{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.10677", "kind": "paper", "url": "https://arxiv.org/abs/2608.10677"}], "authors": ["Suhaas Garre", "Chris Mutty", "Sushant Mehta", "Edwin Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.10677", "source_url": "https://arxiv.org/abs/2608.10677"}, "categories": ["Finance", "Manufacturing & Process Control", "Vision & 3D", "cs.CV"], "description": {"en": "Chartography evaluates vision-language models on 100 chart-understanding tasks sourced from professional practice, with questions authored by domain experts and triple-verified. The benchmark uses pass@1 accuracy as the scoring metric across 30 frontier model configurations."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.10677", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.10677", "title": "Chartography"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.10677", "modality": null, "name": "Chartography", "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_chartography_26c993c6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a4ab4dd7b234aa4f2f4d40a6fabc126810f3034bbecae495801362501858e8c6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.10677"}, "publisher": null, "released": "2026-08-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.10677", "source_url": "https://arxiv.org/abs/2608.10677"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-10677", "source": "claire_radar", "source_benchmark_id": "2608.10677", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Manufacturing & Process Control", "Finance"], "area": "Vision & 3D", "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/2608.10677", "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"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "596c35b8826016fed1a9d257e3e85883bbd76f1636a65e7969490e6c422c1f50", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Chartography evaluates vision-language models on 100 chart-understanding tasks sourced from professional practice, with questions authored by domain experts and triple-verified. The benchmark uses pass@1 accuracy as the scoring metric across 30 frontier model configurations.", "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"], "snippet": "We introduce Chartography, a benchmark of 100 tasks that pair charts drawn from professional practice, in domain-specific formats that standard chart benchmarks rarely include, with questions written by professionals who read these charts for a living and independently verified by three additional experts."}, "familyId": "bmf_ac7027e150a2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_chartography_26c993c6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Manufacturing", "Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.10677", "paper": "https://arxiv.org/abs/2608.10677", "pdf": "https://arxiv.org/pdf/2608.10677", "project": null, "report": "https://arxiv.org/abs/2608.10677"}, "metrics": [], "motivation": "Professionals across medicine, engineering, finance, manufacturing, and the sciences often make consequential decisions from charts.", "name": "Chartography", "oneLine": "Chartography evaluates vision-language models on 100 chart-understanding tasks sourced from professional practice, with questions authored by domain experts and triple-verified. The benchmark uses pass@1 accuracy as the scoring metric across 30 frontier model configurations.", "paperTitle": "Chartography: A Benchmark for Professional Chart Understanding", "primaryDomain": "Manufacturing & Process Control", "publication": {"evidence": "16 pages, 5 figures, 5 tables. Accepted at the 2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2), ECCV 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.10677", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2), ECCV 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Chartography Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.10677"}], "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": "2026-08-11", "source": {"authors": ["Suhaas Garre", "Chris Mutty", "Sushant Mehta", "Edwin Chen"], "categories": ["cs.CV"], "id": "2608.10677", "title": "Chartography: A Benchmark for Professional Chart Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2608.10677"}, "sourceUpdatedAt": "2026-08-11T08:57:25Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "16 pages, 5 figures, 5 tables. Accepted at the 2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2), ECCV 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "16 pages, 5 figures, 5 tables. Accepted at the 2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2), ECCV 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.10677"}], "reviewStatus": "accepted", "venueName": "2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2), ECCV 2026"}], "whyItMatters": "Existing chart benchmarks are saturated and skewed toward simple formats, leaving a gap in measuring performance on realistic, domain-specific charts. Chartography provides a harder, expert-validated test that can differentiate model capabilities in high-stakes professional contexts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
