{"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=LLaVA-Video-7B&bench=Longvideobench","json_url":"https://assignee.net/benchmarks/evidence.json?model=LLaVA-Video-7B&bench=Longvideobench","model":"LLaVA-Video-7B","benchmark":"Longvideobench","source_count":3,"source_coverage":{"record_count":3,"distinct_source_count":3,"coverage_level":"MODERATE","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":3,"missing_source_url_count":0,"domains":["arxiv.org","doi.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":3.3,"max_score_pct":62.7},"spread_pp":59.4,"severity":"HIGH","entries":[{"model":"LLaVA-Video-7B","benchmark":"Longvideobench","score_pct":62.7,"source_title":"Adaptive Keyframe Sampling for Long Video Understanding","source_url":"http://arxiv.org/abs/2502.21271v1","source_domain":"arxiv.org","year":2025},{"model":"LLaVA-Video-7B","benchmark":"Longvideobench","score_pct":3.3,"source_title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","source_url":"http://arxiv.org/abs/2502.03183v3","source_domain":"arxiv.org","year":2025},{"model":"LLaVA-Video-7B","benchmark":"Longvideobench","score_pct":3.28,"source_title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","source_url":"https://doi.org/10.1109/wacv61042.2026.00695","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."]}