{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:33:51Z","timestamp":1783715631853,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"IITP","award":["RS-2024-00456287"],"award-info":[{"award-number":["RS-2024-00456287"]}]},{"name":"IIDAI"},{"name":"PRISM"},{"name":"Intel"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731092","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"544-558","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1157-0127","authenticated-orcid":false,"given":"Hyungyo","family":"Kim","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1431-0067","authenticated-orcid":false,"given":"Nachuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1643-0554","authenticated-orcid":false,"given":"Qirong","family":"Xia","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2314-2734","authenticated-orcid":false,"given":"Jinghan","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8199-7671","authenticated-orcid":false,"given":"Amir","family":"Yazdanbakhsh","sequence":"additional","affiliation":[{"name":"Google DeepMind, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5634","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"2025. NVIDIA Nsight Systems. https:\/\/developer.nvidia.com\/nsight-systems."},{"key":"e_1_3_3_3_3_2","unstructured":"2025. NVIDIANVIDIA Nsight VSE Documentation. https:\/\/docs.nvidia.com\/nsight-visual-studio-edition\/2020.1\/nvtx\/index.html."},{"key":"e_1_3_3_3_4_2","unstructured":"Accessed in 2024. An open-source tool for controlling IPMI-enabled systems. https:\/\/github.com\/ipmitool\/ipmitool."},{"key":"e_1_3_3_3_5_2","unstructured":"Accessed in 2024. August 2024 Server Memory Prices. https:\/\/memory.net\/memory-prices\/."},{"key":"e_1_3_3_3_6_2","unstructured":"Accessed in 2024. HuggingFace Transformers Library. https:\/\/github.com\/huggingface\/transformers."},{"key":"e_1_3_3_3_7_2","unstructured":"Accessed in 2024. Intel\u00ae Architecture Instruction Set Extensions and Future Features. https:\/\/www.intel.com\/content\/www\/us\/en\/content-details\/774990\/intel-architecture-instruction-set-extensions-programming-reference.html."},{"key":"e_1_3_3_3_8_2","unstructured":"Accessed in 2024. Intel\u00ae Extension for PyTorch. https:\/\/github.com\/intel\/intel-extension-for-pytorch."},{"key":"e_1_3_3_3_9_2","unstructured":"Accessed in 2024. Technical Overview Of The 4th Gen Intel\u00ae Xeon\u00ae Scalable processor family. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/fourth-generation-xeon-scalable-family-overview.htmll."},{"key":"e_1_3_3_3_10_2","unstructured":"Accessed in 2024. The Intel\u00ae Xeon\u00ae 6 Processor Family. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/processors\/xeon\/xeon6-product-brief.html."},{"key":"e_1_3_3_3_11_2","unstructured":"Accessed in 2025. Memverge: CXL use case. https:\/\/memverge.com\/cxl-use-case-slash-memory-costs-and-expand-capacity\/."},{"key":"e_1_3_3_3_12_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Agarwal Rishabh","year":"2024","unstructured":"Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela\u00a0Ramos Garea, Matthieu Geist, and Olivier Bachem. 2024. On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_3_13_2","unstructured":"Amey Agrawal Nitin Kedia Jayashree Mohan Ashish Panwar Nipun Kwatra Bhargav Gulavani Ramachandran Ramjee and Alexey Tumanov. 2024. Vidur: A Large-Scale Simulation Framework For LLM Inference. Proceedings of Machine Learning and Systems 6 (2024) 351\u2013366."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"e_1_3_3_3_15_2","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung\u00a0Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew\u00a0M. Dai Thanumalayan\u00a0Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou Xuezhi Wang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. 2023. PaLM: Scaling Language Modeling with Pathways. Journal of Machine Learning Research 24 240 (2023) 1\u2013113."},{"key":"e_1_3_3_3_16_2","unstructured":"Tim Dettmers Mike Lewis Younes Belkada and Luke Zettlemoyer. 2022. GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale. Advances in Neural Information Processing Systems 35 (2022) 30318\u201330332."},{"key":"e_1_3_3_3_17_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_3_18_2","unstructured":"William Fedus Barret Zoph and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23 120 (2022) 1\u201339."},{"key":"e_1_3_3_3_19_2","first-page":"10323","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot. In Proceedings of the International Conference on Machine Learning (ICML). 10323\u201310337."},{"key":"e_1_3_3_3_20_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2023. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.17323 (2023)."},{"key":"e_1_3_3_3_21_2","unstructured":"Gemini Team. 2024. Gemini: A Family of Highly Capable Multimodal Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11805 (2024)."},{"key":"e_1_3_3_3_22_2","unstructured":"Yuxian Gu Li Dong Furu Wei and Minlie Huang. 2023. Knowledge distillation of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.08543 (2023)."},{"key":"e_1_3_3_3_23_2","unstructured":"Sylvain Gugger Lysandre Debut Thomas Wolf Philipp Schmid Zachary Mueller Sourab Mangrulkar Marc Sun and Benjamin Bossan. 2022. Accelerate: Training and inference at scale made simple efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate."},{"key":"e_1_3_3_3_24_2","unstructured":"Jiaao He and Jidong Zhai. 2024. FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.11421 (2024)."},{"key":"e_1_3_3_3_25_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de\u00a0Las Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark et\u00a0al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.15556 (2022)."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Cheng-Yu Hsieh Chun-Liang Li Chih-Kuan Yeh Hootan Nakhost Yasuhisa Fujii Alexander Ratner Ranjay Krishna Chen-Yu Lee and Tomas Pfister. 2023. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.02301 (2023).","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"e_1_3_3_3_27_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.08361 (2020)."