Predicting the satisfiability of Boolean formulas by incorporating gated recurrent unit (GRU) in the Transformer framework

The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:PeerJ. Computer science Ročník 10; s. e2169
Hlavní autori: Chang, Wenjing, Guo, Mengyu, Luo, Junwei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States PeerJ. Ltd 08.08.2024
PeerJ Inc
Predmet:
ISSN:2376-5992, 2376-5992
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately identify these structural features is crucial for neural networks to solve the SAT problem. Currently, learning-based SAT solvers, whether they are end-to-end models or enhancements to traditional heuristic algorithms, have achieved significant progress. In this article, we propose TG-SAT, an end-to-end framework based on Transformer and gated recurrent neural network (GRU) for predicting the satisfiability of SAT problems. TG-SAT can learn the structural features of SAT problems in a weakly supervised environment. To capture the structural information of the SAT problem, we encodes a SAT problem as an undirected graph and integrates GRU into the Transformer structure to update the node embeddings. By computing cross-attention scores between literals and clauses, a weighted representation of nodes is obtained. The model is eventually trained as a classifier to predict the satisfiability of the SAT problem. Experimental results demonstrate that TG-SAT achieves a 2%–5% improvement in accuracy on random 3-SAT problems compared to NeuroSAT. It also outperforms in SR(N), especially in handling more complex SAT problems, where our model achieves higher prediction accuracy.
AbstractList The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately identify these structural features is crucial for neural networks to solve the SAT problem. Currently, learning-based SAT solvers, whether they are end-to-end models or enhancements to traditional heuristic algorithms, have achieved significant progress. In this article, we propose TG-SAT, an end-to-end framework based on Transformer and gated recurrent neural network (GRU) for predicting the satisfiability of SAT problems. TG-SAT can learn the structural features of SAT problems in a weakly supervised environment. To capture the structural information of the SAT problem, we encodes a SAT problem as an undirected graph and integrates GRU into the Transformer structure to update the node embeddings. By computing cross-attention scores between literals and clauses, a weighted representation of nodes is obtained. The model is eventually trained as a classifier to predict the satisfiability of the SAT problem. Experimental results demonstrate that TG-SAT achieves a 2%-5% improvement in accuracy on random 3-SAT problems compared to NeuroSAT. It also outperforms in SR(N), especially in handling more complex SAT problems, where our model achieves higher prediction accuracy.The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately identify these structural features is crucial for neural networks to solve the SAT problem. Currently, learning-based SAT solvers, whether they are end-to-end models or enhancements to traditional heuristic algorithms, have achieved significant progress. In this article, we propose TG-SAT, an end-to-end framework based on Transformer and gated recurrent neural network (GRU) for predicting the satisfiability of SAT problems. TG-SAT can learn the structural features of SAT problems in a weakly supervised environment. To capture the structural information of the SAT problem, we encodes a SAT problem as an undirected graph and integrates GRU into the Transformer structure to update the node embeddings. By computing cross-attention scores between literals and clauses, a weighted representation of nodes is obtained. The model is eventually trained as a classifier to predict the satisfiability of the SAT problem. Experimental results demonstrate that TG-SAT achieves a 2%-5% improvement in accuracy on random 3-SAT problems compared to NeuroSAT. It also outperforms in SR(N), especially in handling more complex SAT problems, where our model achieves higher prediction accuracy.
The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately identify these structural features is crucial for neural networks to solve the SAT problem. Currently, learning-based SAT solvers, whether they are end-to-end models or enhancements to traditional heuristic algorithms, have achieved significant progress. In this article, we propose TG-SAT, an end-to-end framework based on Transformer and gated recurrent neural network (GRU) for predicting the satisfiability of SAT problems. TG-SAT can learn the structural features of SAT problems in a weakly supervised environment. To capture the structural information of the SAT problem, we encodes a SAT problem as an undirected graph and integrates GRU into the Transformer structure to update the node embeddings. By computing cross-attention scores between literals and clauses, a weighted representation of nodes is obtained. The model is eventually trained as a classifier to predict the satisfiability of the SAT problem. Experimental results demonstrate that TG-SAT achieves a 2%-5% improvement in accuracy on random 3-SAT problems compared to NeuroSAT. It also outperforms in SR(N), especially in handling more complex SAT problems, where our model achieves higher prediction accuracy.
