{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T08:28:09Z","timestamp":1786523289439,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767406","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"534-539","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of Test-Time Compute Constraints on Safety and Skill Large Reasoning Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-8788","authenticated-orcid":false,"given":"Adarsha","family":"Balaji","sequence":"first","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7188-6756","authenticated-orcid":false,"given":"Le","family":"Chen","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5532-3048","authenticated-orcid":false,"given":"Rajeev","family":"Thakur","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7890-3934","authenticated-orcid":false,"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0437-8655","authenticated-orcid":false,"given":"Sandeep","family":"Madireddy","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_2","unstructured":"Pranjal Aggarwal and Sean Welleck. 2025. L1: Controlling how long a reasoning model thinks with reinforcement learning 2025. URL https:\/\/arxiv. org\/abs\/2503.04697 (2025)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_3_2_5_2","unstructured":"Yelysei Bondarenko Riccardo Del\u00a0Chiaro and Markus Nagel. 2024. Low-rank quantization-aware training for llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.06385 (2024)."},{"key":"e_1_3_3_2_6_2","unstructured":"Le Chen Nesreen\u00a0K Ahmed Akash Dutta Arijit Bhattacharjee Sixing Yu Quazi\u00a0Ishtiaque Mahmud Waqwoya Abebe Hung Phan Aishwarya Sarkar Branden Butler et\u00a0al. 2024. The landscape and challenges of HPC research and LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.02018 (2024)."},{"key":"e_1_3_3_2_7_2","unstructured":"Jianfeng Chi Ujjwal Karn Hongyuan Zhan Eric Smith Javier Rando Yiming Zhang Kate Plawiak Zacharie\u00a0Delpierre Coudert Kartikeya Upasani and Mahesh Pasupuleti. 2024. Llama guard 3 vision: Safeguarding human-ai image understanding conversations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.10414 (2024)."},{"key":"e_1_3_3_2_8_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.17323 (2022)."},{"key":"e_1_3_3_2_9_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025)."},{"key":"e_1_3_3_2_10_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.03300 (2020)."},{"key":"e_1_3_3_2_11_2","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.03874 (2021)."},{"key":"e_1_3_3_2_12_2","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et\u00a0al. 2024. Openai o1 system card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.16720 (2024)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Fengqing Jiang Zhangchen Xu Yuetai Li Luyao Niu Zhen Xiang Bo Li Bill\u00a0Yuchen Lin and Radha Poovendran. 2025. Safechain: Safety of language models with long chain-of-thought reasoning capabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.12025 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.1197"},{"key":"e_1_3_3_2_14_2","unstructured":"Ian Kivlichan Justyn Harriman Cameron Raymond Meghan Shah Shraman\u00a0Ray Chaudhuri and Keren Gu-Lemberg. 2024. Upgrading the moderation api with our new multimodal moderation model. Website (2024)."},{"key":"e_1_3_3_2_15_2","volume-title":"ICLR","author":"Lin Zhouhan","year":"2016","unstructured":"Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, and Yoshua Bengio. 2016. Neural Networks with Few Multiplications.. In ICLR."},{"key":"e_1_3_3_2_16_2","unstructured":"Mantas Mazeika Long Phan Xuwang Yin Andy Zou Zifan Wang Norman Mu Elham Sakhaee Nathaniel Li Steven Basart Bo Li et\u00a0al. 2024. Harmbench: A standardized evaluation framework for automated red teaming and robust refusal. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.04249 (2024)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Niklas Muennighoff Zitong Yang Weijia Shi Xiang\u00a0Lisa Li Li Fei-Fei Hannaneh Hajishirzi Luke Zettlemoyer Percy Liang Emmanuel Cand\u00e8s and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.19393 (2025).","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"e_1_3_3_2_18_2","volume-title":"First Conference on Language Modeling","author":"Rein David","year":"2024","unstructured":"David Rein, Betty\u00a0Li Hou, Asa\u00a0Cooper Stickland, Jackson Petty, Richard\u00a0Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel\u00a0R Bowman. 2024. Gpqa: A graduate-level google-proof q&a benchmark. In First Conference on Language Modeling."},{"key":"e_1_3_3_2_19_2","unstructured":"Jonathan\u00a0S Rosenfeld Amir Rosenfeld Yonatan Belinkov and Nir Shavit. 2019. A constructive prediction of the generalization error across scales. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.12673 (2019)."},{"key":"e_1_3_3_2_20_2","unstructured":"Charlie Snell Jaehoon Lee Kelvin Xu and Aviral Kumar. 2024. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.03314 (2024)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Alexandra Souly Qingyuan Lu Dillon Bowen Tu Trinh Elvis Hsieh Sana Pandey Pieter Abbeel Justin Svegliato Scott Emmons Olivia Watkins et\u00a0al. 2024. A strongreject for empty jailbreaks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.10260 (2024).","DOI":"10.52202\/079017-3984"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Tom Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems 36 (2023) 11809\u201311822.","DOI":"10.52202\/075280-0517"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Zhewei Yao Reza Yazdani\u00a0Aminabadi Minjia Zhang Xiaoxia Wu Conglong Li and Yuxiong He. 2022. Zeroquant: Efficient and affordable post-training quantization for large-scale transformers. Advances in neural information processing systems 35 (2022) 27168\u201327183.","DOI":"10.52202\/068431-1970"},{"key":"e_1_3_3_2_25_2","unstructured":"Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J\u00a0Zico Kolter and Matt Fredrikson. 2023. Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.15043 (2023)."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:39:06Z","timestamp":1786520346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":24,"alternative-id":["10.1145\/3731599.3767406","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767406","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}