{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T11:56:21Z","timestamp":1781178981541,"version":"3.54.1"},"reference-count":66,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Recent advances in Large Language Models have led to Large Reasoning Models, which produce step\u2010by\u2010step reasoning traces. Such traces may offer insight into how models think, improving explainability and clarifying the underlying process. These traces, however, are often verbose and complex, making them cognitively demanding to comprehend. With this in mind, we propose\n                    <jats:italic>\n                      R\n                      <jats:sc>e<\/jats:sc>\n                      T\n                      <jats:sc>race<\/jats:sc>\n                    <\/jats:italic>\n                    , an interactive system that structures and visualizes textual reasoning traces to support understanding. We use a validated reasoning taxonomy to produce structured reasoning data and investigate two types of interactive visualizations thereof. In a controlled human\u2010subject study, the visualizations provided more accurate comprehension of the model's reasoning and less perceived effort than a raw text baseline. The results of this study could have design implications for making long and complex machine\u2010generated reasoning processes more usable and transparent, an important step in AI explainability.\n                  <\/jats:p>","DOI":"10.1111\/cgf.70452","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:58:42Z","timestamp":1781175522000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["R\n                    <scp>e<\/scp>\n                    T\n                    <scp>race<\/scp>\n                    : Interactive Visualizations for Reasoning Traces of Large Reasoning Models"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7854-0778","authenticated-orcid":false,"given":"L.","family":"Felder","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0567-785X","authenticated-orcid":false,"given":"J.","family":"Miller","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2191-4413","authenticated-orcid":false,"given":"M.","family":"Wallinger","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0477-2724","authenticated-orcid":false,"given":"S. G.","family":"Kobourov","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2011-9618","authenticated-orcid":false,"given":"C.","family":"Chen","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_2_10_3_2","unstructured":"Anthropic:Claude 3.7 sonnet system card. 1 2"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1002\/smr.291"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1803_3"},{"key":"e_1_2_10_7_2","unstructured":"CuadronA. et. al.: The danger of overthinking: Examining the reasoning\u2010action dilemma in agentic tasks.CoRR abs\/2502.08235(2025). arXiv:2502.08235 doi:10.48550\/ARXIV.2502.08235. 2"},{"key":"e_1_2_10_8_2","unstructured":"CobbeK. KosarajuV. BavarianM. ChenM. JunH. KaiserL. PlappertM. TworekJ. HiltonJ. NakanoR. HesseC. SchulmanJ.: Training verifiers to solve math word problems.CoRR abs\/2110.14168(2021). URL:https:\/\/arxiv.org\/abs\/2110.14168 arXiv:2110.14168. 6"},{"key":"e_1_2_10_9_2","unstructured":"ComaniciG. e. a.:Gemini 2.5: Pushing the Frontier with Advanced Reasoning Multimodality Long Context and Next Generation Agentic Capabilities July2025. arXiv:2507.06261 doi:10.48550\/arXiv.2507.06261. 6"},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030357"},{"key":"e_1_2_10_11_2","unstructured":"DeepSeek\u2010AI Guo D. et al.:DeepSeek\u2010R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning Jan.2025. arXiv:2501.12948 doi:10.48550\/arXiv.2501.12948. 1 2 5"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"DibiaV.: LIDA: A tool for automatic generation of grammar\u2010agnostic visualizations and infographics using large language models. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics(July2023) pp.113\u2013126. doi:10.18653\/v1\/2023.acl\u2010demo.11. 