ArticleNumber e2169
Audience Academic
Author Chang, Wenjing
Luo, Junwei
Guo, Mengyu
Author_xml – sequence: 1
  givenname: Wenjing
  surname: Chang
  fullname: Chang, Wenjing
  organization: School of Software, Henan Polytechnic University, Jiaozuo, Henan, China
– sequence: 2
  givenname: Mengyu
  surname: Guo
  fullname: Guo, Mengyu
  organization: School of Software, Henan Polytechnic University, Jiaozuo, Henan, China
– sequence: 3
  givenname: Junwei
  surname: Luo
  fullname: Luo, Junwei
  organization: School of Software, Henan Polytechnic University, Jiaozuo, Henan, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39145235$$D View this record in MEDLINE/PubMed
BookMark eNp1ksFvFCEUhyemxtbao1cziZf2MCsMwzCcTG20btJEU9szYeAxZZ0ZVmDU9a-X2a1N1ygcIPC9Lzzye54djG6ELHuJ0YIxzN6sAfyqUGFR4po_yY5KwuqCcl4ePNofZichrBBCmOI0-LPskHBc0ZLQo-zXZw_aqmjHLo93kAcZbTBWtra3cZM7k79zrgc55sb5YeplyNtNbkfl_Np5ua3rZASde1CT9zDGfBptzE8vr2_PEri13ng5hlkAPjdeDvDD-a8vsqdG9gFO7tfj7PbD-5uLj8XVp8vlxflVoSilsTCsapWGVkMpkcItxZRqTlFrCNRAyhooYyVUHLSpSC0JplWLKtXwBmvNODnOljuvdnIl1t4O0m-Ek1ZsD5zvhPTRqh4E5gYb3ajk15WUpKGEtWXDtUHM1FWVXG93rvXUDqBVatfLfk-6fzPaO9G57wJjUhJUsmQ4vTd4922CEMVgg4K-lyO4KQiCOMGMVpgm9PUO7WR6mx2NS0o14-K8wYShijQkUYt_UGlqGKxKeTE2ne8VnO0VJCbCz9jJKQSx_HK9z7563O9Do38ClIBiByjvQvBgHhCMxJxRsc2oUEHMGU08-YtXNqYYufm7bP-fqt9hqO0X
CitedBy_id crossref_primary_10_1038_s41598_024_82420_9
crossref_primary_10_1016_j_fuel_2025_136452
Cites_doi 10.3390/math10244734
10.1109/ACCESS.2021.3068998
10.1007/978-3-642-81955-1
10.1016/S1574-6526(07)03002-7
10.1016/j.eswa.2022.118241
10.24963/ijcai.2020/164
10.1016/j.2020.07.063
10.1007/BF00339943
10.1007/978-3-030-24258-9_24
10.1016/j.asoc.2022.109312
10.1613/jair.2490
10.3115/v1/D14-1179
10.3233/FAIA200987
10.1016/j.artint.2012.08.001
10.1007/s11633-022-1396-2
10.1016/j.artint.2012.05.004
ContentType Journal Article
Copyright 2024 Chang et al.
COPYRIGHT 2024 PeerJ. Ltd.
2024 Chang et al. 2024 Chang et al.
Copyright_xml – notice: 2024 Chang et al.
– notice: COPYRIGHT 2024 PeerJ. Ltd.
– notice: 2024 Chang et al. 2024 Chang et al.
