{"ID":2898532,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02212","arxiv_id":"2507.02212","title":"SciGA: A Comprehensive Dataset for Designing Graphical Abstracts in Academic Papers","abstract":"Graphical Abstracts (GAs) play a crucial role in visually conveying the key findings of scientific papers. Although recent research increasingly incorporates visual materials such as Figure 1 as de facto GAs, their potential to enhance scientific communication remains largely unexplored. Designing effective GAs requires advanced visualization skills, hindering their widespread adoption. To tackle these challenges, we introduce SciGA-145k, a large-scale dataset comprising approximately 145,000 scientific papers and 1.14 million figures, specifically designed to support GA selection and recommendation, and to facilitate research in automated GA generation. As a preliminary step toward GA design support, we define two tasks: 1) Intra-GA Recommendation, identifying figures within a given paper well-suited as GAs, and 2) Inter-GA Recommendation, retrieving GAs from other papers to inspire new GA designs. Furthermore, we propose Confidence Adjusted top-1 ground truth Ratio (CAR), a novel recommendation metric for fine-grained analysis of model behavior. CAR addresses limitations of traditional rank-based metrics by considering that not only an explicitly labeled GA but also other in-paper figures may plausibly serve as GAs. Benchmark results demonstrate the viability of our tasks and the effectiveness of CAR. Collectively, these establish a foundation for advancing scientific communication within AI for Science.","short_abstract":"Graphical Abstracts (GAs) play a crucial role in visually conveying the key findings of scientific papers. Although recent research increasingly incorporates visual materials such as Figure 1 as de facto GAs, their potential to enhance scientific communication remains largely unexplored. Designing effective GAs require...","url_abs":"https://arxiv.org/abs/2507.02212","url_pdf":"https://arxiv.org/pdf/2507.02212v2","authors":"[\"Takuro Kawada\",\"Shunsuke Kitada\",\"Sota Nemoto\",\"Hitoshi Iyatomi\"]","published":"2025-07-03T00:21:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\",\"cs.LG\"]","methods":"[]","has_code":false}