{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T08:13:59Z","timestamp":1774167239257,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":99,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737403","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:52:41Z","timestamp":1754254361000},"page":"5754-5765","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-8630","authenticated-orcid":false,"given":"Chuan","family":"Qin","sequence":"first","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-9201","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1496-2402","authenticated-orcid":false,"given":"Chengrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9554-9540","authenticated-orcid":false,"given":"Pengmin","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6180-4524","authenticated-orcid":false,"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2396-0306","authenticated-orcid":false,"given":"Yihang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7622-4989","authenticated-orcid":false,"given":"Jingyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5294-5776","authenticated-orcid":false,"given":"Meng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8647-3711","authenticated-orcid":false,"given":"Xiangchao","family":"Dong","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3520-0129","authenticated-orcid":false,"given":"Qingqing","family":"Long","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5146-8235","authenticated-orcid":false,"given":"Boya","family":"Pan","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5599-0625","authenticated-orcid":false,"given":"Han","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9043-6403","authenticated-orcid":false,"given":"Chengzan","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, BeiJing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2144-1131","authenticated-orcid":false,"given":"Yuanchun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4570-643X","authenticated-orcid":false,"given":"Hengshu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Amini Aida","year":"2019","unstructured":"Aida Amini, Saadia Gabriel, Shanchuan Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019. MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2357-2367."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI51800.2020.00249"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.468"},{"key":"e_1_3_2_2_4_1","unstructured":"BIG bench authors. 2023. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. Transactions on Machine Learning Research(2023). https:\/\/openreview.net\/forum?id=uyTL5Bvosj"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","unstructured":"Sid Black Leo Gao Phil Wang Connor Leahy and Stella Biderman. 2021. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow . https:\/\/doi.org\/10.5281\/zenodo.5297715","DOI":"10.5281\/zenodo.5297715"},{"key":"e_1_3_2_2_6_1","first-page":"13263","article-title":"The privacy onion effect: Memorization is relative","volume":"35","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Matthew Jagielski, Chiyuan Zhang, Nicolas Papernot, Andreas Terzis, and Florian Tramer. 2022. The privacy onion effect: Memorization is relative. Advances in Neural Information Processing Systems, Vol. 35 (2022), 13263-13276.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_2_8_1","volume-title":"Paul WC Wong, Jennifer J Xu, Paul SF Yip, and Hsinchun Chen.","author":"Chau Michael","year":"2020","unstructured":"Michael Chau, Tim MH Li, Paul WC Wong, Jennifer J Xu, Paul SF Yip, and Hsinchun Chen. 2020. Finding People with Emotional Distress in Online Social Media: A Design Combining Machine Learning and Rule-Based Classification. MIS quarterly, Vol. 44, 2 (2020)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.390"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.489"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Wei Cheng Dan Li Xiangzheng Deng Jinming Feng Yongli Wang Jing Peng Jing Tian Wei Qi Zhu Liu Xinqi Zheng Demin Zhou Sijian Jiang Haipeng Zhao and Xiaoyu Wang. 2021. Global Monthly Distributions of Atmospheric CO2 Concentrations Under the Historical and Future Scenarios. https:\/\/doi.org\/10.5281\/zenodo.5021361","DOI":"10.5281\/zenodo.5021361"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Timothy Clark Harry Caufield Jillian A. Mohan Sadnan Al Manir Edilberto Amorim James Eddy Nayoon Gim Brian Gow Wesley Goar Melissa Haendel Jan N. Hansen Nomi Harris Henning Hermjakob Marcin Joachimiak Gianna Jordan In-Hee Lee Shannon K. McWeeney Camille Nebeker Milen Nikolov Jamie Shaffer Nathan Sheffield Gloria Sheynkman James Stevenson Jake Y. Chen Chris Mungall Alex Wagner Sek Won Kong Satrajit S. Ghosh Bhavesh Patel Andrew Williams and Monica C. Munoz-Torres. 