{"schema":"https://assignee.net/schemas/benchmark-evidence-v1","schema_version":"1.0","contract_version":"benchmark-evidence-v1.0","contract_updated":"2026-06-01","schema_documentation":"https://assignee.net/schemas","changelog_url":"https://assignee.net/changelog","publisher":{"name":"Assignee Research","url":"https://assignee.net"},"html_url":"https://assignee.net/benchmarks/evidence?model=GPT-3.5&bench=Medqa","json_url":"https://assignee.net/benchmarks/evidence.json?model=GPT-3.5&bench=Medqa","model":"GPT-3.5","benchmark":"Medqa","source_count":2,"source_coverage":{"record_count":2,"distinct_source_count":2,"coverage_level":"LIMITED","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":2,"missing_source_url_count":0,"domains":["doi.org","semanticscholar.org"],"year_min":2024,"year_max":2025,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":10.0,"max_score_pct":69.7},"spread_pp":59.7,"severity":"HIGH","entries":[{"model":"GPT-3.5","benchmark":"Medqa","score_pct":69.68,"source_title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","source_url":"https://doi.org/10.1142/9789819807024_0015","source_domain":"doi.org","year":2024},{"model":"GPT-3.5","benchmark":"Medqa","score_pct":10.0,"source_title":"ARE LLMS READY FOR PEDIATRICS? A COMPARATIVE EVALUATION OF MODEL ACCURACY ACROSS CLINICAL DOMAINS","source_url":"https://www.semanticscholar.org/paper/f9e9e6197ecf25d30244539a0e4682ef01e09c29","source_domain":"semanticscholar.org","year":2025}],"interpretation":"This record groups score claims extracted from papers for the same model and benchmark label. A nonzero spread means the public literature reports different values for this cluster.","limitations":["Differences are not automatically errors.","Reported values may differ because of prompts, dataset versions, evaluation protocols, scoring rules, preprocessing, fine-tuning, or reporting conventions.","Source papers remain authoritative for their own claims."]}