- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/academic-eval/03-ref-hallucination-arenaDo publicador
Evaluate how accurately LLMs recommend real academic references using the
OpenJudge RefArenaPipeline:
# 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."
Each query in the JSON/JSONL dataset:
{
"query": "Please recommend papers on Transformer architectures for NLP.",
"discipline": "computer_science",
"num_refs": 5,
"language": "en",
"year_constraint": {"min_year": 2020}
}
Official dataset: OpenJudge/ref-hallucination-arena
Overall accuracy (verification rate):
Per-field accuracy:
title_accuracy — % of titles matching real papersauthor_accuracy — % of correct author listsyear_accuracy — % of correct publication yearsdoi_accuracy — % of valid DOIsVerification status:
VERIFIED — title + author + year all exactly match a real paperSUSPECT — partial match (e.g. title matches but authors differ)NOT_FOUND — no match in any databaseERROR — API timeout or network failureRanking order: overall accuracy → year compliance rate → avg confidence → completeness
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
>
---name: 03-ref-hallucination-arenadescription: >---# skills/academic-eval/03-ref-hallucination-arena/SKILL.mdPerguntas frequentes
Baixe skills/academic-eval/03-ref-hallucination-arena/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/agentscope-ai/OpenJudge.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.