{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T02:45:20Z","timestamp":1782787520037,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"name":"US Department of Energy","award":["DE-SC0012704"],"award-info":[{"award-number":["DE-SC0012704"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3815572.3815751","type":"proceedings-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:44:02Z","timestamp":1782495842000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CelloAI: Leveraging Large Language Models for HPC Software Development in High Energy Physics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6889-7702","authenticated-orcid":false,"given":"Mohammad","family":"Atif","sequence":"first","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9788-9218","authenticated-orcid":false,"given":"Kriti","family":"Chopra","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-408X","authenticated-orcid":false,"given":"Ozgur","family":"Kilic","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8293-0671","authenticated-orcid":false,"given":"Tianle","family":"Wang","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2758-8812","authenticated-orcid":false,"given":"Zhihua","family":"Dong","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9299-9020","authenticated-orcid":false,"given":"Charles","family":"Leggett","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory (LBNL), Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3010-0857","authenticated-orcid":false,"given":"Meifeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, Upton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1692-1678","authenticated-orcid":false,"given":"Paolo","family":"Calafiura","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory (LBNL), Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7832-0771","authenticated-orcid":false,"given":"Salman","family":"Habib","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Hugging Face."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. Marker."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. Tree-sitter. https:\/\/tree-sitter.github.io\/tree-sitter\/."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2024.1485344"},{"key":"e_1_3_2_1_5_1","unstructured":"Mohammad Atif Meghna Battacharya Paolo Calafiura Taylor Childers Mark Dewing Zhihua Dong Oliver Gutsche Salman Habib Kyle Knoepfel Matti Kortelainen et al. 2023. Evaluating portable parallelization strategies for heterogeneous architectures in high energy physics. arXiv preprint arXiv:2306.15869 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Charles Leggett, Meifeng Lin, et al.","author":"Atif Mohammad","year":"2026","unstructured":"Mohammad Atif, Meghna Bhattacharya, Mark Dewing, Zhihua Dong, Julien Esseiva, Oliver Gutsche, Matti Kortelainen, Ka Hei Martin Kwok, Charles Leggett, Meifeng Lin, et al. 2026. Evaluating Application Characteristics for GPU Portability Layer Selection. arXiv preprint arXiv:2601.17526 (2026)."},{"key":"e_1_3_2_1_7_1","unstructured":"Mohammad Atif Kriti Chopra Fang-Ying Tsai Ozgur O Kilic Tianle Wang Zhihua Dong Douglas Benjamin Charles Leggett Meifeng Lin Paolo Calafiura et al. 2026. CelloAI Benchmarks: Toward Repeatable Evaluation of AI Assistants. arXiv preprint arXiv:2603.01051 (2026)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ka Hei Martin Kwok, and Charles Leggett","author":"Atif Mohammad","year":"2025","unstructured":"Mohammad Atif, Pengfei Ding, Ka Hei Martin Kwok, and Charles Leggett. 2025. Packaging HEP Heterogeneous Mini-apps for Portable Benchmarking and Facility Evaluation on Modern HPCs. arXiv preprint arXiv:2505.08933 (2025)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1051\/epjconf\/202429511018"},{"key":"e_1_3_2_1_10_1","volume-title":"Heterogeneous reconstruction of tracks and primary vertices with the CMS pixel tracker. Frontiers in big Data 3","author":"Bocci Andrea","year":"2020","unstructured":"Andrea Bocci, Vincenzo Innocente, Matti Kortelainen, Felice Pantaleo, and Marco Rovere. 2020. Heterogeneous reconstruction of tracks and primary vertices with the CMS pixel tracker. Frontiers in big Data 3 (2020), 601728."},{"key":"e_1_3_2_1_11_1","volume-title":"Waqwoya Abebe, Hung Phan, Aishwarya Sarkar, Branden Butler, Niranjan Hasabnis, Gal Oren, Vy A. Vo, Juan Pablo Munoz, Theodore L. Willke, Tim Mattson, and Ali Jannesari.","author":"Chen Le","year":"2024","unstructured":"Le Chen, Nesreen K. Ahmed, Akash Dutta, Arijit Bhattacharjee, Sixing Yu, Quazi Ishtiaque Mahmud, Waqwoya Abebe, Hung Phan, Aishwarya Sarkar, Branden Butler, Niranjan Hasabnis, Gal Oren, Vy A. Vo, Juan Pablo Munoz, Theodore L. Willke, Tim Mattson, and Ali Jannesari. 2024. The Landscape and Challenges of HPC Research and LLMs. (2024). arXiv:2402.02018 http:\/\/arxiv.org\/abs\/2402.02018"},{"key":"e_1_3_2_1_12_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"ChromaDB. 2025. ChromaDB. https:\/\/www.trychroma.com\/."