n_neighbors: 15
    min_dist: 0.1
    random_state: 42
  tsne:
    enabled: false
    perplexity: 30
    random_state: 42

error_analysis:
  enabled: true
  top_k_false_positives: 20
  top_k_false_negatives: 20
  analyze_by_frequency_bucket: true
  confusion_focus_groups:
    - color
    - material
    - condition

reporting:
  save_predictions: true
  save_embeddings: true
  output_dir: reports/eval