2","DOI":"10.18653\/v1\/2023.acl-demo.11"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/VIS54172.2023.00015"},{"key":"e_1_2_10_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979114"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010319\u201098131\u20104_1"},{"key":"e_1_2_10_16_2","unstructured":"DuaD. WangY. DasigiP. StanovskyG. SinghS. GardnerM.: DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs. InProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics(June2019) pp.2368\u20132378. doi:10.18653\/v1\/N19\u20101246. 6"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642474"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/24039.24041"},{"key":"e_1_2_10_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642139"},{"key":"e_1_2_10_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl\u2010main.491"},{"key":"e_1_2_10_21_2","doi-asserted-by":"publisher","DOI":"10.1177\/0018720814547570"},{"key":"e_1_2_10_21_3","doi-asserted-by":"crossref","unstructured":"doi:10.1177\/0018720814547570. 10","DOI":"10.1177\/0018720814547570"},{"key":"e_1_2_10_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings\u2010acl.67"},{"key":"e_1_2_10_23_2","unstructured":"HealyD.:Frames_of_mind: Animating R1's thoughts.https:\/\/github.com\/dhealy05\/frames_of_mind. 3"},{"key":"e_1_2_10_24_2","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.ivs.9500115"},{"key":"e_1_2_10_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_2_10_26_2","unstructured":"HouB. ZhangY. JiJ. LiuY. QianK. AndreasJ. ChangS.: Thinkprune: Pruning long chain\u2010of\u2010thought of llms via reinforcement learning.CoRR abs\/2504.01296(2025). arXiv: 2504.01296 doi:10.48550\/ARXIV.2504.01296. 1"},{"key":"e_1_2_10_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606737"},{"key":"e_1_2_10_28_2","unstructured":"KumarK. AshrafT. ThawakarO. AnwerR. M. CholakkalH. ShahM. YangM.\u2010H. TorrP. H. S. KhanF. S. KhanS.:LLM Post\u2010Training: A Deep Dive into Reasoning Large Language Models. arXiv:2502.21321 doi:10.48550\/arXiv.2502.21321. 1"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2678025.2701399"},{"key":"e_1_2_10_30_2","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Kojima T.","year":"2022"},{"key":"e_1_2_10_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2346677"},{"key":"e_1_2_10_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACIFICVIS.2015.7156366"},{"key":"e_1_2_10_33_2","unstructured":"KorbakT. e. a.:Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety July2025. arXiv:2507.11473 doi:10.48550\/arXiv.2507.11473. 1 2 9"},{"key":"e_1_2_10_34_2","unstructured":"LinB. Y. BrasR. L. RichardsonK. SabharwalA. PoovendranR. ClarkP. ChoiY.:ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning July2025. arXiv: 2502.01100 doi:10.48550\/arXiv.2502.01100. 6"},{"key":"e_1_2_10_35_2","first-page":"1","volume-title":"Proceedings of CHI","author":"Liao Q. V.","year":"2020"},{"key":"e_1_2_10_35_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3313831.3376590. 6 9","DOI":"10.1145\/3313831.3376590"},{"key":"e_1_2_10_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2467195"},{"key":"e_1_2_10_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573808"},{"key":"e_1_2_10_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl\u2010demo.14"},{"key":"e_1_2_10_39_2","unstructured":"LiC. WuW. ZhangH. XiaY. MaoS. DongL. Vuli\u0107I. WeiF.: Imagine while reasoning in space: Multimodal visualization\u2010of\u2010thought.arXiv preprint arXiv:2501.07542(2025). 2"},{"key":"e_1_2_10_40_2","unstructured":"Marjanovi\u0107S. V. PatelA. AdlakhaV. AghajohariM. BehnamGhaderP. BhatiaM. KhandelwalA. KraftA. KrojerB. L\u00f9X. H. MeadeN. ShinD. KazemnejadA. KamathG. MosbachM. Sta\u0144czakK. ReddyS.:DeepSeek\u2010R1 Thoughtology: Let's <think> about LLM Reasoning Apr.2025. arXiv:2504.07128 doi:10.48550\/arXiv.2504.07128. 1 3 4 10"},{"key":"e_1_2_10_41_2","doi-asserted-by":"crossref","unstructured":"Muennighoff N. e.a.:s1: Simple test\u2010time scaling. InProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing(Suzhou China Nov.2025) ChristodoulopoulosC. ChakrabortyT. RoseC. PengV. (Eds.) Association for Computational Linguistics pp.20286\u201320332. doi:10.18653\/v1\/2025.emnlp\u2010main.1025. 