DBID AAYXX
CITATION
NPM
ISR
7X8
5PM
DOA
DOI 10.7717/peerj-cs.2169
DatabaseName CrossRef
PubMed
Gale In Context: Science
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed


CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2376-5992
ExternalDocumentID oai_doaj_org_article_19f1fd8cd95d4aa38537b289df07f644
PMC11323027
A813704383
39145235
10_7717_peerj_cs_2169
Genre Journal Article
GrantInformation_xml – fundername: Young Elite Teachers in Henan Province
  grantid: No. 2020GGJS050
– fundername: Doctor Foundation of Henan Polytechnic University
  grantid: B2020-31
– fundername: The National Natural Science Foundation of Chinaunder
  grantid: No. 62202145; No. 61972134
– fundername: Innovative and Scientifc Research Team of Henan Polvtechnic University
  grantid: No. T2021-3
GroupedDBID 53G
5VS
8FE
8FG
AAFWJ
AAYXX
ABUWG
ADBBV
AFFHD
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
ARAPS
ARCSS
AZQEC
BCNDV
BENPR
BGLVJ
BPHCQ
CCPQU
CITATION
DWQXO
FRP
GNUQQ
GROUPED_DOAJ
HCIFZ
IAO
ICD
IEA
ISR
ITC
K6V
K7-
M~E
OK1
P62
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
RPM
H13
NPM
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c555t-f74bcdebde2a0c1b5155d950bf3e6e326e5772e49edf436a3154b04c8981dd793
IEDL.DBID DOA
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001288178000004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2376-5992
IngestDate Fri Oct 03 12:50:48 EDT 2025
Tue Nov 04 02:06:16 EST 2025
Fri Sep 05 08:32:44 EDT 2025
Tue Nov 11 10:54:11 EST 2025
Tue Nov 04 18:18:32 EST 2025
Thu Nov 13 16:11:39 EST 2025
Mon Jul 21 06:05:00 EDT 2025
Tue Nov 18 21:48:07 EST 2025
Sat Nov 29 06:22:50 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Transformer
Cross-attention
GRU
Boolean satisfiability problem
Random 3-SAT
Language English
License https://creativecommons.org/licenses/by-nc/4.0
2024 Chang et al.
This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits using, remixing, and building upon the work non-commercially, as long as it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c555t-f74bcdebde2a0c1b5155d950bf3e6e326e5772e49edf436a3154b04c8981dd793
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://doaj.org/article/19f1fd8cd95d4aa38537b289df07f644
PMID 39145235
PQID 3093175415
PQPubID 23479
PageCount e2169
ParticipantIDs doaj_primary_oai_doaj_org_article_19f1fd8cd95d4aa38537b289df07f644
pubmedcentral_primary_oai_pubmedcentral_nih_gov_11323027
proquest_miscellaneous_3093175415
gale_infotracmisc_A813704383
gale_infotracacademiconefile_A813704383
gale_incontextgauss_ISR_A813704383
pubmed_primary_39145235
crossref_primary_10_7717_peerj_cs_2169
crossref_citationtrail_10_7717_peerj_cs_2169
PublicationCentury 2000
PublicationDate 2024-08-08
PublicationDateYYYYMMDD 2024-08-08
PublicationDate_xml – month: 08
  year: 2024
  text: 2024-08-08
  day: 08
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: San Diego, USA
PublicationTitle PeerJ. Computer science
PublicationTitleAlternate PeerJ Comput Sci
PublicationYear 2024
Publisher PeerJ. Ltd
PeerJ Inc
Publisher_xml – name: PeerJ. Ltd
– name: PeerJ Inc
References Vaswani (10.7717/peerj-cs.2169/ref-29) 2017
Bengio (10.7717/peerj-cs.2169/ref-2) 2021; 290
Karim (10.7717/peerj-cs.2169/ref-13) 2021; 9
Goldberg (10.7717/peerj-cs.2169/ref-9) 2001