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41781-025-00133-8"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Albert Danial. 2021. cloc: v1.92. doi:10.5281\/zenodo.5760077","DOI":"10.5281\/zenodo.5760077"},{"key":"e_1_3_2_1_16_1","volume-title":"LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes. In 2024 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops)","author":"Dealing Matthew T","year":"2024","unstructured":"Matthew T Dealing, Yiheng Tao, Xingfu Wu, Zhiling Lan, and Valerie Taylor. 2024. LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes. In 2024 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops). IEEE, 136\u2013143."},{"key":"e_1_3_2_1_17_1","series-title":"Journal of Physics: Conference Series","volume-title":"Evaluation of Portable Programming Models to Accelerate LArTPC Detector Simulations","author":"Dong Zhihua","year":"2036","unstructured":"Zhihua Dong, Kyle Knoepfel, Meifeng Lin, Brett Viren, and Haiwang Yu. 2023. Evaluation of Portable Programming Models to Accelerate LArTPC Detector Simulations. In Journal of Physics: Conference Series, Vol. 2438. IOP Publishing, 012036."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605731.3605886"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8269"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3732775.3733586"},{"key":"e_1_3_2_1_21_1","unstructured":"IBM Granite Team. 2024. Granite 3.0 Language Models."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3697012"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767398"},{"key":"e_1_3_2_1_24_1","volume-title":"LLMs get lost in multi-turn conversation. arXiv preprint arXiv:2505.06120","author":"Laban Philippe","year":"2025","unstructured":"Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, and Jennifer Neville. 2025. LLMs get lost in multi-turn conversation. arXiv preprint arXiv:2505.06120 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Agustin Dal Lago, et al","author":"Li Yujia","year":"2022","unstructured":"Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, R\u00e9mi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. 2022. Competition-level code generation with alphacode. Science 378, 6624 (2022), 1092\u20131097."},{"key":"e_1_3_2_1_27_1","volume-title":"Portable Programming Model Exploration for LArTPC Simulation in a Heterogeneous Computing Environment: OpenMP vs. SYCL. arXiv preprint arXiv:2304.01841","author":"Lin Meifeng","year":"2023","unstructured":"Meifeng Lin, Zhihua Dong, Tianle Wang, Mohammad Atif, Meghna Battacharya, Kyle Knoepfel, Charles Leggett, Brett Viren, and Haiwang Yu. 2023. Portable Programming Model Exploration for LArTPC Simulation in a Heterogeneous Computing Environment: OpenMP vs. SYCL. arXiv preprint arXiv:2304.01841 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"DUNE: science and status. arXiv preprint arXiv:2502.08493","author":"L\u00f3pez Francisco Mart\u00ednez","year":"2025","unstructured":"Francisco Mart\u00ednez L\u00f3pez. 2025. DUNE: science and status. arXiv preprint arXiv:2502.08493 (2025)."},{"key":"e_1_3_2_1_29_1","volume-title":"Large language models: A survey. arXiv preprint arXiv:2402.06196","author":"Minaee Shervin","year":"2024","unstructured":"Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv preprint arXiv:2402.06196 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528929"},{"key":"e_1_3_2_1_31_1","volume-title":"Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. Code Llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning. arXiv preprint arXiv:2504.17192","author":"Seo Minju","year":"2025","unstructured":"Minju Seo, Jinheon Baek, Seongyun Lee, and Sung Ju Hwang. 2025. Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning. arXiv preprint arXiv:2504.17192 (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00010"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1039\/D3DD00112A"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_3_2_1_36_1","volume-title":"Financial report chunking for effective retrieval augmented generation. arXiv preprint arXiv:2402.05131","author":"Yepes Antonio Jimeno","year":"2024","unstructured":"Antonio Jimeno Yepes, Yao You, Jan Milczek, Sebastian Laverde, and Renyu Li. 2024. Financial report chunking for effective retrieval augmented generation. arXiv preprint arXiv:2402.05131 (2024)."}],"event":{"name":"PASC '26: Platform for Advanced Scientific Computing Conference","location":"Bern Switzerland","acronym":"PASC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3815572.3815751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T02:31:14Z","timestamp":1782786674000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3815572.3815751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,28]]},"references-count":36,"alternative-id":["10.1145\/3815572.3815751","10.1145\/3815572"],"URL":"https:\/\/doi.org\/10.1145\/3815572.3815751","relation":{},"subject":[],"published":{"date-parts":[[2026,6,28]]},"assertion":[{"value":"2026-06-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}