LLM-based program analysis for source codes, abstract syntax trees and webassembly instructions

The advancement of Web3.0 technology has brought about a urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research need a unified solution for various cross-language program. Moreover, the previous studies regard the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Cluster computing Jg. 28; H. 14; S. 892
Hauptverfasser:	Deng, Liangjun, Zhong, Qi, Qiu, Yao, Chen, Jingxue, Lei, Hang, Yang, Shunkun, Zhou, Liming, Cheng, Hongyuan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.11.2025 Springer Nature B.V
Schlagworte:	Accuracy Codes Computer Communication Networks Computer Science Deep learning Defects Edge computing Embedding Internet of Things Large language models Medical research Natural language Natural language processing Neural networks Operating Systems Processor Architectures Program verification (computers) Programming languages Security Semantics Software engineering Software reliability Source code Syntax Webassembly Group key agreement Program analysis Blockchain
ISSN:	1386-7857, 1573-7543
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	The advancement of Web3.0 technology has brought about a urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research need a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions are challenging to represent and identify. This paper proposes three methods for extracting structural information to demonstrate that the underlying principles of source code and instructions align with those of an abstract syntax tree. These methods include (1) embedding program instruction files directly into natural language, (2) embedding formatted source code into natural language, and (3) embedding misformatted, non-compilable source code into natural language. We train large-scale language models (LLMs) to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1%. Our study also suggests a practical approach of plain text embedding using a 7.65 billion LLM. Interestingly, misformatted source codes are readable to humans but un-compilable, and the accuracy remains above 98.63%. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions.
AbstractList	The advancement of Web3.0 technology has brought about a urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research need a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions are challenging to represent and identify. This paper proposes three methods for extracting structural information to demonstrate that the underlying principles of source code and instructions align with those of an abstract syntax tree. These methods include (1) embedding program instruction files directly into natural language, (2) embedding formatted source code into natural language, and (3) embedding misformatted, non-compilable source code into natural language. We train large-scale language models (LLMs) to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1%. Our study also suggests a practical approach of plain text embedding using a 7.65 billion LLM. Interestingly, misformatted source codes are readable to humans but un-compilable, and the accuracy remains above 98.63%. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions. The advancement of Web3.0 technology has brought about a urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research need a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions are challenging to represent and identify. This paper proposes three methods for extracting structural information to demonstrate that the underlying principles of source code and instructions align with those of an abstract syntax tree. These methods include (1) embedding program instruction files directly into natural language, (2) embedding formatted source code into natural language, and (3) embedding misformatted, non-compilable source code into natural language. We train large-scale language models (LLMs) to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1%. Our study also suggests a practical approach of plain text embedding using a 7.65 billion LLM. Interestingly, misformatted source codes are readable to humans but un-compilable, and the accuracy remains above 98.63%. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions.
