{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T20:37:39Z","timestamp":1778877459406,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302535, 62176223, 62371305"],"award-info":[{"award-number":["62302535, 62176223, 62371305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023A1515011639, 2024A1515030025"],"award-info":[{"award-number":["2023A1515011639, 2024A1515030025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754573","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"836-845","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5856-2490","authenticated-orcid":false,"given":"Yiran","family":"Meng","sequence":"first","affiliation":[{"name":"Artificial Intelligence Academy, Sun Yat-Sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4188-2155","authenticated-orcid":false,"given":"Junhong","family":"Ye","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3641-1429","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cardiff University, Cardiff, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6761-8767","authenticated-orcid":false,"given":"Guanghui","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-4176","authenticated-orcid":false,"given":"Xudong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0574-1663","authenticated-orcid":false,"given":"Baoquan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Dylan Campbell, Cristian Rodriguez-Opazo, Hongdong Li, and Stephen Gould.","author":"Ben-Shabat Yizhak","year":"2023","unstructured":"Yizhak Ben-Shabat, Xin Yu, Fatemeh Sadat Saleh, Dylan Campbell, Cristian Rodriguez-Opazo, Hongdong Li, and Stephen Gould. 2023. The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose. arXiv:2007.00394 [cs.CV] https:\/\/arxiv.org\/abs\/2007.00394"},{"key":"e_1_3_2_1_2_1","volume-title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding. arXiv preprint arXiv:2501.13106","author":"Cheng-Zhiqiang Hu Zesen","year":"2025","unstructured":"Zesen Cheng-Zhiqiang Hu Yuqian Yuan Guanzheng Chen Sicong Leng Yuming Jiang Hang Zhang Xin Li Peng Jin Wenqi Zhang Fan Wang Lidong Bing Deli Zhao Boqiang Zhang, Kehan Li. 2025. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding. arXiv preprint arXiv:2501.13106 (2025). https:\/\/arxiv.org\/abs\/2501.13106"},{"key":"e_1_3_2_1_3_1","unstructured":"Joao Carreira Eric Noland Chloe Hillier and Andrew Zisserman. 2022. A Short Note on the Kinetics-700 Human Action Dataset. arXiv:1907.06987 [cs.CV] https:\/\/arxiv.org\/abs\/1907.06987"},{"key":"e_1_3_2_1_4_1","volume-title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions. arXiv preprint arXiv:2406.04325","author":"Chen Lin","year":"2024","unstructured":"Lin Chen, Xilin Wei, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Bin Lin, Zhenyu Tang, Li Yuan, Yu Qiao, Dahua Lin, Feng Zhao, and Jiaqi Wang. 2024. ShareGPT4Video: Improving Video Understanding and Generation with Better Captions. arXiv preprint arXiv:2406.04325 (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Dingxin Cheng Mingda Li Jingyu Liu Yongxin Guo Bin Jiang Qingbin Liu Xi Chen and Bo Zhao. 2024b. Enhancing Long Video Understanding via Hierarchical Event-Based Memory. arXiv:2409.06299 [cs.CV] https:\/\/arxiv.org\/abs\/2409.06299"},{"key":"e_1_3_2_1_6_1","volume-title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. arXiv preprint arXiv:2406.07476","author":"Cheng Zesen","year":"2024","unstructured":"Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, and Lidong Bing. 2024a. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. arXiv preprint arXiv:2406.07476 (2024). https:\/\/arxiv.org\/abs\/2406.07476"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393452"},{"key":"e_1_3_2_1_9_1","unstructured":"Jiajun Fei Dian Li Zhidong Deng Zekun Wang Gang Liu and Hui Wang. 2024a. Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos. arXiv:2408.14023 [cs.CV] https:\/\/arxiv.org\/abs\/2408.14023"},{"key":"e_1_3_2_1_10_1","unstructured":"Chaoyou Fu Yuhan Dai Yondong Luo Lei Li Shuhuai Ren Renrui Zhang Zihan Wang Chenyu Zhou Yunhang Shen Mengdan Zhang et al. 2024. Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis. arXiv preprint arXiv:2405.21075 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_12_1","volume-title":"Video ReCap: Recursive Captioning of Hour-Long Videos. arXiv preprint arXiv:2402.13250","author":"Islam Md Mohaiminul","year":"2024","unstructured":"Md Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, and Gedas Bertasius. 2024. Video ReCap: Recursive Captioning of Hour-Long Videos. arXiv preprint arXiv:2402.13250 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering. arXiv preprint arXiv:2503.09590","author":"Islam Md Mohaiminul","year":"2025","unstructured":"Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Gedas Bertasius, and Lorenzo Torresani. 