Selsam (10.7717/peerj-cs.2169/ref-20) 2019
Danisovszky (10.7717/peerj-cs.2169/ref-6) 2020
Someetheram (10.7717/peerj-cs.2169/ref-27) 2022; 10
Shi (10.7717/peerj-cs.2169/ref-24) 2021
Rintanen (10.7717/peerj-cs.2169/ref-19) 2012; 193
Cook (10.7717/peerj-cs.2169/ref-5) 1971
Kasi (10.7717/peerj-cs.2169/ref-14) 2013
Silva (10.7717/peerj-cs.2169/ref-26) 2021
Sen (10.7717/peerj-cs.2169/ref-22) 2022; 209
Cho (10.7717/peerj-cs.2169/ref-4) 2014
Zhang (10.7717/peerj-cs.2169/ref-33) 2020
Hopfield (10.7717/peerj-cs.2169/ref-12) 1985; 52
Gilmer (10.7717/peerj-cs.2169/ref-8) 2017
Bünz (10.7717/peerj-cs.2169/ref-3) 2017
Xu (10.7717/peerj-cs.2169/ref-30) 2008; 32
Liu (10.7717/peerj-cs.2169/ref-17) 2021
Ozolins (10.7717/peerj-cs.2169/ref-18) 2021
Shi (10.7717/peerj-cs.2169/ref-25) 2022
Selsam (10.7717/peerj-cs.2169/ref-21) 2018
Tseitin (10.7717/peerj-cs.2169/ref-28) 1983
Amizadeh (10.7717/peerj-cs.2169/ref-1) 2018
Yolcu (10.7717/peerj-cs.2169/ref-31) 2019
Zamri (10.7717/peerj-cs.2169/ref-32) 2022; 126
Shi (10.7717/peerj-cs.2169/ref-23) 2021
Guo (10.7717/peerj-cs.2169/ref-11) 2022; 20
Devlin (10.7717/peerj-cs.2169/ref-7) 2008
Gomes (10.7717/peerj-cs.2169/ref-10) 2008; vol. 3
Li (10.7717/peerj-cs.2169/ref-15) 2022
Li (10.7717/peerj-cs.2169/ref-16) 2012; 190
References_xml – volume: 10
  start-page: 4734
  issue: 24
  year: 2022
  ident: 10.7717/peerj-cs.2169/ref-27
  article-title: Random maximum 2 satisfiability logic in discrete hopfield neural network incorporating improved election algorithm
  publication-title: Mathematics
  doi: 10.3390/math10244734
– volume: 9
  start-page: 50831
  year: 2021
  ident: 10.7717/peerj-cs.2169/ref-13
  article-title: Random satisfiability: a higher-order logical approach in discrete hopfield neural network
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3068998
– start-page: 466
  volume-title: Automation of reasoning: 2: classical papers on computational logic 1967–1970
  year: 1983
  ident: 10.7717/peerj-cs.2169/ref-28
  article-title: On the complexity of derivation in propositional calculus
  doi: 10.1007/978-3-642-81955-1
– volume: vol. 3
  start-page: 89
  volume-title: Handbook of knowledge representation
  year: 2008
  ident: 10.7717/peerj-cs.2169/ref-10
  article-title: Satisfiability solvers
  doi: 10.1016/S1574-6526(07)03002-7
– volume: 209
  start-page: 118241
  year: 2022
  ident: 10.7717/peerj-cs.2169/ref-22
  article-title: Toward understanding variations in price and billing in US healthcare services: a predictive analytics approach
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2022.118241
– year: 2020
  ident: 10.7717/peerj-cs.2169/ref-33
  article-title: NLocalSAT: boosting local search with solution prediction
  doi: 10.24963/ijcai.2020/164
– volume: 290
  start-page: 405
  issue: 2
  year: 2021
  ident: 10.7717/peerj-cs.2169/ref-2
  article-title: Machine learning for combinatorial optimization: a methodological tour d’horizon
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.2020.07.063
– start-page: 114
  year: 2001
  ident: 10.7717/peerj-cs.2169/ref-9
  article-title: Using SAT for combinational equivalence checking
– volume: 52
  start-page: 141
  year: 1985
  ident: 10.7717/peerj-cs.2169/ref-12
  article-title: “Neural” computation of decisions in optimization problems
