# Install OpenJudge
pip install py-openjudge

# Extra dependency for ref_hallucination_arena (chart generation)
pip install matplotlib

# Run evaluation with config file
python -m cookbooks.ref_hallucination_arena --config config.yaml --save

# Resume from checkpoint (default behavior)
python -m cookbooks.ref_hallucination_arena --config config.yaml --save

# Start fresh, ignore checkpoint
python -m cookbooks.ref_hallucination_arena --config config.yaml --fresh --save

# Override output directory
python -m cookbooks.ref_hallucination_arena --config config.yaml \
  --output_dir ./my_results --save

import asyncio
from cookbooks.ref_hallucination_arena.pipeline import RefArenaPipeline

async def main():
    pipeline = RefArenaPipeline.from_config("config.yaml")
    result = await pipeline.evaluate()

    for rank, (model, score) in enumerate(result.rankings, 1):
        print(f"{rank}. {model}: {score:.1%}")

asyncio.run(main())

task:
  description: "Evaluate LLM reference recommendation capabilities"

dataset:
  path: "./data/queries.json"

target_endpoints:
  model_a:
    base_url: "https://api.openai.com/v1"
    api_key: "${OPENAI_API_KEY}"
    model: "gpt-4"
    system_prompt: "You are an academic literature recommendation expert. Recommend {num_refs} real papers in BibTeX format. Only recommend papers you are confident actually exist."

  model_b:
    base_url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
    api_key: "${DASHSCOPE_API_KEY}"
    model: "qwen3-max"
    system_prompt: "You are an academic literature recommendation expert. Recommend {num_refs} real papers in BibTeX format. Only recommend papers you are confident actually exist."

{
  "query": "Please recommend papers on Transformer architectures for NLP.",
  "discipline": "computer_science",
  "num_refs": 5,
  "language": "en",
  "year_constraint": {"min_year": 2020}
}

evaluation_results/ref_hallucination_arena/
├── evaluation_report.md          # Detailed Markdown report
├── evaluation_results.json       # Rankings, per-field accuracy, scores
├── verification_chart.png        # Per-field accuracy bar chart
├── discipline_chart.png          # Per-discipline accuracy chart
├── queries.json                  # Loaded evaluation queries
├── responses.json                # Raw model responses
├── extracted_refs.json           # Extracted BibTeX references
├── verification_results.json     # Per-reference verification details
└── checkpoint.json               # Pipeline checkpoint for resume