2025. BIMBA: Selective-Scan Compression for Long-Range Video Question Answering. arXiv preprint arXiv:2503.09590 (2025)."},{"key":"e_1_3_2_1_14_1","first-page":"2025","article-title":"CrewAI: Framework for Building Multi-Agent Systems. https:\/\/github.com\/joaomdmoura\/crewai","author":"Labs Cognition","year":"2024","unstructured":"Cognition Labs. 2024. CrewAI: Framework for Building Multi-Agent Systems. https:\/\/github.com\/joaomdmoura\/crewai. Accessed: 2025-04.","journal-title":"Accessed"},{"key":"e_1_3_2_1_15_1","volume-title":"LLaVA-OneVision: Easy Visual Task Transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024d. LLaVA-OneVision: Easy Visual Task Transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612838"},{"key":"e_1_3_2_1_18_1","unstructured":"Xinhao Li Yi Wang Jiashuo Yu Xiangyu Zeng Yuhan Zhu Haian Huang Jianfei Gao Kunchang Li Yinan He Chenting Wang et al. 2024c. VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling. arXiv preprint arXiv:2501.00574 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning. ArXiv","author":"Li Yunxin","year":"2024","unstructured":"Yunxin Li, Xinyu Chen, Baotian Hu, Longyue Wang, Haoyuan Shi, and Min Zhang. 2024a. VideoVista: A Versatile Benchmark for Video Understanding and Reasoning. ArXiv, Vol. abs\/2406.11303 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270559556"},{"key":"e_1_3_2_1_20_1","volume-title":"Snoek","author":"Liu Huabin","year":"2025","unstructured":"Huabin Liu, Filip Ilievski, and Cees G. M. Snoek. 2025a. Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning. arXiv:2501.05069 [cs.CV] https:\/\/arxiv.org\/abs\/2501.05069"},{"key":"e_1_3_2_1_21_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024a. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_6"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3571119"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Yi Liu Limin Wang Yali Wang Xiao Ma and Yu Qiao. 2022. FineAction: A Fine-Grained Video Dataset for Temporal Action Localization. arXiv:2105.11107 [cs.CV] https:\/\/arxiv.org\/abs\/2105.11107","DOI":"10.1109\/TIP.2022.3217368"},{"key":"e_1_3_2_1_25_1","unstructured":"Ziyu Ma Chenhui Gou Hengcan Shi Bin Sun Shutao Li Hamid Rezatofighi and Jianfei Cai. 2024. DrVideo: Document Retrieval Based Long Video Understanding. arXiv:2406.12846 [cs.CV] https:\/\/arxiv.org\/abs\/2406.12846"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"e_1_3_2_1_27_1","volume-title":"Moeslund","author":"Madan Neelu","year":"2024","unstructured":"Neelu Madan, Andreas Moegelmose, Rajat Modi, Yogesh S. Rawat, and Thomas B. Moeslund. 2024. Foundation Models for Video Understanding: A Survey. arXiv:2405.03770 [cs.CV] https:\/\/arxiv.org\/abs\/2405.03770"},{"key":"e_1_3_2_1_28_1","first-page":"46212","article-title":"Egoschema: A diagnostic benchmark for very long-form video language understanding","volume":"36","author":"Mangalam Karttikeya","year":"2023","unstructured":"Karttikeya Mangalam, Raiymbek Akshulakov, and Jitendra Malik. 2023. Egoschema: A diagnostic benchmark for very long-form video language understanding. Advances in Neural Information Processing Systems, Vol. 36 (2023), 46212-46244.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models. arXiv preprint arXiv:2311.16103","author":"Ning Munan","year":"2023","unstructured":"Munan Ning, Bin Zhu, Yujia Xie, Bin Lin, Jiaxi Cui, Lu Yuan, Dongdong Chen, and Li Yuan. 2023. Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models. arXiv preprint arXiv:2311.16103 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Ryoo","author":"Park Jong Sung","year":"2024","unstructured":"Jong Sung Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Wonjeong Ryoo, Donghyun Kim, and Michael S. Ryoo. 2024. Too Many Frames, not all Useful: Efficient Strategies for Long-Form Video QA. ArXiv, Vol. abs\/2406.09396 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270440923"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 2020 International Conference on Pattern Recognition. Online.","author":"Qasim T.","unstructured":"T. Qasim, R. B. Fisher, and N. Bhatti. 2021. Ground-truthing Large Human Behavior Monitoring Datasets. In Proceedings of the 2020 International Conference on Pattern Recognition. Online."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Kate Sanders Nathaniel Weir and Benjamin Van Durme. 2024. TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning. arXiv:2402.19467 [cs.CL] https:\/\/arxiv.org\/abs\/2402.19467","DOI":"10.18653\/v1\/2024.emnlp-main.1059"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Gunnar A. Sigurdsson G\u00fcl Varol Xiaolong Wang Ali Farhadi Ivan Laptev and Abhinav Gupta. 2016. Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding. arXiv:1604.01753 [cs.CV] https:\/\/arxiv.org\/abs\/1604.01753","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_1_35_1","volume-title":"Chatvideo: A tracklet-centric multimodal and versatile video understanding system. arXiv preprint arXiv:2304.14407","author":"Wang Junke","year":"2023","unstructured":"Junke Wang, Dongdong Chen, Chong Luo, Xiyang Dai, Lu Yuan, Zuxuan Wu, and Yu-Gang Jiang. 2023a. Chatvideo: A tracklet-centric multimodal and versatile video understanding system. arXiv preprint arXiv:2304.14407 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation. In The Twelfth International Conference on Learning Representations.","author":"Wang Yi","year":"2023","unstructured":"Yi Wang, Yinan He, Yizhuo Li, Kunchang Li, Jiashuo Yu, Xin Ma, Xinhao Li, Guo Chen, Xinyuan Chen, Yaohui Wang, et al., 2023b. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_37_1","volume-title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning. arXiv preprint arXiv:2212.03191","author":"Wang Yi","year":"2022","unstructured":"Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang, Limin Wang, and Yu Qiao. 2022. InternVideo: General Video Foundation Models via Generative and Discriminative Learning. arXiv preprint arXiv:2212.03191 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Empowering Video MLLMs with Long and Rich Context Modeling. arXiv preprint arXiv:2501.12386","author":"Wang Yi","year":"2025","unstructured":"Yi Wang, Xinhao Li, Ziang Yan, Yinan He, Jiashuo Yu, Xiangyu Zeng, Chenting Wang, Changlian Ma, Haian Huang, Jianfei Gao, Min Dou, Kai Chen, Wenhai Wang, Yu Qiao, Yali Wang, and Limin Wang. 2025. InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling. arXiv preprint arXiv:2501.12386 (2025)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01181"},{"key":"e_1_3_2_1_40_1","unstructured":"Haoning Wu Dongxu Li Bei Chen and Junnan Li. 2024. LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding. arXiv:2407.15754 [cs.CV] https:\/\/arxiv.org\/abs\/2407.15754"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"e_1_3_2_1_42_1","unstructured":"Tianyi Xiong Xiyao Wang Dong Guo Qinghao Ye Haoqi Fan Quanquan Gu Heng Huang and Chunyuan Li. 2024. LLaVA-Critic: Learning to Evaluate Multimodal Models. (2024). arXiv:2410.02712 [cs.CV] https:\/\/arxiv.org\/abs\/2410.02712"},{"key":"e_1_3_2_1_43_1","unstructured":"Jiabo Ye Haiyang Xu Haowei Liu Anwen Hu Ming Yan Qi Qian Ji Zhang Fei Huang and Jingren Zhou. 2024. mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models. arXiv:2408.04840 [cs.CV] https:\/\/arxiv.org\/abs\/2408.04840"},{"key":"e_1_3_2_1_44_1","unstructured":"Shoubin Yu Jaemin Cho Prateek Yadav and Mohit Bansal. 2023. Self-Chained Image-Language Model for Video Localization and Question Answering. arXiv:2305.06988 [cs.CV] https:\/\/arxiv.org\/abs\/2305.06988"},{"key":"e_1_3_2_1_45_1","volume-title":"Ziyang Wang, Shoubin Yu, Mohit Bansal, and Gedas Bertasius.","author":"Zhang Ce","year":"2024","unstructured":"Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, and Gedas Bertasius. 2024b. A Simple LLM Framework for Long-Range Video Question-Answering. arXiv:2312.17235 [cs.CV] https:\/\/arxiv.org\/abs\/2312.17235"},{"key":"e_1_3_2_1_46_1","volume-title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023. Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding. arXiv preprint arXiv:2306.02858 (2023). https:\/\/arxiv.org\/abs\/2306.02858"},{"key":"e_1_3_2_1_47_1","volume-title":"Yong jae Lee, Liangke Gui, Di Fu, Jiashi Feng, Ziwei Liu, and Chunyuan Li.","author":"Zhang Yuanhan","year":"2024","unstructured":"Yuanhan Zhang, Bo Li, haotian Liu, Yong jae Lee, Liangke Gui, Di Fu, Jiashi Feng, Ziwei Liu, and Chunyuan Li. 2024a. LLaVA-NeXT: A Strong Zero-shot Video Understanding Model. https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"e_1_3_2_1_48_1","volume-title":"HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization. arXiv preprint arXiv:1712.09374","author":"Zhao Hang","year":"2019","unstructured":"Hang Zhao, Zhicheng Yan, Lorenzo Torresani, and Antonio Torralba. 2019. HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization. arXiv preprint arXiv:1712.09374 (2019)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3223955"},{"key":"e_1_3_2_1_50_1","volume-title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos. arxiv","author":"Stengel-Eskin Jaehong Elias","year":"2024","unstructured":"Elias Stengel-Eskin Jaehong Yoon Feng Cheng Gedas Bertasius Mohit Bansal Ziyang Wang, Shoubin Yu. 2024. VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos. arxiv (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:12:04Z","timestamp":1765339924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754573"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3754573","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754573","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}