ArticleNumber	892
Author	Qiu, Yao Lei, Hang Cheng, Hongyuan Zhong, Qi Deng, Liangjun Yang, Shunkun Zhou, Liming Chen, Jingxue
Author_xml	– sequence: 1 givenname: Liangjun orcidid: 0009-0005-3771-7114 surname: Deng fullname: Deng, Liangjun organization: School of Information and Software Engineering, University of Electronic Science and Technology of China – sequence: 2 givenname: Qi surname: Zhong fullname: Zhong, Qi organization: Faculty of Data Science, City University of Macau – sequence: 3 givenname: Yao surname: Qiu fullname: Qiu, Yao organization: Ningbo Polytechnic College – sequence: 4 givenname: Jingxue surname: Chen fullname: Chen, Jingxue organization: School of Mathematical and Physical Sciences, University of Technology Sydney – sequence: 5 givenname: Hang surname: Lei fullname: Lei, Hang organization: School of Information and Software Engineering, University of Electronic Science and Technology of China – sequence: 6 givenname: Shunkun surname: Yang fullname: Yang, Shunkun organization: Kash Institute of Electronics and Information Industry of China – sequence: 7 givenname: Liming surname: Zhou fullname: Zhou, Liming organization: School of Information and Software Engineering, University of Electronic Science and Technology of China – sequence: 8 givenname: Hongyuan surname: Cheng fullname: Cheng, Hongyuan email: chenghongyuan@lyu.edu.cn organization: School of Information Science and Engineering, Linyi University
BookMark	eNp9kE9LAzEQxYNUsK1-AU8Br0aT7GaTHKX4D1a86Dkk2WzZ0u7WTErdb290BW8ehhmY9x4zvwWa9UMfELpk9IZRKm-BUaEqQrkgVAghyfEEzZmQBZGiLGZ5LvJaKiHP0AJgQynVkus5MnX9QpyF0OB9HNbR7rDt7XaEDnA7RAzDIfqA_dAEuMbWQYrWJwxjn-wnTjEEyIYGH0MOgbBz2xF3fVYdfOqGHs7RaWu3EC5--xK9P9y_rZ5I_fr4vLqrieeSJ8Kco4p7W5a0ZIUWwblWC8WqqmqVbB1vlLOW21C6hgrO20orqr1loXGysqxYoqspN3_xcQiQzCZfnj8BU3AhdC6ls4pPKh8HgBhas4_dzsbRMGq-QZoJpMkgzQ9Ic8ymYjJBFvfrEP-i_3F9ATtQehU
Cites_doi	10.3390/electronics12234749 10.1145/3442381.3450138 10.1145/3297858.3304068 10.1609/aaai.v30i1.10139 10.1109/ICCVE45908.2019.8965092 10.1109/TITS.2019.2926042 10.1016/j.aiopen.2023.08.012 10.1109/ICSE.2019.00086 10.1007/s10489-023-05171-6 10.1145/2970276.2970326 10.1109/JIOT.2024.3393122 10.1016/j.compag.2018.02.016 10.48550/ARXIV.2204.06745 10.18653/v1/2020.findings-emnlp.139 10.1109/MWC.2018.1700364 10.1145/3597503.3639187 10.1007/s10489-021-02894-2 10.1016/j.knosys.2024.111909 10.18653/v1/P16-2022 10.1109/ACCESS.2019.2900462 10.24963/ijcai.2017/423 10.1109/ACCESS.2024.3389497 10.1109/JSAC.2023.3310094 10.1109/TCC.2024.3372598 10.1016/j.cose.2022.102914 10.1145/2884781.2884877 10.1007/978-1-4842-7496-5 10.1145/3679013 10.1109/JSYST.2023.3264773 10.1016/j.jss.2007.03.004
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
Copyright_xml	– notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
DBID	AAYXX CITATION JQ2
DOI	10.1007/s10586-025-05557-w
DatabaseName	CrossRef ProQuest Computer Science Collection
DatabaseTitle	CrossRef ProQuest Computer Science Collection
DatabaseTitleList	ProQuest Computer Science Collection
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	1573-7543
ExternalDocumentID	10_1007_s10586_025_05557_w
GrantInformation_xml	– fundername: Research on digital twin collaboration technology for dynamic assembly of human-computer collaboration grantid: 2024Z296
