PlotGround：将图表数字化锚定于真实科学图形及其源数据

中文摘要 AI 辅助

科学图形常常编码了机器可读形式中不易获取的定量结果，使得准确的图表数字化对于验证和重用已发表的研究发现至关重要。然而，目前尚不清楚现有模型从真实科学图形中恢复绘图值的准确程度，因为现有基准大多依赖合成图表或仅覆盖有限的图表类型。我们提出了PlotGround，一个自动化流水线，用于从真实科学图形及其作者发布的源数据构建图表数字化基准。PlotGround将图形映射到源表格，识别可重建的面板，并生成带有源接地参考值的定量问题。我们使用PlotGround构建了PlotGround-1k，一个包含来自1066篇bioRxiv预印本的1119个问题的人工验证基准。在十六个多模态模型中，最佳模型在±5%相对误差容限下达到87.5%的准确率。将容限收紧至±2%会使每个模型的准确率降低11至24个百分点，揭示了近似视觉读取与精确定量恢复之间的差距。PlotGround的成对图形-源结构使我们能够比较从图形和源表格中恢复相同值的准确度。提供源表格而非图形，将编码代理的准确率从90.0%提升至97.4%，同时将成本降低72%。

英文摘要

Scientific figures often encode quantitative results that are not readily available in machine-readable form, making accurate plot digitization important for verifying and reusing published findings. Yet it remains unclear how accurately current models recover plotted values from real scientific figures, as existing benchmarks rely largely on synthetic charts or cover only a limited range of chart types. We introduce PlotGround, an automated pipeline for building plot digitization benchmarks from real scientific figures and their author-released source data. PlotGround maps figures to source tables, identifies reconstructable panels, and generates quantitative questions with source-grounded reference values. We use PlotGround to construct PlotGround-1k, a human-verified benchmark of 1,119 questions from 1,066 bioRxiv preprints. Across sixteen multimodal models, the best reaches 87.5% accuracy at a $\pm 5\%$ relative-error tolerance. Tightening the tolerance to $\pm 2\%$ lowers every model's accuracy by 11-24 percentage points, revealing a gap between approximate visual reading and precise quantitative recovery. PlotGround's paired figure-source structure lets us compare how accurately the same values are recovered from figures and from source tables. Providing source tables instead of figures raises a coding agent's accuracy from 90.0% to 97.4% while cutting cost by 72%.

发表机构

• Generative Expert Labs, Inc（生成专家实验室公司）
• Stanford University（斯坦福大学）
• Princeton University（普林斯顿大学）

机构由 AI 辅助整理，请以论文原文为准。