{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/holist-an-environment-for-machine-learning-of","title":"HOList: An Environment for Machine Learning of Higher-Order Theorem Proving","arxiv_id":"1904.03241","date":"2019-04-05","proceeding":null,"authors":["Kshitij Bansal","Sarah M. Loos","Markus N. Rabe","Christian Szegedy","Stewart Wilcox"],"abstract":"We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an interesting, open-ended challenge for deep learning. We provide an open-source framework based on the HOL Light theorem prover that can be used as a reinforcement learning environment. HOL Light comes with a broad coverage of basic mathematical theorems on calculus and the formal proof of the Kepler conjecture, from which we derive a challenging benchmark for automated reasoning. We also present a deep reinforcement learning driven automated theorem prover, DeepHOL, with strong initial results on this benchmark.","url_abs":"https://arxiv.org/abs/1904.03241v3","url_pdf":"https://arxiv.org/pdf/1904.03241v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"holist-an-environment-for-machine-learning-of","repo_url":"https://github.com/Kerram/Deephol-Bert-Zpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"holist-an-environment-for-machine-learning-of","repo_url":"https://github.com/Kerram/holist-train","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"holist-an-environment-for-machine-learning-of","repo_url":"https://github.com/tensorflow/deepmath/tree/master/deepmath/deephol","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"},{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"holist","name":"HOList","full_name":"HOList"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/automated-theorem-proving-on-holist-benchmark","task":"Automated Theorem Proving","dataset":"HOList benchmark","model":"Tactic Dependent Loop","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"38.88"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-holist-benchmark","task":"Automated Theorem Proving","dataset":"HOList benchmark","model":"Deeper Wider WaveNet","rank_in_archive_order":4,"of":4,"metrics":{"Percentage correct":"32.65"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.03241","atlas_url":"https://app.syntology.ai/?focus=1904.03241","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}