{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:07:11Z","timestamp":1784279231089,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100009108","name":"Shandong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025CXGC010901"],"award-info":[{"award-number":["2025CXGC010901"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113639","type":"journal-article","created":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T23:24:22Z","timestamp":1774826662000},"page":"113639","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PC","title":["Thought graph traversal for test-time scaling in chest X-ray VLLMs"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9852-4667","authenticated-orcid":false,"given":"Yue","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8022-9484","authenticated-orcid":false,"given":"Zelin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8356-4909","authenticated-orcid":false,"given":"Tom","family":"Gedeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113639_bib0001","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","first-page":"30016","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"10.1016\/j.patcog.2026.113639_bib0002","doi-asserted-by":"crossref","unstructured":"N. Muennighoff, Z. Yang, W. Shi, X. L. Li, L. Fei-Fei, H. Hajishirzi, L. Zettlemoyer, P. Liang, E. Cand\u00e8s, T. Hashimoto, s1: Simple test-time scaling, arXiv preprint, arXiv: 2501.19393(2025).","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"10.1016\/j.patcog.2026.113639_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111300","article-title":"CTPT: Continual test-time prompt tuning for vision-language models","volume":"161","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113639_bib0004","article-title":"Context-aware prompt learning for test-time vision recognition with frozen vision-language model","author":"Yin","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113639_bib0005","unstructured":"C. Snell, J. Lee, K. Xu, A. Kumar, Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters, 2024. https:\/\/arxiv.org\/abs\/2408.03314. 2408.03314."},{"key":"10.1016\/j.patcog.2026.113639_bib0006","unstructured":"OpenAI, Learning to Reason with LLMs, 2024. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/."},{"key":"10.1016\/j.patcog.2026.113639_bib0007","unstructured":"Y. Zhang, S. Wu, Y. Yang, J. Shu, J. Xiao, C. Kong, J. Sang, o1-Coder: an o1 Replication for Coding, 2024. https:\/\/arxiv.org\/abs\/2412.00154. 2412.00154."},{"key":"10.1016\/j.patcog.2026.113639_bib0008","unstructured":"Y. Qin, X. Li, H. Zou, Y. Liu, S. Xia, Z. Huang, Y. Ye, W. Yuan, H. Liu, Y. Li, P. Liu, O1 Replication Journey: A Strategic Progress Report \u2013 Part 1, 2024. https:\/\/arxiv.org\/abs\/2410.18982. 2410.18982."},{"key":"10.1016\/j.patcog.2026.113639_bib0009","unstructured":"DeepSeek-AI, DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning, 2025. https:\/\/arxiv.org\/abs\/2501.12948. 2501.12948."},{"key":"10.1016\/j.patcog.2026.113639_bib0010","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1439","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"issue":"1","key":"10.1016\/j.patcog.2026.113639_bib0011","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.acra.2017.08.005","article-title":"Structured reporting in radiology","volume":"25","author":"Ganeshan","year":"2018","journal-title":"Acad. Radiol."},{"key":"10.1016\/j.patcog.2026.113639_bib0012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113639_bib0013","unstructured":"OpenAI, J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F.L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, et al., GPT-4 Technical Report, 2023. 2303.08774."},{"key":"10.1016\/j.patcog.2026.113639_bib0014","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113639_bib0015","unstructured":"C. Wu, S. Yin, W. Qi, X. Wang, Z. Tang, N. Duan, Visual chatgpt: Talking, drawing and editing with visual foundation models, arXiv preprint, arXiv: 2303.04671(2023)."},{"key":"10.1016\/j.patcog.2026.113639_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11558","article-title":"METransformer: Radiology report generation by transformer with multiple learnable expert tokens","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113639_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102798","article-title":"Radiology report generation with a learned knowledge base and multi-modal alignment","volume":"86","author":"Yang","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113639_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7433","article-title":"Interactive and explainable region-guided radiology report generation","author":"Tanida","year":"2023"},{"key":"10.1016\/j.patcog.2026.113639_bib0019","series-title":"Findings of the Association for Computational Linguistics: ACL 2022","first-page":"448","article-title":"Reinforced cross-modal alignment for radiology report generation","author":"Qin","year":"2022"},{"key":"10.1016\/j.patcog.2026.113639_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13753","article-title":"Exploring and distilling posterior and prior knowledge for radiology report generation","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113639_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3334","article-title":"Dynamic graph enhanced contrastive learning for chest X-ray report generation","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113639_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19809","article-title":"KiUT: knowledge-injected U-Transformer for radiology report generation","author":"Huang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113639_bib0023","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113639_bib0024","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113639_bib0025","series-title":"Advances in Neural Information Processing Systems","article-title":"Large language models are zero-Shot reasoners","author":"Kojima","year":"2022"},{"key":"10.1016\/j.patcog.2026.113639_bib0026","unstructured":"Y. Liu, J. Singh, G. Liu, A. Payani, L. Zheng, Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization, arXiv preprint, arXiv: 2405.20252(2024)."