  publication-title: Biological Cybernetics
  doi: 10.1007/BF00339943
– year: 2008
  ident: 10.7717/peerj-cs.2169/ref-7
  article-title: Satisfiability as a classification problem
– year: 2019
  ident: 10.7717/peerj-cs.2169/ref-20
  article-title: Guiding high-performance SAT solvers with unsat-core predictions
  doi: 10.1007/978-3-030-24258-9_24
– volume: 126
  start-page: 109312
  year: 2022
  ident: 10.7717/peerj-cs.2169/ref-32
  article-title: Weighted random k satisfiability for k=1,2 (r2SAT) in discrete hopfield neural network
  publication-title: Applied Soft Computing
  doi: 10.1016/j.asoc.2022.109312
– volume: 32
  start-page: 565
  year: 2008
  ident: 10.7717/peerj-cs.2169/ref-30
  article-title: SATzilla: portfolio-based algorithm selection for SAT
  publication-title: Journal of Artificial Intelligence Research
  doi: 10.1613/jair.2490
– year: 2022
  ident: 10.7717/peerj-cs.2169/ref-15
  article-title: DeepSAT: an EDA-driven learning framework for SAT
– year: 2017
  ident: 10.7717/peerj-cs.2169/ref-29
  article-title: Attention is all you need
– year: 2022
  ident: 10.7717/peerj-cs.2169/ref-25
  article-title: SATformer: transformers for SAT solving
– year: 2021
  ident: 10.7717/peerj-cs.2169/ref-17
  article-title: Can graph neural networks learn to solve MaxSAT problem?
– year: 2017
  ident: 10.7717/peerj-cs.2169/ref-3
  article-title: Graph neural networks and boolean satisfiability
– year: 2021
  ident: 10.7717/peerj-cs.2169/ref-24
  article-title: Transformers satisfy
– start-page: 1
  year: 2021
  ident: 10.7717/peerj-cs.2169/ref-18
  article-title: Goal-aware neural SAT solver
– year: 2014
  ident: 10.7717/peerj-cs.2169/ref-4
  article-title: Learning phrase representations using RNN Encoder–Decoder for statistical machine translation
  doi: 10.3115/v1/D14-1179
– start-page: 7992
  year: 2019
  ident: 10.7717/peerj-cs.2169/ref-31
  article-title: Learning local search heuristics for Boolean satisfiability
– start-page: 151
  year: 1971
  ident: 10.7717/peerj-cs.2169/ref-5
  article-title: The complexity of theorem-proving procedures
– year: 2021
  ident: 10.7717/peerj-cs.2169/ref-23
  article-title: Transformer-based machine learning for fast SAT solvers and logic synthesis
– start-page: 732
  year: 2013
  ident: 10.7717/peerj-cs.2169/ref-14
  article-title: Cassandra: proactive conflict minimization through optimized task scheduling
– year: 2018
  ident: 10.7717/peerj-cs.2169/ref-21
  article-title: Learning a SAT solver from single-bit supervision
– start-page: 133
  volume-title: Handbook of satisfiability
  year: 2021
  ident: 10.7717/peerj-cs.2169/ref-26
  article-title: Conflict-driven clause learning SAT solvers
  doi: 10.3233/FAIA200987
– year: 2018
  ident: 10.7717/peerj-cs.2169/ref-1
  article-title: Learning to solve circuit-SAT: an unsupervised differentiable approach
– volume: 193
  start-page: 45
  year: 2012
  ident: 10.7717/peerj-cs.2169/ref-19
  article-title: Planning as satisfiability: heuristics
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2012.08.001
– year: 2020
  ident: 10.7717/peerj-cs.2169/ref-6
  article-title: Classification of SAT problem instances by machine learning methods
– year: 2017
  ident: 10.7717/peerj-cs.2169/ref-8