GroupedDBID	-~C .86 .DC .VR 06D 0R~ 0VY 1N0 203 29B 2J2 2JN 2JY 2KG 2LR 2~H 30V 4.4 406 408 409 40D 40E 5GY 5VS 67Z 6NX 78A 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAJBT AAJKR AANZL AAPKM AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN ABAKF ABBBX ABBRH ABBXA ABDBE ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABWNU ABXPI ACAOD ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADKFA ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEFQL AEGAL AEGNC AEJHL AEJRE AEMSY AEOHA AEPYU AETLH AEVLU AEXYK AFDZB AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYJHY AZFZN B-. BA0 BGNMA BSONS CS3 CSCUP DDRTE DL5 DNIVK DPUIP EBLON EBS EIOEI ESBYG FEDTE FERAY FFXSO FIGPU FNLPD FRRFC FWDCC GGCAI GGRSB GJIRD GNWQR GQ7 GQ8 GXS HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF I09 IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV LAK LLZTM M4Y MA- NB0 NPVJJ NQJWS NU0 O93 O9J OAM P9O PF0 PT4 PT5 QOS R89 R9I RNS ROL RPX RSV S16 S1Z S27 S3B SAP SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 ZMTXR ~A9 -Y2 1SB 2P1 2VQ AAIAL AARHV AAYTO AAYXX ABQSL ABULA ACBXY ADHKG AEBTG AEKMD AFFHD AFGCZ AFKRA AGGDS AGQPQ AHSBF AJBLW ARAPS BDATZ BENPR BGLVJ CAG CCPQU CITATION COF EJD FINBP FSGXE H13 HCIFZ HZ~ IHE K7- N2Q O9- OVD PHGZM PHGZT PQGLB RNI RZC RZE RZK TEORI JQ2
ID	FETCH-LOGICAL-c272t-1bb082ca44041395ebbf9581666f87fb2d8baa2ae4bd0522f69809ca1edb76a13
IEDL.DBID	RSV
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001586153500035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1386-7857
IngestDate	Sat Nov 29 03:45:57 EST 2025 Thu Nov 20 00:51:35 EST 2025 Fri Nov 28 01:10:43 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	14
Keywords	Webassembly Group key agreement Program analysis Blockchain
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c272t-1bb082ca44041395ebbf9581666f87fb2d8baa2ae4bd0522f69809ca1edb76a13
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0005-3771-7114
PQID	3255925589
PQPubID	2043865
ParticipantIDs	proquest_journals_3255925589 crossref_primary_10_1007_s10586_025_05557_w springer_journals_10_1007_s10586_025_05557_w
PublicationCentury	2000
PublicationDate	2025-11-01
PublicationDateYYYYMMDD	2025-11-01
PublicationDate_xml	– month: 11 year: 2025 text: 2025-11-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York – name: Dordrecht
PublicationSubtitle	The Journal of Networks, Software Tools and Applications
PublicationTitle	Cluster computing
PublicationTitleAbbrev	Cluster Comput
PublicationYear	2025
Publisher	Springer US Springer Nature B.V
Publisher_xml	– name: Springer US – name: Springer Nature B.V
References	P Koopman (5557_CR8) 2017; 9 5557_CR9 5557_CR30 5557_CR31 J Guo (5557_CR10) 2019; 21 5557_CR32 5557_CR33 5557_CR34 A Kamilaris (5557_CR1) 2018; 147 5557_CR13 5557_CR35 5557_CR14 5557_CR36 5557_CR3 G Frantzeskou (5557_CR16) 2008; 81 AO Bang (5557_CR2) 2022; 123 G Huang (5557_CR15) 2019; 7 5557_CR37 J Chen (5557_CR4) 2024; 56 5557_CR17 5557_CR39 H Cheng (5557_CR6) 2023; 17 5557_CR18 Q Luo (5557_CR12) 2018; 25 5557_CR19 5557_CR40 J Chen (5557_CR11) 2024; 39 5557_CR41 5557_CR20 5557_CR42 5557_CR21 W Hua (5557_CR25) 2022; 52 5557_CR43 5557_CR22 5557_CR44 5557_CR23 5557_CR45 5557_CR24 5557_CR46 5557_CR47 W Ke (5557_CR5) 2024; 296 D Zheng (5557_CR7) 2024; 54 S Black (5557_CR38) 2022 5557_CR26 5557_CR48 5557_CR27 5557_CR28 5557_CR29
