{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.13441", "kind": "paper", "url": "https://arxiv.org/abs/2608.13441"}, {"id": "gh:solunny/edit2tikz", "kind": "repo", "url": "https://github.com/Solunny/Edit2TikZ"}], "authors": ["Zongyun Zhang", "Jiacheng Ruan", "Xian Gao", "Ruizhu Zhou", "Lingcheng Meng", "Lining Hu", "Ting Liu", "Yuzhuo Fu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13441", "source_url": "https://arxiv.org/abs/2608.13441"}, "categories": ["Software & AI Compute", "Vision & 3D", "cs.CV"], "description": {"en": "Edit2TikZ evaluates instruction-guided scientific figure editing with TikZ code, featuring 1,548 samples with textual or visual localization requests and multi-step edits, using a human-aligned evaluation framework to measure edit completion and content preservation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13441", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13441", "title": "Edit2TikZ"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.13441", "modality": null, "name": "Edit2TikZ", "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_edit2tikz_4730ba41", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5aed952e92e1585f9ea7f373d7f1a03e388ee1fc9e0fdce1d4387fb2d4af71e9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.13441"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13441", "source_url": "https://arxiv.org/abs/2608.13441"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13441", "source": "claire_radar", "source_benchmark_id": "2608.13441", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Software & AI Compute"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Solunny/Edit2TikZ", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.13441", "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": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "c72b462be79393ac1f33e98bd8b2621eb4ba990f93da0280006cf195e2551067", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Edit2TikZ evaluates instruction-guided scientific figure editing with TikZ code, featuring 1,548 samples with textual or visual localization requests and multi-step edits, using a human-aligned evaluation framework to measure edit completion and content preservation.", "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": "We introduce Edit2TikZ, a comprehensive benchmark for scientific figure editing tasks, featuring 1,548 diverse and high-quality samples."}, "familyId": "bmf_95a10c6e66b2", "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/Solunny/Edit2TikZ", "url": "https://github.com/Solunny/Edit2TikZ"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Solunny/Edit2TikZ", "url": "https://huggingface.co/papers/2608.13441"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Solunny/Edit2TikZ.", "url": "https://arxiv.org/abs/2608.13441"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Solunny/Edit2TikZ", "url": "https://arxiv.org/abs/2608.13441"}], "scope": "benchmark_repo", "url": "https://github.com/Solunny/Edit2TikZ", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_edit2tikz_4730ba41", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/Solunny/Edit2TikZ", "data": null, "hfPaper": "https://huggingface.co/papers/2608.13441", "paper": "https://arxiv.org/abs/2608.13441", "pdf": "https://arxiv.org/pdf/2608.13441", "project": null, "report": "https://arxiv.org/abs/2608.13441"}, "metrics": [], "motivation": "Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code presents a greater challenge: a model must jointly recover visual structure, ground the requested change, generate compilable code, and preserve all unrelated content.", "name": "Edit2TikZ", "oneLine": "Edit2TikZ evaluates instruction-guided scientific figure editing with TikZ code, featuring 1,548 samples with textual or visual localization requests and multi-step edits, using a human-aligned evaluation framework to measure edit completion and content preservation.", "paperTitle": "Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13441", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Solunny", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Solunny/Edit2TikZ"}], "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 339, "score": 28}, "method": "attention-ranking-v13", "rank": 339, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-13", "source": {"authors": ["Zongyun Zhang", "Jiacheng Ruan", "Xian Gao", "Ruizhu Zhou", "Lingcheng Meng", "Lining Hu", "Ting Liu", "Yuzhuo Fu"], "categories": ["cs.CV"], "id": "2608.13441", "title": "Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13441"}, "sourceUpdatedAt": "2026-08-13T16:27:18Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing benchmarks focus on figure reconstruction or generation, leaving a gap for systematic evaluation of instruction-guided editing with compilable code. This benchmark provides a standardized protocol for assessing models' ability to perform precise, code-based edits while preserving unrelated content, offering practical value for developing reliable multimodal systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
