{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:13:47Z","timestamp":1784236427097,"version":"3.55.0"},"reference-count":82,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T00:00:00Z","timestamp":1626220800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,14]],"date-time":"2021-07-14T00:00:00Z","timestamp":1626220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Swiss National Foundation grant","award":["200021E 17554"],"award-info":[{"award-number":["200021E 17554"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Many natural optimization problems are NP-hard, which implies that they are probably hard to solve exactly in the worst-case. However, it suffices to get reasonably good solutions for all (or even most) instances in practice. This paper presents a new algorithm for computing approximate solutions in \u0398(<jats:italic>N<\/jats:italic>) for the maximum exact 3-satisfiability (MAX-E-3-SAT) problem by using supervised learning methodology. This methodology allows us to create a learning algorithm able to fix Boolean variables by using local information obtained by the Survey Propagation algorithm. By performing an accurate analysis, on random conjunctive normal form instances of the MAX-E-3-SAT with several Boolean variables, we show that this new algorithm, avoiding any decimation strategy, can build assignments better than a random one, even if the convergence of the messages is not found. Although this algorithm is not competitive with state-of-the-art maximum satisfiability solvers, it can solve substantially larger and more complicated problems than it ever saw during training.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac0496","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T22:45:21Z","timestamp":1621896321000},"page":"035032","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning from survey propagation: a neural network for MAX-E-3-SAT"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2311-4380","authenticated-orcid":false,"given":"Raffaele","family":"Marino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,7,14]]},"reference":[{"key":"mlstac0496bib1","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/978-3-030-51825-7","author":"Pulina","year":"2020"},{"key":"mlstac0496bib2","first-page":"7990","article-title":"Learning local search heuristics for boolean satisfiability","author":"Yolcu","year":"2019"},{"key":"mlstac0496bib3","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-030-63583-1","author":"Chang","year":"2021","edition":"1st edn"},{"key":"mlstac0496bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.disopt.2021.100630","article-title":"Probabilistic characterization of random Max r-Sat","volume":"40","author":"Berend","year":"2021","journal-title":"Discrete Optim."},{"key":"mlstac0496bib5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-319-91086-4_5","author":"Louren\u00e7o","year":"2019"},{"key":"mlstac0496bib6","first-page":"1","article-title":"Generating weighted MAX-2-SAT instances with frustrated loops: an RBM case dtudy","volume":"21","author":"Pei","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac0496bib7","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1145\/502090.502098","article-title":"Some optimal inapproximability results","volume":"48","author":"H\u00e5stad","year":"2001","journal-title":"J. ACM (JACM)"},{"key":"mlstac0496bib8","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-58475-7_11","article-title":"Bounding linear programs by constraint propagation: application to Max-SAT","author":"Dlask","year":"2020"},{"key":"mlstac0496bib9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s10844-016-0422-7","article-title":"Constraint-based and SAT-based diagnosis of automotive configuration problems","volume":"49","author":"Walter","year":"2017","journal-title":"J. Intell. Inf. Syst."},{"key":"mlstac0496bib10","doi-asserted-by":"publisher","first-page":"50","DOI":"10.29007\/3qkh","article-title":"Applications of MaxSAT in data analysis","volume":"vol 59","author":"Berg","year":"2019"},{"key":"mlstac0496bib11","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ejor.2019.03.047","article-title":"A new branch-and-bound algorithm for the maximum edge-weighted clique problem","volume":"278","author":"San Segundo","year":"2019","journal-title":"Eur. J. Oper. Res."},{"key":"mlstac0496bib12","article-title":"Revisiting the challenges of MaxClique","author":"Marino","year":"2018"},{"key":"mlstac0496bib13","article-title":"Large independent sets on random d-regular graphs with fixed degree d","author":"Marino","year":"2020"},{"key":"mlstac0496bib14","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/978-3-319-63387-9_4","article-title":"Maximum satisfiability in software analysis: applications and techniques","author":"Si","year":"2017"},{"key":"mlstac0496bib15","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1007\/978-3-030-67067-2_25","article-title":"On preprocessing for weighted MaxSAT","author":"Paxian","year":"2021"},{"key":"mlstac0496bib16","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-94144-8_3","article-title":"Dynamic polynomial watchdog encoding for solving weighted MaxSAT","author":"Paxian","year":"2018"},{"key":"mlstac0496bib17","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1089\/cmb.2019.0289","article-title":"Revision of Boolean models of regulatory networks using stable state observations","volume":"27","author":"Gouveia","year":"2020","journal-title":"J. Comput. Biol."