},{"key":"10.1016\/j.patcog.2026.113639_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110399","article-title":"Prompting large language model with context and pre-answer for knowledge-based VQA","volume":"151","author":"Hu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113639_bib0028","doi-asserted-by":"crossref","unstructured":"S. Yao, D. Yu, J. Zhao, I. Shafran, T. Griffiths, Y. Cao, K. Narasimhan, Tree of Thoughts: Deliberate Problem Solving with Large Language Models, in: A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, S. Levine (Eds.), Advances in Neural Information Processing Systems, 36, Curran Associates, Inc., 2023, pp. 11809\u201311822. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/271db9922b8d1f4dd7aaef84ed5ac703-Paper-Conference.pdf.","DOI":"10.52202\/075280-0517"},{"key":"10.1016\/j.patcog.2026.113639_bib0029","unstructured":"Z. Gou, Z. Shao, Y. Gong, Y. Shen, Y. Yang, N. Duan, W. Chen, CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing, 2024. https:\/\/arxiv.org\/abs\/2305.11738. 2305.11738."},{"key":"10.1016\/j.patcog.2026.113639_bib0030","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","first-page":"607","article-title":"Semantic-Aware chest X-ray report generation with domain-Specific lexicon and diversity-Controlled retrieval","author":"Zhang","year":"2026"},{"key":"10.1016\/j.patcog.2026.113639_bib0031","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10348","article-title":"Enhanced contrastive learning with multi-view longitudinal data for chest X-ray report generation","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113639_bib0032","unstructured":"P. Wu, H. Dong, Y. Lin, Y. Ding, Y. Peng, A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation, 2025. https:\/\/arxiv.org\/abs\/2511.12259. 2511.12259."},{"key":"10.1016\/j.patcog.2026.113639_bib0033","unstructured":"S. Bai, K. Chen, X. Liu, J. Wang, W. Ge, S. Song, K. Dang, P. Wang, S. Wang, J. Tang, H. Zhong, Y. Zhu, M. Yang, Z. Li, J. Wan, P. Wang, W. Ding, Z. Fu, Y. Xu, J. Ye, X. Zhang, T. Xie, Z. Cheng, H. Zhang, Z. Yang, H. Xu, J. Lin, Qwen2.5-VL Technical Report, 2025. https:\/\/arxiv.org\/abs\/2502.13923. 2502.13923."},{"key":"10.1016\/j.patcog.2026.113639_bib0034","unstructured":"J. Chen, C. Gui, R. Ouyang, A. Gao, S. Chen, G.H. Chen, X. Wang, R. Zhang, Z. Cai, K. Ji, G. Yu, X. Wan, B. Wang, HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale, 2024. https:\/\/arxiv.org\/abs\/2406.19280. 2406.19280."},{"key":"10.1016\/j.patcog.2026.113639_bib0035","doi-asserted-by":"crossref","unstructured":"Q. Dong, L. Li, D. Dai, C. Zheng, J. Ma, R. Li, H. Xia, J. Xu, Z. Wu, B. Chang, X. Sun, L. Li, Z. Sui, A Survey on In-context Learning, in: Y. Al-Onaizan, M. Bansal, Y.-N. Chen (Eds.), Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Miami, Florida, USA, 2024, pp. 1107\u20131128. 10.18653\/v1\/2024.emnlp-main.64.","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"10.1016\/j.patcog.2026.113639_bib0036","unstructured":"OpenAI, GPT-4o System Card, 2024. https:\/\/arxiv.org\/abs\/2410.21276. 2410.21276."},{"key":"10.1016\/j.patcog.2026.113639_bib0037","series-title":"Proceedings of the Second Workshop on Shortcomings in Vision and Language","first-page":"26","article-title":"A survey on biomedical image captioning","author":"Pavlopoulos","year":"2019"},{"key":"10.1016\/j.patcog.2026.113639_bib0038","doi-asserted-by":"crossref","unstructured":"A.E.W. Johnson, T.J. Pollard, N.R. Greenbaum, M.P. Lungren, C.-y. Deng, Y. Peng, Z. Lu, R.G. Mark, S.J. Berkowitz, S. Horng, MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs, arXiv preprint, arXiv: 1901.07042(2019).","DOI":"10.1038\/s41597-019-0322-0"},{"key":"10.1016\/j.patcog.2026.113639_bib0039","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.patcog.2026.113639_bib0040","series-title":"Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.patcog.2026.113639_bib0041","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.patcog.2026.113639_bib0042","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"374","article-title":"Green: generative radiology report evaluation and error notation","author":"Ostmeier","year":"2024"},{"key":"10.1016\/j.patcog.2026.113639_bib0043","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"590","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.patcog.2026.113639_bib0044","unstructured":"Y. Deng, W. Zhang, Z. Chen, Q. Gu, Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves, arXiv preprint, arXiv: 2311.04205(2023)."},{"key":"10.1016\/j.patcog.2026.113639_bib0045","unstructured":"A. de Wynter, X. Wang, Q. Gu, S.-Q. Chen, On Meta-Prompting, arXiv preprint, arXiv: 2312.06562(2023)."},{"key":"10.1016\/j.patcog.2026.113639_bib0046","doi-asserted-by":"crossref","unstructured":"A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y. Yang, S. Gupta, B.P. Majumder, K. Hermann, S. Welleck, A. Yazdanbakhsh, P. Clark, Self-Refine: Iterative Refinement with Self-Feedback, in: A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, S. Levine (Eds.), Advances in Neural Information Processing Systems, 36, Curran Associates, Inc., 2023, pp. 46534\u201346594.","DOI":"10.52202\/075280-2019"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006047?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006047?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:38:31Z","timestamp":1784277511000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":46,"alternative-id":["S0031320326006047"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113639","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Thought graph traversal for test-time scaling in chest X-ray VLLMs","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113639","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113639"}}