{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12262", "kind": "paper", "url": "https://arxiv.org/abs/2608.12262"}, {"id": "gh:aigrounding/diagram-mmu", "kind": "repo", "url": "https://github.com/AIGrounding/Diagram-MMU"}, {"kind": "website", "url": "https://vi-ocean.github.io/projects/diagram-mmu"}], "authors": ["Weihao Bo", "Shan Zhang", "Yanpeng Sun", "Jie Liu", "Yongke Yao", "Jinhao Du", "Wei He", "Kai Zou", "Zechao Li", "Jingdong Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12262", "source_url": "https://arxiv.org/abs/2608.12262"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Diagram-MMU evaluates multimodal language models on parsing scientific diagrams into LaTeX TikZ code, editing diagram code, and answering questions about diagrams, using 3.7k diagrams and 18.3k questions across six domains."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12262", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12262", "title": "Diagram-MMU"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.12262", "modality": null, "name": "Diagram-MMU", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_diagram-mmu_a41bffa4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "76d6dca5e571194a6e8d1d4d5732a2b91e1970e92355dd7b402ab1d4234c62d9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12262"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12262", "source_url": "https://arxiv.org/abs/2608.12262"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12262", "source": "claire_radar", "source_benchmark_id": "2608.12262", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/AIGrounding/Diagram-MMU", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.12262", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "1adae049c186596aba9d2f70186ac67ca1a4334d31facfbf4a63cddbd6526ca2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Diagram-MMU evaluates multimodal language models on parsing scientific diagrams into LaTeX TikZ code, editing diagram code, and answering questions about diagrams, using 3.7k diagrams and 18.3k questions across six domains.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "In this paper, we build a benchmark, Diagram-MMU, a multi-modal benchmark designed to assess MLLMs' ability for scientific diagram parsing and understanding."}, "familyId": "bmf_39ca0919aed5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/AIGrounding/Diagram-MMU", "url": "https://vi-ocean.github.io/projects/diagram-mmu"}], "scope": "benchmark_repo", "url": "https://github.com/AIGrounding/Diagram-MMU", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_diagram-mmu_a41bffa4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/AIGrounding/Diagram-MMU", "data": null, "hfPaper": "https://huggingface.co/papers/2608.12262", "paper": "https://arxiv.org/abs/2608.12262", "pdf": "https://arxiv.org/pdf/2608.12262", "project": "https://vi-ocean.github.io/projects/diagram-mmu", "report": "https://arxiv.org/abs/2608.12262"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration.", "name": "Diagram-MMU", "oneLine": "Diagram-MMU evaluates multimodal language models on parsing scientific diagrams into LaTeX TikZ code, editing diagram code, and answering questions about diagrams, using 3.7k diagrams and 18.3k questions across six domains.", "paperTitle": "Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12262", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 526, "score": 23}, "method": "attention-ranking-v13", "rank": 526, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Weihao Bo", "Shan Zhang", "Yanpeng Sun", "Jie Liu", "Yongke Yao", "Jinhao Du", "Wei He", "Kai Zou", "Zechao Li", "Jingdong Wang"], "categories": ["cs.CV", "cs.AI"], "id": "2608.12262", "title": "Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12262"}, "sourceUpdatedAt": "2026-08-12T17:04:13Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "The evaluation provides insight into model capabilities on diagram-to-code generation tasks, a practical need in scientific authoring tools, and identifies gaps between reasoning and code generation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