2024. AI-readiness for Biomedical Data: Bridge2AI Recommendations. bioRxiv(2024).","DOI":"10.1101\/2024.10.23.619844"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Daniel JB Clarke Lily Wang Alex Jones Megan L Wojciechowicz Denis Torre Kathleen M Jagodnik Sherry L Jenkins Peter McQuilton Zachary Flamholz Moshe C Silverstein et al. 2019. FAIRshake: Toolkit to evaluate the FAIRness of research digital resources. Cell systems Vol. 9 5 (2019) 417-421.","DOI":"10.1016\/j.cels.2019.09.011"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.19983722.v1"},{"key":"e_1_3_2_2_15_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168(2021)."},{"key":"e_1_3_2_2_16_1","unstructured":"Computer Network Information Center of the Chinese Academy of Sciences. 2024. Scientific Data Trusted Certification. https:\/\/datatrusted.cn\/service\/dataFair"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.14"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618257.3624801"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.47"},{"key":"e_1_3_2_2_20_1","volume-title":"Mathematical capabilities of chatgpt. Advances in neural information processing systems","author":"Frieder Simon","year":"2024","unstructured":"Simon Frieder, Luca Pinchetti, Ryan-Rhys Griffiths, Tommaso Salvatori, Thomas Lukasiewicz, Philipp Petersen, and Julius Berner. 2024. Mathematical capabilities of chatgpt. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657961"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29767"},{"key":"e_1_3_2_2_23_1","first-page":"59662","article-title":"What can large language models do in chemistry? a comprehensive benchmark on eight tasks","volume":"36","author":"Guo Taicheng","year":"2023","unstructured":"Taicheng Guo, Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh Chawla, Olaf Wiest, Xiangliang Zhang, et al., 2023. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. Advances in Neural Information Processing Systems, Vol. 36 (2023), 59662-59688.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_24_1","volume-title":"The role of ChatGPT in data science: how ai-assisted conversational interfaces are revolutionizing the field. Big data and cognitive computing","author":"Hassani Hossein","year":"2023","unstructured":"Hossein Hassani and Emmanuel Sirmal Silva. 2023. The role of ChatGPT in data science: how ai-assisted conversational interfaces are revolutionizing the field. Big data and cognitive computing, Vol. 7, 2 (2023), 62."},{"key":"e_1_3_2_2_25_1","volume-title":"Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Kaveen Hiniduma Suren Byna and Jean Luca Bez. 2024a. Data Readiness for AI: A 360-Degree Survey. arXiv:2404.05779 [cs.LG] https:\/\/arxiv.org\/abs\/2404.05779","DOI":"10.1145\/3722214"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676288.3676296"},{"key":"e_1_3_2_2_28_1","first-page":"1","article-title":"The dataset nutrition label","volume":"12","author":"Holland Sarah","year":"2020","unstructured":"Sarah Holland, Ahmed Hosny, Sarah Newman, Joshua Joseph, and Kasia Chmielinski. 2020. The dataset nutrition label. Data Protection and Privacy, Vol. 12, 12 (2020), 1.","journal-title":"Data Protection and Privacy"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.05.010"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","unstructured":"Bin Hu. 2022. A Multi-modal Open Dataset for Mental-Disorder Analysis. https:\/\/doi.org\/10.5255\/UKDA-SN-854301","DOI":"10.5255\/UKDA-SN-854301"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","unstructured":"Guojie Hu Ren Li Tonghua Wu Yao Xiao Yongping Qiao Zangping Xing Yonghua Zhao Jianzong Shi Qiangqiang Pang Lingxiao Wang Changwei Xie Chong Wang Guodong Cheng Zhe Sun Defu Zou Lin Zhao Guangyue Liu Erji Du and Xiaodong Wu. 2021. A Synthesis Dataset of Permafrost for the Qinghai-Xizang (Tibet) Plateau China (2002-2018). https:\/\/doi.org\/10.11888\/Geocry.tpdc.271107","DOI":"10.11888\/Geocry.tpdc.271107"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-93877-7"},{"key":"e_1_3_2_2_33_1","first-page":"62991","article-title":"C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models","volume":"36","author":"Huang Yuzhen","year":"2023","unstructured":"Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Yao Fu, et al., 2023. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 62991-63010.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02298-6"},{"key":"e_1_3_2_2_35_1","unstructured":"Yang Ji Ying Sun Yuting Zhang Zhigaoyuan Wang Yuanxin Zhuang Zheng Gong Dazhong Shen Chuan Qin Hengshu Zhu and Hui Xiong. 