{"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/learning-a-sat-solver-from-single-bit","title":"Learning a SAT Solver from Single-Bit Supervision","arxiv_id":"1802.03685","date":"2018-02-11","proceeding":"ICLR 2019 5","authors":["Daniel Selsam","Matthew Lamm","Benedikt Bünz","Percy Liang","Leonardo de Moura","David L. Dill"],"abstract":"We present NeuroSAT, a message passing neural network that learns to solve\nSAT problems after only being trained as a classifier to predict\nsatisfiability. Although it is not competitive with state-of-the-art SAT\nsolvers, NeuroSAT can solve problems that are substantially larger and more\ndifficult than it ever saw during training by simply running for more\niterations. Moreover, NeuroSAT generalizes to novel distributions; after\ntraining only on random SAT problems, at test time it can solve SAT problems\nencoding graph coloring, clique detection, dominating set, and vertex cover\nproblems, all on a range of distributions over small random graphs.","url_abs":"http://arxiv.org/abs/1802.03685v4","url_pdf":"http://arxiv.org/pdf/1802.03685v4.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":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/corail-research/learning-generic-csp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/dragonavelar/Learning-SAT-Solver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/dselsam/neurosat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/mister-bailey/TensorSAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/mluszczyk/deepsat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-a-sat-solver-from-single-bit","repo_url":"https://github.com/ryanzhangfan/NeuroSAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.03685","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}