},{"key":"mlstac0496bib18","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/978-3-662-54577-5_27","article-title":"Minimization of visibly pushdown automata using partial Max-SAT","author":"Heizmann","year":"2017"},{"key":"mlstac0496bib19","article-title":"SAT-based compressive sensing","author":"Ayanzadeh","year":"2019"},{"key":"mlstac0496bib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00607-020-00803-y","article-title":"SAT-based models for overlapping community detection in networks","volume":"102","author":"Jabbour","year":"2020","journal-title":"Computing"},{"key":"mlstac0496bib21","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/3205977.3205987","article-title":"Parametric RBAC maintenance via Max-SAT","author":"Benedetti","year":"2018"},{"key":"mlstac0496bib22","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/978-3-030-63799-6_4","article-title":"The use of Max-SAT for optimal choice of automated theory repairs","author":"Urbonas","year":"2020"},{"key":"mlstac0496bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-021-02276-8","article-title":"Maximizing a deep submodular function optimization with a weighted MAX-SAT problem for trajectory clustering and motion segmentation","volume":"51","author":"Chandriah","year":"2021","journal-title":"Appl. Intell."},{"key":"mlstac0496bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400302.3415612","article-title":"Mcell: multi-row cell layout synthesis with resource constrained max-sat based detailed routing","author":"Li","year":"2020"},{"key":"mlstac0496bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.94.134424","article-title":"Finding and proving the exact ground state of a generalized Ising model by convex optimization and MAX-SAT","volume":"94","author":"Huang","year":"2016","journal-title":"Phys. Rev. B"},{"key":"mlstac0496bib26","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-58115-2_9","article-title":"Global landscape structure and the random Max-SAT phase transition","author":"Ochoa","year":"2020"},{"key":"mlstac0496bib27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07327-2","article-title":"A continuous-time MaxSAT solver with high analog performance","volume":"9","author":"Moln\u00e1r","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstac0496bib28","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/ICTAI50040.2020.00032","article-title":"Towards bridging the gap between SAT and Max-SAT refutations","author":"Py","year":"2020"},{"key":"mlstac0496bib29","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-319-98334-9_15","article-title":"Approximation strategies for incomplete MaxSAT","author":"Joshi","year":"2018"},{"key":"mlstac0496bib30","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/ISMVL.2019.00031","article-title":"Clausal form transformation in MaxSAT","author":"Li","year":"2019"},{"key":"mlstac0496bib31","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1016\/S0022-0000(74)80044-9","article-title":"Approximation algorithms for combinatorial problems","volume":"9","author":"Johnson","year":"1974","journal-title":"J. Comput. Syst. Sci."},{"key":"mlstac0496bib32","doi-asserted-by":"publisher","first-page":"p 349","DOI":"10.1007\/978-3-030-59758-0","author":"Knebl","year":"2020","edition":"1st edn"},{"key":"mlstac0496bib33","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1145\/278298.278306","article-title":"Proof verification and the hardness of approximation problems","volume":"45","author":"Arora","year":"1998","journal-title":"J. ACM (JACM)"},{"key":"mlstac0496bib34","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1137\/15M1053369","article-title":"Greedy algorithms for the maximum satisfiability problem: simple algorithms and inapproximability bounds","volume":"46","author":"Poloczek","year":"2017","journal-title":"SIAM J. Comput."},{"key":"mlstac0496bib35","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1109\/FOCS46700.2020.00039","article-title":"Optimal streaming approximations for all boolean Max-2CSPs and Max-kSAT","author":"Chou","year":"2020"},{"key":"mlstac0496bib36","first-page":"484","article-title":"On the mysteries of MAX NAE-SAT","author":"Brakensiek","year":"2021"},{"key":"mlstac0496bib37","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-30048-7_11","article-title":"Techniques inspired by local search for incomplete MaxSAT and the linear algorithm: varying resolution and solution-guided search","author":"Demirovi\u0107","year":"2019"},{"key":"mlstac0496bib38","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/978-3-319-58088-3_10","article-title":"Walksat based-learning automata