2025. A Comprehensive Survey on Self-Interpretable Neural Networks. arXiv preprint arXiv:2501.15638(2025)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5562-2_18"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.19688169.v1"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin \u017d\u00eddek Anna Potapenko et al. 2021. Highly accurate protein structure prediction with AlphaFold. nature Vol. 596 7873 (2021) 583-589.","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","unstructured":"Farah Khan Rixin Wang Melissa Skanderson Cynthia Brandt Samah Fodeh and Julie Womack. 2023. A Roadmap to Artificial Intelligence (AI): Methods for Designing and Building AI ready Data for Womens Health Studies. https:\/\/doi.org\/10.1101\/2023.05.25.23290399","DOI":"10.1101\/2023.05.25.23290399"},{"key":"e_1_3_2_2_41_1","first-page":"51080","article-title":"Geo-bench: Toward foundation models for earth monitoring","volume":"36","author":"Lacoste Alexandre","year":"2023","unstructured":"Alexandre Lacoste, Nils Lehmann, Pau Rodriguez, Evan Sherwin, Hannah Kerner, Bj\u00f6rn L\u00fctjens, Jeremy Irvin, David Dao, Hamed Alemohammad, Alexandre Drouin, et al., 2023. Geo-bench: Toward foundation models for earth monitoring. Advances in Neural Information Processing Systems, Vol. 36 (2023), 51080-51093.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"David M Levine Rudraksh Tuwani Benjamin Kompa Amita Varma Samuel G Finlayson Ateev Mehrotra and Andrew Beam. 2023. The diagnostic and triage accuracy of the GPT-3 artificial intelligence model. MedRxiv(2023).","DOI":"10.1101\/2023.01.30.23285067"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00009"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","unstructured":"Xin Li Youhua Ran Masahiro Hori Juha Aalto Olli Karjalainen Jan Hjort Miska Luoto Jaroslav Obu Guodong Cheng Jinxing Che Huijun Jin Qihao Yu and Xiaoli Chang. 2021a. High-resolution Datasets of Permafrost Thermal State and Hydrothermal Zonation in the Northern Hemisphere. https:\/\/doi.org\/10.11888\/Geocry.tpdc.271190","DOI":"10.11888\/Geocry.tpdc.271190"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","unstructured":"Yi Li Jihong Yu and Chuting Zheng. 2019. Database of Open-Framework Aluminophosphate Structures. https:\/\/doi.org\/10.6084\/m9.figshare.7822574.v6","DOI":"10.6084\/m9.figshare.7822574.v6"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","unstructured":"Jiechun Liang Shuqian Ye Tianshu Dai Ziyue Zha Yuechen Gao and Xi Zhu. 2020. QM-symex-database. https:\/\/doi.org\/10.6084\/m9.figshare.12815276.v3","DOI":"10.6084\/m9.figshare.12815276.v3"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"J. Liao Z. Yu Y. Chen C. Zou H. Zhang J. Cheng D. Liu T. Li Q. Zhang and Z. Mo. 2019. Single-cell RNA Sequencing of Human Kidney. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE131685","DOI":"10.1038\/s41597-019-0351-8"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","unstructured":"Chuanyu Liu Mingyue Wang Xiaoyu Wei and Longqi Liu. 2018. An ATAC-seq Atlas of Chromatin Accessibility in Mouse Tissues. https:\/\/doi.org\/10.26036\/CNP0000198","DOI":"10.26036\/CNP0000198"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.411"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","unstructured":"Liangyun Liu Xiao Zhang Xidong Chen Yuan Gao and Jun Mi. 2020. GLC_FCS30: Global Land-Cover Product with Fine Classification System at 30 m Using Time-Series Landsat Imagery. https:\/\/doi.org\/10.5281\/zenodo.3986872","DOI":"10.5281\/zenodo.3986872"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","unstructured":"Haijin Lu Nan Zou Ryan Jacobs Ben Afflerbach Xiao-Gang Lu and Dane Morgan. 2022b. Error assessment and optimal cross-validation approaches in machine learning applied to impurity diffusion. https:\/\/doi.org\/10.18126\/uppe-p8p1","DOI":"10.18126\/uppe-p8p1"},{"key":"e_1_3_2_2_54_1","volume-title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KUNzEQMWU7","author":"Lu Pan","year":"2024","unstructured":"Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2024. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KUNzEQMWU7"},{"key":"e_1_3_2_2_55_1","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022a. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, Vol. 35 (2022), 2507-2521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1177\/16094069231211248"},{"key":"e_1_3_2_2_57_1","unstructured":"The Chinese University of Hong Kong. 2021. miRTarBase: The Experimentally Validated microRNA-target Interactions Database. https:\/\/mirtarbase.cuhk.edu.cn\/ miRTarBase\/miRTarBase_2025\/php\/index.php"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.11888\/Geogra.tpdc.271702"},{"key":"e_1_3_2_2_59_1","volume-title":"Conference on health, inference, and learning. PMLR, 248-260","author":"Pal Ankit","year":"2022","unstructured":"Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Conference on health, inference, and learning. PMLR, 248-260."