Webブラウジングエージェントのアノテーション：WebArenaトレースから人間評価まで

pip install potato-annotation

{
  "trace_id": "wa_001",
  "task": "Find the cheapest laptop on the electronics store and add it to the cart",
  "website": "shopping",
  "steps": [
    {
      "step": 0,
      "url": "http://shop.example.com/",
      "action_type": "click",
      "action_target": "Electronics category link",
      "element_id": "nav-electronics",
      "coordinates": [245, 82],
      "screenshot": "screenshots/wa_001_step_00.png"
    },
    {
      "step": 1,
      "url": "http://shop.example.com/electronics",
      "action_type": "click",
      "action_target": "Laptops subcategory",
      "element_id": "cat-laptops",
      "coordinates": [180, 310],
      "screenshot": "screenshots/wa_001_step_01.png"
    }
  ],
  "success": true
}

python -m potato.trace_converter -i traces.json -f web_agent -o data/web_traces.jsonl

annotation_task_name: "WebArena Agent Evaluation"
task_dir: "."
 
data_files:
  - "data/web_traces.jsonl"
 
item_properties:
  id_key: id
  text_key: task_description
 
output_annotation_dir: "output/"
export_annotation_format: "jsonl"
 
instance_display:
  layout:
    direction: vertical
    gap: 16px
  fields:
    - key: task_description
      type: text
      label: "Task"
 
    - key: steps
      type: web_agent_trace
      label: "Agent Browsing Trace"
      display_options:
        show_overlays: true
        show_filmstrip: true
        show_thought: true
        show_observation: true
        show_element_info: true
        screenshot_max_width: 900
        screenshot_max_height: 600
        filmstrip_size: 80
 
annotation_schemes:
  - annotation_type: radio
    name: task_success
    description: "Did the agent complete the task?"
    labels:
      - "Success"
      - "Partial success"
      - "Failure"
    label_requirement:
      required: true
 
  - annotation_type: radio
    name: task_efficiency
    description: "Was the agent's path to the goal efficient?"
    labels:
      - "Optimal path"
      - "Reasonable but not optimal"
      - "Inefficient, unnecessary steps"
      - "Completely wrong direction"
    label_requirement:
      required: true
 
  - annotation_type: trajectory_eval
    name: step_evaluation
    description: "Judge each action against the task"
    steps_key: steps
    step_text_key: action_type
    correctness_options:
      - correct
      - acceptable
      - incorrect
      - unnecessary
    error_types:
      - name: wrong_element_clicked
      - name: wrong_page_navigated_to
      - name: missed_better_option
      - name: incorrect_form_input
      - name: premature_completion
      - name: unnecessary_navigation
      - name: failed_to_scroll
      - name: wrong_page_section
      - name: other
    severities:
      - name: minor
        weight: -1
      - name: major
        weight: -5
      - name: critical
        weight: -10
    show_score: true
    max_score: 100
 
user_config:
  allow_all_users: true

import json
 
annotations = []
with open("output/exports/jsonl/annotations.jsonl") as f:
    for line in f:
        annotations.append(json.loads(line))
 
step_counts = {}
for ann in annotations:
    evaluation = ann["labels"].get("step_evaluation", {})
    for step in evaluation.get("steps", []):
        pos = step["step_index"]
        counts = step_counts.setdefault(pos, {})
        label = step.get("correctness", "unrated")
        counts[label] = counts.get(label, 0) + 1
 
print("Error rate by step position:")
for pos in sorted(step_counts):
    counts = step_counts[pos]
    total = sum(counts.values())
    errors = counts.get("incorrect", 0) + counts.get("unnecessary", 0)
    print(f"  Step {pos}: {errors / total:.1%} error rate ({total} observations)")

error_counts = {}
for ann in annotations:
    evaluation = ann["labels"].get("step_evaluation", {})
    for step in evaluation.get("steps", []):
        error = step.get("error_type")
        if error:
            error_counts[error] = error_counts.get(error, 0) + 1
 
for error, count in sorted(error_counts.items(), key=lambda x: -x[1]):
    print(f"  {error}: {count}")

num_annotators_per_item: 3
assignment_strategy: random

python -m potato.export -c config.yaml -f parquet -o ./parquet_export/

from sklearn.metrics import cohen_kappa_score
import pandas as pd
 
df = pd.read_parquet("parquet_export/annotations.parquet")
success = df[df["schema_name"] == "task_success"]
pivot = success.pivot(index="instance_id", columns="annotator", values="value")
 
annotators = pivot.columns.tolist()
for i in range(len(annotators)):
    for j in range(i + 1, len(annotators)):
        pair = pivot[[annotators[i], annotators[j]]].dropna()
        kappa = cohen_kappa_score(pair[annotators[i]], pair[annotators[j]])
        print(f"Kappa ({annotators[i]} vs {annotators[j]}): {kappa:.3f}")

solo_mode:
  enabled: true
  labeling_models:
    - endpoint_type: "anthropic"
      model: "claude-sonnet-4-20250514"
      api_key: "${ANTHROPIC_API_KEY}"
  thresholds:
    end_human_annotation_agreement: 0.90
    minimum_validation_sample: 50