{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T19:00:31Z","timestamp":1764788431490,"version":"3.46.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001824","name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","doi-asserted-by":"publisher","award":["24-11664S"],"award-info":[{"award-number":["24-11664S"]}],"id":[{"id":"10.13039\/501100001824","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tnnls.2025.3599009","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:30:42Z","timestamp":1755801042000},"page":"20214-20228","source":"Crossref","is-referenced-by-count":0,"title":["Geometric Deep Learning for the Rubik\u2019s Cube Group"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9710-1147","authenticated-orcid":false,"given":"Martin","family":"Krutsk\u00fd","sequence":"first","affiliation":[{"name":"Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6964-4232","authenticated-orcid":false,"given":"Gustav","family":"\u0160\u00edr","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"Bronstein","year":"2021","journal-title":"arXiv:2104.13478"},{"key":"ref3","first-page":"1","article-title":"Deep sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"volume-title":"Two-Phase Algorithm Details","year":"2014","author":"Kociemba","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0070-z"},{"key":"ref8","first-page":"1","article-title":"Deep heuristic-learning in the Rubik\u2019s cube domain: An experimental evaluation","volume-title":"Proc. Inf. Technol. Appl. (ITAT)","author":"Brunetto"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34885-4_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12665"},{"key":"ref11","article-title":"Self-supervision is all you need for solving Rubik\u2019s cube","author":"Takano","year":"2021","journal-title":"arXiv:2106.03157"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1051\/e3sconf\/202449101009"},{"key":"ref13","first-page":"1","article-title":"Solving the Rubik\u2019s cube with approximate policy iteration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"McAleer"},{"key":"ref14","article-title":"Solving Rubik\u2019s cube without tricky sampling","author":"Lin","year":"2024","journal-title":"arXiv:2411.19583"},{"key":"ref15","article-title":"Solving a Rubik\u2019s cube using its local graph structure","author":"Yao","year":"2024","journal-title":"arXiv:2408.07945"},{"key":"ref16","article-title":"Node classification and search on the Rubik\u2019s cube graph with GNNs","author":"Barro","year":"2025","journal-title":"arXiv:2501.18580"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/0824-7935.00065"},{"key":"ref18","first-page":"13251","article-title":"Learning symmetric rules with SATNet","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1098\/rsfs.2022.0077"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/ac2596"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2533\/1\/012006"},{"key":"ref22","article-title":"Towards learning Rubik\u2019s cube with N-tuple-based reinforcement learning","author":"Konen","year":"2023","journal-title":"arXiv:2301.12167"},{"key":"ref23","first-page":"1","article-title":"Learning to play Othello with N-tuple systems","volume":"4","author":"Lucas","year":"2008","journal-title":"Austral. J. Intell. Inf. Process."},{"volume-title":"Notes on Rubik\u2019s Magic Cube","year":"1981","author":"Singmaster","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.2023.2263158"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.54254\/2753-8818\/9\/20240732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.4169\/college.math.j.45.4.242"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/140973499"},{"key":"ref29","first-page":"1","article-title":"Solving all 164,604,041,664 symmetric positions of the Rubik\u2019s cube in the quarter turn metric","volume":"1","author":"Rokicki","year":"2018","journal-title":"Gathering 4 Gardner"},{"volume-title":"The Real Size of Cube Space","year":"1994","author":"Hoey","key":"ref30"},{"key":"ref31","article-title":"Solving the Rubik\u2019s cube optimally is NP-complete","author":"Demaine","year":"2017","journal-title":"arXiv:1706.06708"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4171\/zaa\/1156"},{"volume-title":"Conjugation Invariant Learning With Neural Networks","year":"2022","author":"Low","key":"ref33"},{"key":"ref34","first-page":"1","article-title":"Frame averaging for invariant and equivariant network design","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Puny"},{"key":"ref35","first-page":"15546","article-title":"Equivariance with learned canonicalization functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaba"},{"key":"ref36","first-page":"23727","article-title":"A canonicalization perspective on invariant and equivariant learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref37","first-page":"12","article-title":"A reduction of a graph to a canonical form and an algebra arising during this reduction","volume":"2","author":"Weisfeiler","year":"1968","journal-title":"Nauchno-Technicheskaya Informatsia"},{"key":"ref38","first-page":"1","article-title":"How powerful are graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref39","first-page":"1","article-title":"Lossless compression of structured convolutional models via lifting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"\u0160ourek"},{"volume-title":"Cube Explorer","year":"2018","author":"Kociemba","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"DeeperGCN: All you need to train deeper GCNs","author":"Li","year":"2020","journal-title":"arXiv:2006.07739"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557447"},{"key":"ref45","first-page":"410","article-title":"Hypergraph learning with hyperedge expansion","volume-title":"Proc. Joint Eur. Conf. Mach. Learn. Knowl. Discovery Databases","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00418-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122498"},{"key":"ref49","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref50","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019","journal-title":"arXiv:1903.02428"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11272992\/11134077.pdf?arnumber=11134077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:26Z","timestamp":1764787406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":51,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3599009","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}