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmat.2023.08.007"},{"key":"e_1_3_2_2_61_1","volume-title":"COTR: Efficient Job Task Recognition for Occupational Information Systems with Class-Incremental Learning. ACM Transactions on Management Information Systems(2025).","author":"Qin Chuan","year":"2025","unstructured":"Chuan Qin, Chuyu Fang, Kaichun Yao, Xi Chen, Fuzhen Zhuang, and Hengshu Zhu. 2025. COTR: Efficient Job Task Recognition for Occupational Information Systems with Class-Incremental Learning. ACM Transactions on Management Information Systems(2025)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","unstructured":"Jingyu Qu and Qiang Zhu. 2020. High dielectric ternary oxides from crystal structure prediction and high-throughput screening. https:\/\/doi.org\/10.6084\/m9.figshare.10482707.v2","DOI":"10.6084\/m9.figshare.10482707.v2"},{"key":"e_1_3_2_2_63_1","volume-title":"First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=Ti67584b98","author":"Rein David","unstructured":"David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2024. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=Ti67584b98"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"e_1_3_2_2_65_1","unstructured":"scihorizon. 2025. SciHorizon Platform Officially Launched Establishing a New Evaluation System for AI4Science!"},{"key":"e_1_3_2_2_66_1","first-page":"912","article-title":"A machine learning-enhanced robust P-phase picker for real-time seismic monitoring","volume":"51","author":"Shen Dazhong","year":"2021","unstructured":"Dazhong Shen, Qi Zhang, Tong Xu, Hengshu Zhu, Wenjia Zhao, Zikai Yin, Peilun Zhou, Lihua Fang, Enhong Chen, and Hui Xiong. 2021. A machine learning-enhanced robust P-phase picker for real-time seismic monitoring. SCIENCE CHINA: Information Sciences, Vol. 51, 5 (2021), 912.","journal-title":"SCIENCE CHINA: Information Sciences"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.3390\/info10040137"},{"key":"e_1_3_2_2_68_1","first-page":"172","volume-title":"Nature","volume":"620","author":"Singhal Karan","year":"2023","unstructured":"Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al., 2023. Large language models encode clinical knowledge. Nature, Vol. 620, 7972 (2023), 172-180."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29872"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.37281"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709225"},{"key":"e_1_3_2_2_72_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971(2023).","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971(2023)."},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.128"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","unstructured":"Ludi Wang. 2023. A corpus of CO2 Electrocatalytic Reduction Process extracted from the scientific literature. https:\/\/doi.org\/10.57760\/sciencedb.07106","DOI":"10.57760\/sciencedb.07106"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.343"},{"key":"e_1_3_2_2_76_1","volume-title":"Scibench: Evaluating college-level scientific problem-solving abilities of large language models. arXiv preprint arXiv:2307.10635(2023).","author":"Wang Xiaoxuan","year":"2023","unstructured":"Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R Loomba, Shichang Zhang, Yizhou Sun, and Wei Wang. 2023. Scibench: Evaluating college-level scientific problem-solving abilities of large language models. arXiv preprint arXiv:2307.10635(2023)."},{"key":"e_1_3_2_2_77_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning.","author":"Wang Zhigaoyuan","year":"2025","unstructured":"Zhigaoyuan Wang, Ying Sun, and Hengshu Zhu. 2025. Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach. In Proceedings of the 42nd International Conference on Machine Learning."},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","unstructured":"Zhongfeng Xu Ying Han Chi-Yung Tam Zong-Liang Yang and Congbin Fu. 2024. Bias-corrected CMIP6 Global Dataset for Dynamical Downscaling of the Earth's Historical and Future Climate (1979-2100). https:\/\/doi.org\/10.11922\/sciencedb.00487","DOI":"10.11922\/sciencedb.00487"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","unstructured":"Fapeng Yan Wei Shangguan Jing Zhang and Bifeng Hu. 2019. Depth-to-Bedrock Map of China at a Spatial Resolution of 100 Meters. https:\/\/doi.org\/10.6084\/m9.figshare.c.4714514.v1","DOI":"10.6084\/m9.figshare.c.4714514.v1"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","unstructured":"Cheng Yang Chuan Ren Yifan Jia Guoqiang Wang Meng Li and Weiping Lu. 2022. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness. https:\/\/doi.org\/10.18126\/rska-ta67","DOI":"10.18126\/rska-ta67"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4417810"},{"key":"e_1_3_2_2_83_1","unstructured":"Jiancheng Yang Rui Shi Donglai Wei Zequan Liu Lin Zhao Bilian Ke Hanspeter Pfister and Bingbing Ni. 2021. MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification."},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","unstructured":"Mingjia Yao Yuxiang Wang Xin Li Ye Sheng Haiyang Huo Lili Xi Jiong Yang and Wenqing Zhang. 2021. Materials informatics platform with three dimensional structures (MIP-3d). https:\/\/doi.org\/10.6084\/m9.figshare.13655276.v7","DOI":"10.6084\/m9.figshare.13655276.v7"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","unstructured":"CHEN Yingying YANG Kun TANG Wenjun LI Xin LU Hui HE Jie and QIN Jun. 2015. China meteorological forcing dataset (1979-2018). https:\/\/doi.org\/10.11888\/AtmosphericPhysics.tpe.249369.file","DOI":"10.11888\/AtmosphericPhysics.tpe.249369.file"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","unstructured":"Jin Yuan Lijie Deng Xiaoying Tang Haixiang Huang and Yuqing Deng. 2020. The SUSTech-SYSU Dataset for Automatically Segmenting and Classifying Corneal Ulcers. https:\/\/doi.org\/10.6084\/m9.figshare.c.4526675.v1","DOI":"10.6084\/m9.figshare.c.4526675.v1"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","unstructured":"Ziqi Yuwei Cheng Fangyi Liang Zeyi Jia Yunzhuo Chen Dongliang Zhang Jinyi Jin Xue Guo Xi He Jie Zhang Lei Zhao Xiaotong and Sun Yanjing. 2024. A materials terminology knowledge graph automatically constructed from text corpus. https:\/\/doi.org\/10.5281\/zenodo.11315713","DOI":"10.5281\/zenodo.11315713"},{"key":"e_1_3_2_2_88_1","unstructured":"Dan Zhang Ziniu Hu Sining Zhoubian Zhengxiao Du Kaiyu Yang Zihan Wang Yisong Yue Yuxiao Dong and Jie Tang. 2024a. SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning. arXiv:2401.07950 [cs.CL]"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"crossref","unstructured":"Guanshi Zhang Duo Zheng Yuqin Tian and Sen Li. 2019b. A Dataset of Distribution and Diversity of Ticks in China.","DOI":"10.1038\/s41597-019-0115-5"},{"key":"e_1_3_2_2_90_1","first-page":"886","article-title":"Aftershock detection with multi-scale description based neural network. In 2019 ieee international conference on data mining (icdm)","author":"Zhang Qi","year":"2019","unstructured":"Qi Zhang, Tong Xu, Hengshu Zhu, Lifu Zhang, Hui Xiong, Enhong Chen, and Qi Liu. 2019a. Aftershock detection with multi-scale description based neural network. In 2019 ieee international conference on data mining (icdm). IEEE, 886-895.","journal-title":"IEEE"},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453842"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"publisher","unstructured":"Yijia Zhang Qingyu Chen Zhihao Yang Hongfei Lin and Zhiyong Lu. 2018. BioWordVec: Improving Biomedical Word Embeddings with Subword Information and MeSH Ontology. https:\/\/doi.org\/10.6084\/m9.figshare.6882647.v2","DOI":"10.6084\/m9.figshare.6882647.v2"},{"key":"e_1_3_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103808"},{"key":"e_1_3_2_2_94_1","doi-asserted-by":"publisher","unstructured":"Zian Zhang and Zhiping Xu. 2023. Fatigue Database of Additively Manufactured Alloys. https:\/\/doi.org\/10.6084\/m9.figshare.22337629.v2","DOI":"10.6084\/m9.figshare.22337629.v2"},{"key":"e_1_3_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.16602224.v1"},{"key":"e_1_3_2_2_96_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhao Yiran","year":"2024","unstructured":"Yiran Zhao, Jinghan Zhang, I Chern, Siyang Gao, Pengfei Liu, Junxian He, et al., 2024. Felm: Benchmarking factuality evaluation of large language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_97_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"e_1_3_2_2_98_1","volume-title":"Rapid Learning of earthquake felt Area and intensity Distribution with Real-time Search engine Queries. Scientific reports","author":"Zhu Hengshu","year":"2020","unstructured":"Hengshu Zhu, Ying Sun, Wenjia Zhao, Fuzhen Zhuang, Baoshan Wang, and Hui Xiong. 2020. Rapid Learning of earthquake felt Area and intensity Distribution with Real-time Search engine Queries. Scientific reports, Vol. 10, 1 (2020), 5437."},{"key":"e_1_3_2_2_99_1","doi-asserted-by":"publisher","unstructured":"Yifei Zhu. 2024. QCDGE database: Quantum Chemistry Database with Ground- and Excited-State Properties. https:\/\/doi.org\/10.6084\/m9.figshare.c.7259125.v1","DOI":"10.6084\/m9.figshare.c.7259125.v1"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:26:56Z","timestamp":1755354416000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":99,"alternative-id":["10.1145\/3711896.3737403","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737403","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}