{"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=Rouge-L","json_url":"https://assignee.net/benchmarks/evidence.json?model=GPT-3.5&bench=Rouge-L","model":"GPT-3.5","benchmark":"Rouge-L","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"],"year_min":2023,"year_max":2025,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":1.8,"max_score_pct":80.0},"spread_pp":78.2,"severity":"HIGH","entries":[{"model":"GPT-3.5","benchmark":"Rouge-L","score_pct":80.0,"source_title":"Comparison of Open-Source and Proprietary LLMs for Machine Reading Comprehension: A Practical Analysis for Industrial Applications","source_url":"http://arxiv.org/abs/2406.13713v2","source_domain":"arxiv.org","year":2024},{"model":"GPT-3.5","benchmark":"Rouge-L","score_pct":18.9,"source_title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","source_url":"http://arxiv.org/abs/2305.09758v3","source_domain":"arxiv.org","year":2023},{"model":"GPT-3.5","benchmark":"Rouge-L","score_pct":18.1,"source_title":"Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation","source_url":"http://arxiv.org/abs/2411.18583v1","source_domain":"arxiv.org","year":2024},{"model":"GPT-3.5","benchmark":"Rouge-L","score_pct":1.8,"source_title":"ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback","source_url":"http://arxiv.org/abs/2504.04657v1","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."]}