{"slug":"agentscope-ai-03-ref-hallucination-arena","source_name":"agentscope-ai/03-ref-hallucination-arena","name":"Agentscope AI/03 Ref Hallucination Arena","description":"Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.","version":1,"lift":{"pass_rate_delta_pts":64,"pass_rate_pct":80,"total_cases":25,"passed_cases":20,"tokens_delta_pct":54.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-10-11T00:23:36.472650+00:00"},"skill_score":0.8000000000000002,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":64,"with_pass_pct":80,"without_pass_pct":16,"tokens_delta_pct":54.1,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":25,"verdict":"mixed","never_hurt":true,"completed_at":"2026-10-11T00:23:36.472650+00:00","run_id":"a3ce3e10-9806-40ab-9ef8-da59adf4c82f","latest_attempt":{"id":"a3ce3e10-9806-40ab-9ef8-da59adf4c82f","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-10-11T00:23:36.472650+00:00","gate":null},"version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"abe2fa877cce20e8bbf5601b58406c4c9265422f121ae30a2ab098eb43393a1e","install_name":"agentscope-ai-03-ref-hallucination-arena","version_id":"25190e8b-1ba2-4cca-ac4f-2905faae79ab","body_sha256":"abe2fa877cce20e8bbf5601b58406c4c9265422f121ae30a2ab098eb43393a1e","render_hash":"0565736736f0c49bbe3bf05432a1d49eba06c173dd8f8ddaee70124946c260c3","raw_url":"https://app.decimal.ai/s/agentscope-ai-03-ref-hallucination-arena/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-03-ref-hallucination-arena"}