{"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=DeepSeek-R1&bench=MATH","json_url":"https://assignee.net/benchmarks/evidence.json?model=DeepSeek-R1&bench=MATH","model":"DeepSeek-R1","benchmark":"MATH","source_count":4,"source_coverage":{"record_count":4,"distinct_source_count":4,"coverage_level":"MODERATE","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":4,"missing_source_url_count":0,"domains":["arxiv.org","openalex.org"],"year_min":2025,"year_max":2026,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":30.0,"max_score_pct":97.3},"spread_pp":67.3,"severity":"HIGH","entries":[{"model":"DeepSeek-R1","benchmark":"MATH","score_pct":97.3,"source_title":"Quantitative Analysis of Performance Drop in DeepSeek Model Quantization","source_url":"http://arxiv.org/abs/2505.02390v2","source_domain":"arxiv.org","year":2025},{"model":"DeepSeek-R1","benchmark":"MATH","score_pct":79.8,"source_title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","source_url":"https://openalex.org/W7125352730","source_domain":"openalex.org","year":2026},{"model":"DeepSeek-R1","benchmark":"MATH","score_pct":72.22,"source_title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","source_url":"http://arxiv.org/abs/2501.11790v4","source_domain":"arxiv.org","year":2025},{"model":"DeepSeek-R1","benchmark":"MATH","score_pct":30.0,"source_title":"Token-Hungry, Yet Precise: DeepSeek R1 Highlights the Need for Multi-Step Reasoning Over Speed in MATH","source_url":"http://arxiv.org/abs/2501.18576v1","source_domain":"arxiv.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."]}