{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.02956", "kind": "paper", "url": "https://arxiv.org/abs/2607.02956"}, {"id": "gh:zimoqingfeng/more", "kind": "repo", "url": "https://github.com/zimoqingfeng/MORE"}], "authors": ["Long Xu", "Binghong Wu", "Tinghao Yu", "Hao Feng", "Zhenyu Huang", "Haoqing Jiang", "Yunhao Wang", "Shuo Huang", "Feng Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.02956", "source_url": "https://arxiv.org/abs/2607.02956"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "MORE evaluates multilingual document parsing across 149 languages, covering text, formulas, tables, code blocks, catalogs, and reading order, using 1,288 real-world document images with human-refined annotations."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.02956", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.02956", "title": "MORE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.02956", "modality": null, "name": "MORE", "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_more_09a372c7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9c48f45eeff9526aaf8b35d483f414e00b6e8466db1946dbfef7c1fc3c0debf0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.02956"}, "publisher": null, "released": "2026-07-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.02956", "source_url": "https://arxiv.org/abs/2607.02956"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-02956", "source": "claire_radar", "source_benchmark_id": "2607.02956", "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/zimoqingfeng/MORE", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.02956", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "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": "de191e91e618d2ef15e6d3be694619cb5aac0ea95ba4b04d80f106157c7c42e5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MORE evaluates multilingual document parsing across 149 languages, covering text, formulas, tables, code blocks, catalogs, and reading order, using 1,288 real-world document images with human-refined annotations.", "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": "To bridge this gap, we introduce MORE, a large-scale benchmark designed for multilingual document parsing evaluation."}, "familyId": "bmf_187897ce0afc", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/zimoqingfeng/MORE", "url": "https://github.com/zimoqingfeng/MORE"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/zimoqingfeng/MORE", "url": "https://huggingface.co/papers/2607.02956"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/zimoqingfeng/MORE", "url": "https://arxiv.org/abs/2607.02956"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/zimoqingfeng/MORE.", "url": "https://arxiv.org/abs/2607.02956"}], "scope": "project_repo", "url": "https://github.com/zimoqingfeng/MORE", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_more_09a372c7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/zimoqingfeng/MORE", "data": null, "hfPaper": "https://huggingface.co/papers/2607.02956", "paper": "https://arxiv.org/abs/2607.02956", "pdf": "https://arxiv.org/pdf/2607.02956", "project": null, "report": "https://arxiv.org/abs/2607.02956"}, "metrics": [], "motivation": "Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records.", "name": "MORE", "oneLine": "MORE evaluates multilingual document parsing across 149 languages, covering text, formulas, tables, code blocks, catalogs, and reading order, using 1,288 real-world document images with human-refined annotations.", "paperTitle": "MORE: A Multilingual Document Parsing Benchmark and Evaluation", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to the 43rd International Conference on Machine Learning (ICML 2026). 22 pages, 11 figures. Code and dataset available at https://github.com/zimoqingfeng/MORE", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.02956", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "43rd International Conference on Machine Learning (ICML 2026)", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MORE Benchmark Team", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/zimoqingfeng/MORE"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-03", "source": {"authors": ["Long Xu", "Binghong Wu", "Tinghao Yu", "Hao Feng", "Zhenyu Huang", "Haoqing Jiang", "Yunhao Wang", "Shuo Huang", "Feng Zhang"], "categories": ["cs.CV", "cs.CL"], "id": "2607.02956", "title": "MORE: A Multilingual Document Parsing Benchmark and Evaluation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.02956"}, "sourceUpdatedAt": "2026-07-03T04:59:12Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted to the 43rd International Conference on Machine Learning (ICML 2026). 22 pages, 11 figures. Code and dataset available at https://github.com/zimoqingfeng/MORE", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to the 43rd International Conference on Machine Learning (ICML 2026). 22 pages, 11 figures. Code and dataset available at https://github.com/zimoqingfeng/MORE", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.02956"}], "reviewStatus": "accepted", "venueName": "43rd International Conference on Machine Learning (ICML 2026)"}], "whyItMatters": "Existing benchmarks focus on high-resource languages, leaving a gap in assessing multilingual document parsers. MORE provides a broad and structured evaluation to compare model capabilities on low-resource languages and diverse document elements."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
