{"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/automated-proof-synthesis-for-propositional","title":"Automated proof synthesis for propositional logic with deep neural networks","arxiv_id":"1805.11799","date":"2018-05-30","proceeding":null,"authors":["Taro Sekiyama","Kohei Suenaga"],"abstract":"This work explores the application of deep learning, a machine learning\ntechnique that uses deep neural networks (DNN) in its core, to an automated\ntheorem proving (ATP) problem. To this end, we construct a statistical model\nwhich quantifies the likelihood that a proof is indeed a correct one of a given\nproposition. Based on this model, we give a proof-synthesis procedure that\nsearches for a proof in the order of the likelihood. This procedure uses an\nestimator of the likelihood of an inference rule being applied at each step of\na proof. As an implementation of the estimator, we propose a\nproposition-to-proof architecture, which is a DNN tailored to the automated\nproof synthesis problem. To empirically demonstrate its usefulness, we apply\nour model to synthesize proofs of propositional logic. We train the\nproposition-to-proof model using a training dataset of proposition-proof pairs.\nThe evaluation against a benchmark set shows the very high accuracy and an\nimprovement to the recent work of neural proof synthesis.","url_abs":"http://arxiv.org/abs/1805.11799v1","url_pdf":"http://arxiv.org/pdf/1805.11799v1.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":"automated-proof-synthesis-for-propositional","repo_url":"https://github.com/mluszczyk/deepsat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}