},{"key":"e_1_3_3_3_28_2","unstructured":"Dan Kondratyuk Lijun Yu Xiuye Gu Jos\u00e9 Lezama Jonathan Huang Grant Schindler Rachel Hornung Vighnesh Birodkar Jimmy Yan Ming-Chang Chiu et\u00a0al. 2023. Videopoet: A large language model for zero-shot video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.14125 (2023)."},{"key":"e_1_3_3_3_29_2","unstructured":"Teven Le\u00a0Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ili\u0107 Daniel Hesslow Roman Castagn\u00e9 Alexandra\u00a0Sasha Luccioni Fran\u00e7ois Yvon Matthias Gall\u00e9 et\u00a0al. 2023. Bloom: A 176b-parameter open-access multilingual language model. (2023)."},{"key":"e_1_3_3_3_30_2","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et\u00a0al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.09110 (2022)."},{"key":"e_1_3_3_3_31_2","unstructured":"Hao Liu Matei Zaharia and Pieter Abbeel. 2023. Ring attention with blockwise transformers for near-infinite context. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.01889 (2023)."},{"key":"e_1_3_3_3_32_2","unstructured":"Xinyin Ma Gongfan Fang and Xinchao Wang. 2023. Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36 (2023) 21702\u201321720."},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Bonan Min Hayley Ross Elior Sulem Amir Pouran\u00a0Ben Veyseh Thien\u00a0Huu Nguyen Oscar Sainz Eneko Agirre Ilana Heintz and Dan Roth. 2023. Recent advances in natural language processing via large pre-trained language models: A survey. Comput. Surveys 56 2 (2023) 1\u201340.","DOI":"10.1145\/3605943"},{"key":"e_1_3_3_3_34_2","unstructured":"Avanika Narayan Ines Chami Laurel Orr Simran Arora and Christopher R\u00e9. 2022. Can foundation models wrangle your data? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.09911 (2022)."},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Shashi Narayan Shay\u00a0B Cohen and Mirella Lapata. 2018. Don\u2019t give me the details just the summary! topic-aware convolutional neural networks for extreme summarization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.08745 (2018).","DOI":"10.18653\/v1\/D18-1206"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_3_3_37_2","unstructured":"OpenAI(2023). 2024. GPT-4 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2024)."},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Pratyush Patel Esha Choukse Chaojie Zhang \u00cd\u00f1igo Goiri Aashaka Shah Saeed Maleki and Ricardo Bianchini. 2024. Splitwise: Efficient Generative LLM Inference Using Phase Splitting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.18677 (2024).","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.748"},{"key":"e_1_3_3_3_41_2","unstructured":"Bharadwaj Pudipeddi Maral Mesmakhosroshahi Jinwen Xi and Sujeeth Bharadwaj. 2020. Training Large Neural Networks with Constant Memory using a New Execution Algorithm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.05645 (2020)."},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"crossref","unstructured":"Debendra\u00a0Das Sharma. 2022. Compute Express Link (CXL): Enabling Heterogeneous Data-Centric Computing With Heterogeneous Memory Hierarchy. IEEE Micro 43 2 (2022) 99\u2013109.","DOI":"10.1109\/MM.2022.3228561"},{"key":"e_1_3_3_3_44_2","first-page":"31094","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. In Proceedings of the International Conference on Machine Learning (ICML). 31094\u201331116."},{"key":"e_1_3_3_3_45_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.08053 (2020)."},{"key":"e_1_3_3_3_46_2","unstructured":"Yixin Song Zeyu Mi Haotong Xie and Haibo Chen. 2023. Powerinfer: Fast large language model serving with a consumer-grade gpu. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.12456 (2023)."},{"key":"e_1_3_3_3_47_2","first-page":"2","volume-title":"Proceedings of the international conference on intelligent analysis","volume":"2","author":"Strohman Trevor","year":"2005","unstructured":"Trevor Strohman, Donald Metzler, Howard Turtle, and W\u00a0Bruce Croft. 2005. Indri: A language model-based search engine for complex queries. In Proceedings of the international conference on intelligent analysis, Vol.\u00a02. Washington, DC., 2\u20136."},{"key":"e_1_3_3_3_48_2","unstructured":"Mingjie Sun Zhuang Liu Anna Bair and J\u00a0Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.11695 (2024)."},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614256"},{"key":"e_1_3_3_3_50_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian\u00a0Canton Faerrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit\u00a0Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric\u00a0Michael Smith Ranjan Subramanian Xiaoqing\u00a0Ellen Tan Binh Tang Ross Taylor Adina Williams Jian\u00a0Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_3_51_2","first-page":"38087","volume-title":"International Conference on Machine Learning","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087\u201338099."},{"key":"e_1_3_3_3_52_2","unstructured":"Sungmin Yun Kwanhee Kyung Juhwan Cho Jaewan Choi Jongmin Kim Byeongho Kim Sukhan Lee Kyomin Sohn and Jung\u00a0Ho Ahn. 2024. Duplex: A Device for Large Language Models with Mixture of Experts Grouped Query Attention and Continuous Batching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.01141 (2024)."},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373017.3373028"},{"key":"e_1_3_3_3_54_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022)."},{"key":"e_1_3_3_3_55_2","volume-title":"Symposium on Operating Systems Design and Implementation","author":"Zhong Yuhong","year":"2024","unstructured":"Yuhong Zhong, Daniel\u00a0S Berger, Carl Waldspurger, Ishwar Agarwal, Rajat Agarwal, Frank Hady, Karthik Kumar, Mark\u00a0D Hill, Mosharaf Chowdhury, and Asaf Cidon. 2024. Managing Memory Tiers with CXL in Virtualized Environments. In Symposium on Operating Systems Design and Implementation."}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:05:18Z","timestamp":1750503918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731092"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":54,"alternative-id":["10.1145\/3695053.3731092","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731092","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}