  article-title: Neural message passing for quantum chemistry
– volume: 20
  start-page: 640
  year: 2022
  ident: 10.7717/peerj-cs.2169/ref-11
  article-title: Machine learning methods in solving the boolean satisfiability problem
  publication-title: Machine Intelligence Research
  doi: 10.1007/s11633-022-1396-2
– volume: 190
  start-page: 32
  year: 2012
  ident: 10.7717/peerj-cs.2169/ref-16
  article-title: Optimizing with minimum satisfiability
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2012.05.004
SSID ssj0001511119
Score 2.2784958
Snippet The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage e2169
SubjectTerms Algorithms
Algorithms and Analysis of Algorithms
Artificial Intelligence
Boolean satisfiability problem
Computational linguistics
Cross-attention
Data Mining and Machine Learning
Deep learning
Electric transformers
GRU
Language processing
Natural language interfaces
Neural Networks
Random 3-SAT
Software Engineering
Transformer
Title Predicting the satisfiability of Boolean formulas by incorporating gated recurrent unit (GRU) in the Transformer framework
URI https://www.ncbi.nlm.nih.gov/pubmed/39145235
https://www.proquest.com/docview/3093175415
https://pubmed.ncbi.nlm.nih.gov/PMC11323027
https://doaj.org/article/19f1fd8cd95d4aa38537b289df07f644
Volume 10
WOSCitedRecordID wos001288178000004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: P5Z
  dateStart: 20150527
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: K7-
  dateStart: 20150527
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: BENPR
  dateStart: 20150527
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2376-5992
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001511119
  issn: 2376-5992
  databaseCode: PIMPY
  dateStart: 20150527
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagcOBS3hAoK4MQD4nQOI91fOyiLVSoq2hppaUXy3bsUlQlVdIglQO_nZk8VhshxIWLD-vZ3die8XwTj78h5KUw4NVi7vwgsLEfc5X7OgHDEzpPhDOWO67aYhN8sUhXK5FtlPrCnLCOHribuF0mHHNYYkckeaxUBO6Fa4gSchdwB84cd9-Ai41gqrsfjFuB6Eg1OYQsuxfWVt99U78PGSY3bzihlqv_zx15wyWN0yU3_M_-HbLdA0e61z3wXXLNFvfI7aEoA-1t9D75mVV49oLZzBTAHa3b6wtnHR33FS0dnZXluVUFRbjaAHim-ooiR0NHaYzfw1drOa3wVTySN9EG7J6--bg8fguC7a8eDXgX_toN-V0PyPH-_OjDJ78vsOCbJEkufcdjbXKrcxuqwDCN5V5gngPtIju1AOxsAuDbxsLmLo6mKgK8pYPYpAJQbg6W_ZBsFWVhHxPqdGRSw1I1ZTZmSkNYh7Q0IuQQfSdCeeTdMOPS9OzjWATjXEIUggsk2wWSppa4QB55tRa_6Gg3_iY4w-VbCyFbdvsB6JDsdUj-S4c88gIXX-JcF5hwc6qaupYHX5ZyL2URb_lcPfK6F3IlPLlR_f0FGD9SaI0kd0aSYLBm1P180DGJXZjlVtiyqSWeSgOcA0zlkUedzq0HFgkWJ2EEPelIG0cjH_cUZ99avnDGohCPp5_8j7l6Sm6FgOvaHMh0h2xdVo19Rm6aH6DM1YRc56t0Qm7M5otsOWltEtrP3If28Ncc2iw5gf7s4DD7-hvlPEMg
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predicting+the+satisfiability+of+Boolean+formulas+by+incorporating+gated+recurrent+unit+%28GRU%29+in+the+Transformer+framework&rft.jtitle=PeerJ.+Computer+science&rft.au=Chang%2C+Wenjing&rft.au=Guo%2C+Mengyu&rft.au=Luo%2C+Junwei&rft.date=2024-08-08&rft.issn=2376-5992&rft.eissn=2376-5992&rft.volume=10&rft.spage=e2169&rft_id=info:doi/10.7717%2Fpeerj-cs.2169&rft.externalDBID=n%2Fa&rft.externalDocID=10_7717_peerj_cs_2169
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2376-5992&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2376-5992&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2376-5992&client=summon