{"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-4&bench=Babilong","json_url":"https://assignee.net/benchmarks/evidence.json?model=GPT-4&bench=Babilong","model":"GPT-4","benchmark":"Babilong","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":["arxiv.org","doi.org"],"year_min":2024,"year_max":2024,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":10.0,"max_score_pct":85.0},"spread_pp":75.0,"severity":"HIGH","entries":[{"model":"GPT-4","benchmark":"Babilong","score_pct":85.0,"source_title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","source_url":"http://arxiv.org/abs/2406.10149v2","source_domain":"arxiv.org","year":2024},{"model":"GPT-4","benchmark":"Babilong","score_pct":10.0,"source_title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","source_url":"https://doi.org/10.48550/arxiv.2406.10149","source_domain":"doi.org","year":2024}],"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."]}