画像比較と選好タスク

{"id": "pair_001", "prompt": "A sunset over mountains", "image_a": "/media/model_a_001.png", "image_b": "/media/model_b_001.png"}
{"id": "pair_002", "prompt": "A cat on a windowsill", "image_a": "/media/model_a_002.png", "image_b": "/media/model_b_002.png"}

instance_display:
  layout:
    direction: horizontal
    gap: 24px
  fields:
    - key: image_a
      type: image
      label: "Image A"
      display_options:
        max_height: 512
        zoomable: true
        alt_text: "First generated image"
    - key: image_b
      type: image
      label: "Image B"
      display_options:
        max_height: 512
        zoomable: true
        alt_text: "Second generated image"

annotation_schemes:
  - annotation_type: radio
    name: preference
    description: "Which image better matches the prompt?"
    labels:
      - name: "A is clearly better"
      - name: "A is slightly better"
      - name: "About equal"
      - name: "B is slightly better"
      - name: "B is clearly better"
    sequential_key_binding: true
    label_requirement:
      required: true

  - annotation_type: radio
    name: prompt_adherence
    description: "Which image better matches the prompt?"
    labels:
      - name: A
      - name: Tie
      - name: B
 
  - annotation_type: multiselect
    name: issues_a
    description: "Problems in Image A (select all that apply)"
    labels:
      - name: "Distorted faces or hands"
      - name: "Text rendering errors"
      - name: "Unnatural lighting"
      - name: "Missing elements from the prompt"
      - name: "Blurry or low quality"
      - name: "None"

instance_display:
  layout:
    direction: horizontal
    gap: 24px
  fields:
    - key: original
      type: image
      label: "Original"
      display_options:
        max_height: 512
        zoomable: true
    - key: enhanced
      type: image
      label: "Enhanced"
      display_options:
        max_height: 512
        zoomable: true
 
annotation_schemes:
  - annotation_type: radio
    name: enhancement_quality
    description: "How did the edit change the image?"
    labels:
      - name: "Clearly improved"
      - name: "Slightly improved"
      - name: "No noticeable change"
      - name: "Made worse"
    label_requirement:
      required: true
 
  - annotation_type: multiselect
    name: problems_introduced
    description: "Problems the edit introduced (select all that apply)"
    labels:
      - name: "Over-sharpening or halos"
      - name: "Color shift"
      - name: "Loss of detail"
      - name: "New artifacts"
      - name: "None"

item_properties:
  id_key: id
  text_key: prompt
 
instance_display:
  fields:
    - key: prompt
      type: text
      label: "Prompt"
    - key: images
      type: gallery
      display_options:
        layout: grid
        columns: 2
        thumbnail_size: 320
        zoomable: true
 
annotation_schemes:
  - annotation_type: ranking
    name: preference_rank
    description: "Drag the image numbers to rank them from best at the top to worst at the bottom."
    labels:
      - "Image 1"
      - "Image 2"
      - "Image 3"
      - "Image 4"
    allow_ties: false
    label_requirement:
      required: true

  - annotation_type: bws
    name: quality
    description: "Select the BEST and the WORST image in this set."
    tuple_size: 4
    best_description: "Best"
    worst_description: "Worst"

python -m potato.bws_scoring --config config.yaml --method bradley_terry

annotation_instructions: |
  Judge each pair on how well it matches the prompt first, then on visual
  quality, then on how appealing it looks. Zoom in before deciding: hands,
  text, and fine texture are where generation failures show up. Mark "About
  equal" only when you have looked at both and cannot separate them.

attention_checks:
  enabled: true
  items_file: "data/attention_checks.json"
  frequency: 20
  min_response_time: 3.0
  failure_handling:
    warn_threshold: 2
    block_threshold: 5

annotation_task_name: "Generative Model Comparison"
task_description: "Compare two generated images against the prompt that produced them."
 
data_files:
  - data/model_outputs.json
 
item_properties:
  id_key: id
  text_key: prompt
 
instance_display:
  layout:
    direction: horizontal
    gap: 24px
  fields:
    - key: image_a
      type: image
      label: "Image A"
      display_options:
        max_height: 512
        zoomable: true
        alt_text: "First generated image"
    - key: image_b
      type: image
      label: "Image B"
      display_options:
        max_height: 512
        zoomable: true
        alt_text: "Second generated image"
 
annotation_instructions: |
  Judge each pair on prompt match first, then visual quality, then appeal.
  Zoom in before deciding. Mark "About equal" only when you cannot separate them.
 
annotation_schemes:
  - annotation_type: radio
    name: preference
    description: "Which image better represents the prompt?"
    labels:
      - name: "A is clearly better"
      - name: "A is slightly better"
      - name: "About equal"
      - name: "B is slightly better"
      - name: "B is clearly better"
    sequential_key_binding: true
    label_requirement:
      required: true
 
  - annotation_type: radio
    name: prompt_adherence
    description: "Which image matches the prompt more closely?"
    labels:
      - name: A
      - name: Tie
      - name: B
 
  - annotation_type: likert
    name: confidence
    description: "How confident are you in this judgment?"
    size: 5
    min_label: "Guessing"
    max_label: "Certain"
 
attention_checks:
  enabled: true
  items_file: "data/attention_checks.json"
  frequency: 20
  min_response_time: 3.0
  failure_handling:
    warn_threshold: 2
    block_threshold: 5
 
num_annotators_per_item: 3
output_annotation_dir: annotation_output/image-comparison/
export_annotation_format: jsonl

{"instance_id": "pair_001", "user_id": "rater_01", "labels": {"preference": {"A is slightly better": "A is slightly better"}, "confidence": {"4": "4"}}, "spans": {}, "links": {}}