{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.18586", "kind": "paper", "url": "https://arxiv.org/abs/2608.18586"}], "authors": ["Zinuo Guo", "Min Zhang", "Bo Jiang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.18586", "source_url": "https://arxiv.org/abs/2608.18586"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates multimodal LLMs and OCR systems on handwritten text and mathematical expression recognition across six subtasks and twelve subsets with 77.57K images."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.18586", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.18586", "title": "OmniHandwritingOCR"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.18586", "modality": null, "name": "OmniHandwritingOCR", "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": "true", "origin_record_id": "bm_omnihandwritingocr_85cf42ca", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "637dc7af0709a1b89246ad80e4e03b9d332518483759b542e5382fd751c75cd6", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-25T23:23:46.758372Z", "source_url": "https://arxiv.org/abs/2608.18586"}, "publisher": null, "released": "2026-08-19", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.18586", "source_url": "https://arxiv.org/abs/2608.18586"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-18586", "source": "claire_radar", "source_benchmark_id": "2608.18586", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.18586", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The CIKM venue and comprehensive handwritten OCR coverage, including new formula corpus, may draw interest from document AI researchers.", "score": 60}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T23:23:46.758372Z", "inputHash": "a13f277371086f1142d4638e8fe2044697e25c4aef8f50f31e9d1449ea6a480b", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios", "canonicalNameSource": "paper_title", "decisionReason": "The paper defines a specific benchmark with subsets, metrics, and a unified protocol, and the arxiv report serves as a public source for the evaluation contract.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T23:23:46.758372Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal LLMs and OCR systems on handwritten text and mathematical expression recognition across six subtasks and twelve subsets with 77.57K images.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce OmniHandwritingOCR, a diagnostic benchmark for evaluating MLLMs and OCR systems on handwritten OCR."}, "familyId": "bmf_485481a48f61", "firstSeenAt": "2026-08-20", "heat": null, "id": "bm_omnihandwritingocr_85cf42ca", "indexedAt": "2026-08-20T14:20:56.750721Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.18586", "pdf": "https://arxiv.org/pdf/2608.18586", "project": null, "report": "https://arxiv.org/abs/2608.18586"}, "metrics": [], "motivation": "Multimodal large language models (MLLMs) are increasingly used as OCR systems in document and knowledge-processing pipelines, but their ability to faithfully read real handwriting remains underexplored.", "name": "OmniHandwritingOCR", "oneLine": "Evaluates multimodal LLMs and OCR systems on handwritten text and mathematical expression recognition across six subtasks and twelve subsets with 77.57K images.", "paperTitle": "OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.18586", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-20T14:20:56.750721Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-19", "source": {"authors": ["Zinuo Guo and Min Zhang and Bo Jiang"], "categories": ["cs.CV", "cs.AI"], "id": "2608.18586", "title": "OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios", "type": "arxiv", "url": "https://arxiv.org/abs/2608.18586"}, "sourceUpdatedAt": "2026-08-19T06:27:05Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Provides a challenging diagnostic benchmark for realistic handwritten OCR, highlighting failures in complex formulas and visual grounding that existing printed-text benchmarks miss."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
