{"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=Llama-3.1-8B&bench=Ruler","json_url":"https://assignee.net/benchmarks/evidence.json?model=Llama-3.1-8B&bench=Ruler","model":"Llama-3.1-8B","benchmark":"Ruler","source_count":5,"source_coverage":{"record_count":5,"distinct_source_count":5,"coverage_level":"BROAD","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":5,"missing_source_url_count":0,"domains":["arxiv.org","doi.org"],"year_min":2024,"year_max":2026,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":1.9,"max_score_pct":85.6},"spread_pp":83.7,"severity":"HIGH","entries":[{"model":"Llama-3.1-8B","benchmark":"Ruler","score_pct":85.6,"source_title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","source_url":"http://arxiv.org/abs/2605.08840v1","source_domain":"arxiv.org","year":2026},{"model":"Llama-3.1-8B","benchmark":"Ruler","score_pct":32.0,"source_title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","source_url":"http://arxiv.org/abs/2404.06654v3","source_domain":"arxiv.org","year":2024},{"model":"Llama-3.1-8B","benchmark":"Ruler","score_pct":3.51,"source_title":"AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference","source_url":"http://arxiv.org/abs/2605.12110v1","source_domain":"arxiv.org","year":2026},{"model":"Llama-3.1-8B","benchmark":"Ruler","score_pct":1.94,"source_title":"MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training","source_url":"http://arxiv.org/abs/2510.18830v2","source_domain":"arxiv.org","year":2025},{"model":"Llama-3.1-8B","benchmark":"Ruler","score_pct":1.9,"source_title":"Ruler Score Discrepancies in Llama-3.1-8B Benchmark Evaluations Across Studies","source_url":"https://doi.org/10.5281/zenodo.20582421","source_domain":"doi.org","year":2026}],"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."]}