for Max-SAT","author":"Bouhmala","year":"2016"},{"key":"mlstac0496bib39","doi-asserted-by":"publisher","first-page":"3915","DOI":"10.5555\/3298023.3298137","article-title":"Should algorithms for random SAT and Max-SAT be different?","author":"Liu","year":"2017"},{"key":"mlstac0496bib40","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s10732-018-9386-9","article-title":"Combining simulated annealing with local search heuristic for MAX-SAT","volume":"25","author":"Bouhmala","year":"2019","journal-title":"J. Heuristics"},{"key":"mlstac0496bib41","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/MIS.2017.3121546","article-title":"Data mining-based decomposition for solving the MAXSAT problem: toward a new approach","volume":"32","author":"Djenouri","year":"2017","journal-title":"IEEE Intell. Syst."},{"key":"mlstac0496bib42","author":"Brandts-Longtin","year":"2019"},{"key":"mlstac0496bib43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.94.042318","article-title":"Adiabatic optimization versus diffusion Monte Carlo methods","volume":"94","author":"Jarret","year":"2016","journal-title":"Phys. Rev. A"},{"key":"mlstac0496bib44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/7982851","article-title":"Evidence of exponential speed-up in the solution of hard optimization problems","volume":"2018","author":"Traversa","year":"2018","journal-title":"Complexity"},{"key":"mlstac0496bib45","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1109\/IEMCON.2019.8936281","article-title":"Solving Max-SAT problem by binary biogeograph-based optimization algorithm","author":"Ali","year":"2019"},{"key":"mlstac0496bib46","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/978-3-319-66984-7","author":"Bouhmala","year":"2018","edition":"1st edn"},{"key":"mlstac0496bib47","article-title":"Effect of initial assignment on local search performance for Max SAT","author":"Berend","year":"2020"},{"key":"mlstac0496bib48","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.cor.2018.12.005","article-title":"An iterative Path-Breaking approach with mutation and restart strategies for the MAX-SAT problem","volume":"104","author":"Xu","year":"2019","journal-title":"Comput. Oper. Res."},{"key":"mlstac0496bib49","author":"Bacchus","year":"2020"},{"key":"mlstac0496bib50","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1007\/s10462-020-09908-4","article-title":"Stochastic local search for partial Max-SAT: an experimental evaluation","volume":"54","author":"AlKasem","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"mlstac0496bib51","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.24963\/ijcai.2018\/187","article-title":"Solving (weighted) partial MaxSAT by dynamic local search for SAT","volume":"7","author":"Lei","year":"2018","journal-title":"IJCAI"},{"key":"mlstac0496bib52","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3233\/SAT190116","article-title":"RC2: an efficient MaxSAT solver","volume":"11","author":"Ignatiev","year":"2019","journal-title":"J. Satisfiabil. Boolean Model. Comput."},{"key":"mlstac0496bib53","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-030-19212-9_3","article-title":"Core-boosted linear search for incomplete MaxSAT","author":"Berg","year":"2019"},{"key":"mlstac0496bib54","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.artint.2016.11.001","article-title":"An efficient local search algorithm for weighted partial maximum satisfiability","volume":"243","author":"Luo","year":"2017","journal-title":"Artif. Intell."},{"key":"mlstac0496bib55","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/978-3-319-94144-8_4","article-title":"Solving MaxSAT with bit-vector optimization","author":"Nadel","year":"2018"},{"key":"mlstac0496bib56","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/abe6fe","article-title":"Belief propagation guided decimation algorithms for random constraint satisfaction problems with growing domainsBelief propagation guided decimation algorithms for random constraint satisfaction problems with growing domains","volume":"2021","author":"Zhao","year":"2021","journal-title":"J. Stat. Mech.: Theory Expl."},{"key":"mlstac0496bib57","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1126\/science.1073287","article-title":"Analytic and algorithmic solution of random satisfiability problems","volume":"297","author":"M\u00e9zard","year":"2002","journal-title":"Science"},{"key":"mlstac0496bib58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms12996","article-title":"The backtracking survey propagation algorithm for solving random K-SAT problems","volume":"7","author":"Marino","year":"2016","journal-title":"Nat. Commun."