1","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"e_1_2_10_42_2","unstructured":"MuellerS. T. VeinottE. S. HoffmanR. R. KleinG. AlamL. MamunT. ClanceyW. J.: Principles of explanation in human\u2010ai systems.arXiv preprint arXiv:2102.04972(2021). 10"},{"key":"e_1_2_10_43_2","unstructured":"OpenAI Agarwal S. e. a.:Gpt\u2010oss\u2010120b & gpt\u2010oss\u201020b Model Card. URL:http:\/\/arxiv.org\/abs\/2508.10925 arXiv:2508.10925 doi:10.48550\/arXiv.2508.10925. 10"},{"key":"e_1_2_10_44_2","unstructured":"OpenAI JaechA. et al.:OpenAI o1 System Card. arXiv:2412.16720 doi:10.48550\/arXiv.2412.16720. 1 2"},{"key":"e_1_2_10_45_2","unstructured":"PierseC.:Transformers Interpret Feb.2021. 3"},{"key":"e_1_2_10_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_2_10_47_2","doi-asserted-by":"crossref","unstructured":"RussellD. M. StefikM. J. PirolliP. CardS. K.:The cost structure of sensemaking. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems \u2010 CHI '93 ACM Press pp.269\u2013276. doi:10.1145\/169059.169209. 6","DOI":"10.1145\/169059.169209"},{"key":"e_1_2_10_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518946"},{"key":"e_1_2_10_49_2","unstructured":"ShneidermanB.:Human\u2010Centered AI.Oxford University Press. arXiv:https:\/\/academic.oup.com\/book\/41126\/book-pdf\/50987951\/9780192659996\\_web.pdf"},{"key":"e_1_2_10_49_3","doi-asserted-by":"crossref","unstructured":"doi:10.1093\/oso\/9780192845290.001.0001. 10","DOI":"10.1093\/oso\/9780192845290.001.0001"},{"key":"e_1_2_10_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606756"},{"key":"e_1_2_10_51_2","unstructured":"Svelte.https:\/\/svelte.dev. Accessed: 2025. 5"},{"key":"e_1_2_10_52_2","unstructured":"Svelte Flow.https:\/\/svelteflow.dev. Accessed: 2025. 5"},{"key":"e_1_2_10_53_2","unstructured":"TeamK. Bai Y. e.a.:Kimi K2: Open Agentic Intelligence. URL:http:\/\/arxiv.org\/abs\/2507.20534 arXiv:2507.20534 doi:10.48550\/arXiv.2507.20534. 10"},{"key":"e_1_2_10_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/VISSOFT.2014.25"},{"key":"e_1_2_10_55_2","first-page":"699","article-title":"Process mining and visual analytics: Breathing life into business process models","volume":"17","author":"Aalst W. M.","year":"2011","journal-title":"BPM Center Report BPM\u201011\u201015"},{"key":"e_1_2_10_56_2","unstructured":"VigJ.:A multiscale visualization of attention in the transformer model July 2019. URL:https:\/\/www.aclweb.org\/anthology\/P19\u20103007 doi:10.18653\/v1\/P19\u20103007. 3"},{"key":"e_1_2_10_57_2","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"a Wei J. e.","year":"2022"},{"key":"e_1_2_10_58_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017\u20102866"},{"key":"e_1_2_10_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3724389.3730790"},{"key":"e_1_2_10_60_2","unstructured":"Yang A.o.:Qwen3 Technical Report. arXiv:2505.09388 doi:10.48550\/arXiv.2505.09388. 1 2"},{"key":"e_1_2_10_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025171.3025219"},{"key":"e_1_2_10_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664194"},{"key":"e_1_2_10_63_2","unstructured":"Zhou Z. e.a.: Landscape of thoughts: Visualizing the reasoning process of large language models.arXiv preprint arXiv:2503.22165(2025). 3"},{"key":"e_1_2_10_64_2","doi-asserted-by":"crossref","unstructured":"Zou R. e.a.: Gistvis: Automatic generation of word\u2010scale visualizations from data\u2010rich documents. InProceedings of the 2025 CHI(2025) pp.1\u201318. 2","DOI":"10.1145\/3706598.3713881"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70452","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70452","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:58:56Z","timestamp":1781175536000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70452"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":66,"alternative-id":["10.1111\/cgf.70452"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70452","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]},"assertion":[{"value":"2026-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70452"}}