{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chartgalaxy-a-dataset-for-infographic-chart","title":"ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation","arxiv_id":"2505.18668","date":"2025-05-24","proceeding":null,"authors":["Zhen Li","Yukai Guo","Duan Li","Xinyuan Guo","Bowen Li","Lanxi Xiao","Shenyu Qiao","Jiashu Chen","Zijian Wu","HUI ZHANG","Xinhuan Shu","Shixia Liu"],"abstract":"Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 330 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.","url_abs":"https://arxiv.org/abs/2505.18668v1","url_pdf":"https://arxiv.org/pdf/2505.18668v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"chartgalaxy-a-dataset-for-infographic-chart","repo_url":"https://github.com/chartgalaxy/chartgalaxy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"chartgalaxy-a-dataset-for-infographic-chart","repo_url":"https://github.com/cooldawnant/infochartqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"chartgalaxy-a-dataset-for-infographic-chart","repo_url":"https://github.com/orionbench/orionbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"chart-understanding","task_name":"Chart Understanding"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.18668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18668"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chartgalaxy/chartgalaxy","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/orionbench/orionbench","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cooldawnant/infochartqa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fb35a4fb403a10b9","entry":"fix_list_format","repo":"chartgalaxy/chartgalaxy","repo_kind":"official","path":"code_understanding/scoring.py","file_url":"https://github.com/chartgalaxy/chartgalaxy/blob/HEAD/code_understanding/scoring.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb35a4fb403a10b9"}},{"code_sha256_prefix":"36667e7b107acaec","entry":"load_predictions","repo":"chartgalaxy/chartgalaxy","repo_kind":"official","path":"code_understanding/scoring.py","file_url":"https://github.com/chartgalaxy/chartgalaxy/blob/HEAD/code_understanding/scoring.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"36667e7b107acaec"}},{"code_sha256_prefix":"af8755d4fa414194","entry":"parse_to_list","repo":"chartgalaxy/chartgalaxy","repo_kind":"official","path":"code_understanding/scoring.py","file_url":"https://github.com/chartgalaxy/chartgalaxy/blob/HEAD/code_understanding/scoring.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af8755d4fa414194"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}