},{"key":"mlstac0496bib59","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.70.036107","article-title":"Minimizing energy below the glass thresholds","volume":"70","author":"Battaglia","year":"2004","journal-title":"Phys. Rev. E"},{"key":"mlstac0496bib60","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TETC.2017.2736504","article-title":"Propagation algorithm for the MAX-3-SAT problem","volume":"7","author":"Wang","year":"2017","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"mlstac0496bib61","doi-asserted-by":"publisher","first-page":"p 187","DOI":"10.1007\/978-3-030-22475-2","author":"Berry","year":"2019"},{"key":"mlstac0496bib62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICCUBEA.2018.8697857","article-title":"A review of machine learning and deep learning applications","author":"Shinde","year":"2018"},{"key":"mlstac0496bib63","doi-asserted-by":"publisher","first-page":"9375","DOI":"10.1109\/ACCESS.2017.2788044","article-title":"Deep learning applications in medical image analysis","volume":"6","author":"Ker","year":"2017","journal-title":"IEEE Access"},{"key":"mlstac0496bib64","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1109\/ISSRE.2019.00020","article-title":"An empirical study of common challenges in developing deep learning applications","author":"Zhang","year":"2019"},{"key":"mlstac0496bib65","doi-asserted-by":"publisher","author":"Balas","year":"2019","DOI":"10.1007\/978-3-030-11479-4"},{"key":"mlstac0496bib66","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s00419-020-01779-z","article-title":"Application of supervised learning to validation of damage detection","volume":"91","author":"Sarmadi","year":"2021","journal-title":"Arch. Appl. Mech."},{"key":"mlstac0496bib67","article-title":"Learning a sat solver from single-bit supervision","author":"Selsam","year":"2018"},{"key":"mlstac0496bib68","article-title":"Learning combinatorial optimization algorithms over graphs","author":"Dai","year":"2020"},{"key":"mlstac0496bib69","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","article-title":"Machine learning for combinatorial optimization: A methodological tour d\u2019horizon","volume":"290","author":"Bengio","year":"2020","journal-title":"Eur. J. Oper. Res."},{"key":"mlstac0496bib70","doi-asserted-by":"publisher","first-page":"4493","DOI":"10.1609\/aaai.v34i04.5877","article-title":"Learning Max-SAT from contextual examples for combinatorial optimisation","volume":"34","author":"Kumar","year":"2020","journal-title":"Proc. Conf. Artif. Intell."},{"key":"mlstac0496bib71","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab02de","article-title":"Biased landscapes for random constraint satisfaction problems","volume":"2019","author":"Budzynski","year":"2019","journal-title":"J. Stat. Mech.: Theory Exp."},{"key":"mlstac0496bib72","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1109\/FOCS.2019.00086","article-title":"Breaking of 1RSB in random regular MAX-NAE-SAT","author":"Bartha","year":"2019"},{"key":"mlstac0496bib73","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/aa9529","article-title":"Phase transitions in the q-coloring of random hypergraphs","volume":"50","author":"Gabri\u00e9","year":"2017","journal-title":"J. Phys. A"},{"key":"mlstac0496bib74","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1007\/s10955-020-02635-8","article-title":"The asymptotics of the clustering transition for random constraint satisfaction problems","volume":"181","author":"Budzynski","year":"2020","journal-title":"J. Stat. Phys."},{"key":"mlstac0496bib75","article-title":"Replica symmetry breaking in the random regular k-NAE-SAT problem","author":"Bartha","year":"2020"},{"key":"mlstac0496bib76","article-title":"The computer science and physics of community detection: landscapes, phase transitions, and hardness","author":"Moore","year":"2017"},{"key":"mlstac0496bib77","first-page":"1","article-title":"Analysing survey propagation guided decimationon random formulas","volume":"vol 55","author":"Hetterich","year":"2016"},{"key":"mlstac0496bib78","first-page":"801","article-title":"MLPACK: a scalable C++ machine learning library","volume":"14","author":"Curtin","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac0496bib79","author":"Marino","year":"2020"},{"key":"mlstac0496bib80","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1090\/dimacs\/026","article-title":"Local search strategies for satisfiability testing","volume":"26","author":"Selman","year":"1996","journal-title":"Cliques Coloring Satisfiabil."},{"key":"mlstac0496bib81","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/2746539.2746619","article-title":"Proof of the satisfiability conjecture for large k","author":"Ding","year":"2015"},{"key":"mlstac0496bib82","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T13:55:25Z","timestamp":1639403725000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac0496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,14]]},"references-count":82,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,7,14]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac0496","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,14]]},"assertion":[{"value":"Learning from survey propagation: a neural network for MAX-E-3-SAT","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-10-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-05-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-07-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}