{"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=M3P&bench=Xgqa","json_url":"https://assignee.net/benchmarks/evidence.json?model=M3P&bench=Xgqa","model":"M3P","benchmark":"Xgqa","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":2021,"year_max":2022,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":0.0,"max_score_pct":80.0},"spread_pp":80.0,"severity":"HIGH","entries":[{"model":"M3P","benchmark":"Xgqa","score_pct":80.0,"source_title":"Delving Deeper into Cross-lingual Visual Question Answering","source_url":"http://arxiv.org/abs/2202.07630v2","source_domain":"arxiv.org","year":2022},{"model":"M3P","benchmark":"Xgqa","score_pct":58.43,"source_title":"xGQA: Cross-Lingual Visual Question Answering","source_url":"http://arxiv.org/abs/2109.06082v2","source_domain":"arxiv.org","year":2021},{"model":"M3P","benchmark":"Xgqa","score_pct":0.0,"source_title":"xGQA: Cross-Lingual Visual Question Answering","source_url":"https://doi.org/10.18653/v1/2022.findings-acl.196","source_domain":"doi.org","year":2022}],"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."]}