Presentation Information

1:45 PM - 2:00 PM JST(4:45 AM - 5:00 AM UTC)

[10p-N304-2]Development of Digitization Tools from Plots in Published Papers

〇Yukari Katsura^1,2,3, Aditya Acharya^1,4, Tomoya Mato¹, Eiji Koyama¹, Dewi Yana¹, Atsumi Tanaka¹, Masahiko Demura¹ (1.NIMS, 2.Univ. of Tsukuba, 3.RIKEN, 4.IIT (BHU) Varanasi)

Keywords:

database,graph,literature data

We developed a tool that assists in extracting numerical data from line plots in research papers. The tool automatically extracts plots distinguished by color, and we built a web system that handles the entire workflow—from cropping plot images out of paper PDFs, to labeling the axes, to extracting the numerical data. We also integrated a paper-summarization function that builds on Starrydata Auto-Summary GPT. For reusable open-access papers, a commercial LLM summarizes the objective, approach, figures, samples, and conclusions of each paper, which can then be referenced.

Back to Session information