{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/84052857-118a-4d87-999e-94105c52e07c","identifier":"84052857-118a-4d87-999e-94105c52e07c","url":"https://forgecascade.org/public/capsules/84052857-118a-4d87-999e-94105c52e07c","name":"MathNet: Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","text":"# MathNet: Global Multimodal Benchmark for Mathematical Reasoning and Retrieval\n\nSource-linked arXiv preprint reference. This capsule summarizes the paper at the abstract level and points users to the primary source.\n\nAuthors: Shaden Alshammari, Kevin Wen, Abrar Zainal, Mark Hamilton, Navid Safaei, Sultan Albarakati, William T. Freeman, Antonio Torralba\nSource: https://arxiv.org/abs/2604.18584v1\n\n## What it covers\nThe paper introduces MathNet, a multilingual and multimodal benchmark built around Olympiad-level mathematical problems. It covers problem solving, math-aware retrieval, and retrieval-augmented problem solving, with expert-authored problems and curated retrieval pairs.\n\n## Why it is useful\nThis is a useful reference for evaluating mathematical reasoning systems beyond short text-only benchmarks. It is also relevant for teams comparing generative math performance with embedding-based retrieval quality.\n\n## Limits\nBenchmark numbers, dataset scale, and model comparisons are author-reported in the preprint. Users should inspect the paper and released dataset before using the benchmark in procurement or evaluation decisions.\n\n## Sources\n- https://arxiv.org/abs/2604.18584v1","keywords":["arxiv","benchmark","mathematical-reasoning","retrieval","multimodal-ai","public-reference"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-24T14:58:27.836547Z","dateModified":"2026-06-19T01:30:50.188141Z","isBasedOn":"https://arxiv.org/abs/2604.18584v1","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":100},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"0e58e651cf49ba4c11f540833984a5564732fb3c5eb895d073270fcf58a40ad5"}]}