References_xml	– ident: 5557_CR3 doi: 10.3390/electronics12234749 – ident: 5557_CR35 doi: 10.1145/3442381.3450138 – ident: 5557_CR36 doi: 10.1145/3297858.3304068 – ident: 5557_CR22 doi: 10.1609/aaai.v30i1.10139 – ident: 5557_CR13 doi: 10.1109/ICCVE45908.2019.8965092 – ident: 5557_CR24 – volume: 21 start-page: 3135 issue: 8 year: 2019 ident: 5557_CR10 publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2019.2926042 – ident: 5557_CR47 – ident: 5557_CR26 doi: 10.1016/j.aiopen.2023.08.012 – ident: 5557_CR28 – ident: 5557_CR48 doi: 10.1109/ICSE.2019.00086 – volume: 54 start-page: 428 issue: 1 year: 2024 ident: 5557_CR7 publication-title: Appl. Intell. doi: 10.1007/s10489-023-05171-6 – ident: 5557_CR45 – ident: 5557_CR43 – ident: 5557_CR17 doi: 10.1145/2970276.2970326 – ident: 5557_CR14 doi: 10.1109/JIOT.2024.3393122 – ident: 5557_CR40 – volume: 147 start-page: 70 year: 2018 ident: 5557_CR1 publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2018.02.016 – ident: 5557_CR34 – volume: 39 start-page: 100593 year: 2024 ident: 5557_CR11 publication-title: J. Industrial Inform. Integr. – year: 2022 ident: 5557_CR38 publication-title: ARXIV doi: 10.48550/ARXIV.2204.06745 – ident: 5557_CR20 doi: 10.18653/v1/2020.findings-emnlp.139 – volume: 25 start-page: 113 issue: 6 year: 2018 ident: 5557_CR12 publication-title: IEEE Wirel. Commun. doi: 10.1109/MWC.2018.1700364 – ident: 5557_CR29 doi: 10.1145/3597503.3639187 – ident: 5557_CR46 – volume: 52 start-page: 8895 issue: 8 year: 2022 ident: 5557_CR25 publication-title: Appl. Intell. doi: 10.1007/s10489-021-02894-2 – ident: 5557_CR44 – volume: 296 start-page: 111909 year: 2024 ident: 5557_CR5 publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2024.111909 – ident: 5557_CR42 – ident: 5557_CR23 – ident: 5557_CR21 doi: 10.18653/v1/P16-2022 – volume: 7 start-page: 28291 year: 2019 ident: 5557_CR15 publication-title: IEEE Access. doi: 10.1109/ACCESS.2019.2900462 – ident: 5557_CR18 doi: 10.24963/ijcai.2017/423 – ident: 5557_CR27 doi: 10.1109/ACCESS.2024.3389497 – ident: 5557_CR30 doi: 10.1109/JSAC.2023.3310094 – volume: 9 start-page: 90 issue: 1 year: 2017 ident: 5557_CR8 publication-title: IEEE Intell. Transp. Syst. Mag. – ident: 5557_CR37 – ident: 5557_CR41 – ident: 5557_CR9 doi: 10.1109/TCC.2024.3372598 – volume: 123 start-page: 102914 year: 2022 ident: 5557_CR2 publication-title: Computers Secur. doi: 10.1016/j.cose.2022.102914 – ident: 5557_CR19 doi: 10.1145/2884781.2884877 – ident: 5557_CR39 – ident: 5557_CR31 – ident: 5557_CR32 doi: 10.1007/978-1-4842-7496-5 – ident: 5557_CR33 – volume: 56 start-page: 1 issue: 12 year: 2024 ident: 5557_CR4 publication-title: ACM Comput. Surveys doi: 10.1145/3679013 – volume: 17 start-page: 4922 issue: 3 year: 2023 ident: 5557_CR6 publication-title: IEEE Syst. J. doi: 10.1109/JSYST.2023.3264773 – volume: 81 start-page: 447 issue: 3 year: 2008 ident: 5557_CR16 publication-title: J. Syst. Softw. doi: 10.1016/j.jss.2007.03.004
SSID	ssj0009729
Score	2.366196
Snippet	The advancement of Web3.0 technology has brought about a urgent need for ensuring the safety and reliability of the software systems. Program analysis, a...
SourceID	proquest crossref springer
SourceType	Aggregation Database Index Database Publisher
StartPage	892
SubjectTerms	Accuracy Codes Computer Communication Networks Computer Science Deep learning Defects Edge computing Embedding Internet of Things Large language models Medical research Natural language Natural language processing Neural networks Operating Systems Processor Architectures Program verification (computers) Programming languages Security Semantics Software engineering Software reliability Source code Syntax
Title	LLM-based program analysis for source codes, abstract syntax trees and webassembly instructions
URI	https://link.springer.com/article/10.1007/s10586-025-05557-w https://www.proquest.com/docview/3255925589
Volume	28
WOSCitedRecordID	wos001586153500035&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1573-7543 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009729 issn: 1386-7857 databaseCode: RSV dateStart: 19980101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED5BYWChPEWhIA9s1FLzqp0RISqGUiEeVTfLdhypEgREIkr_PWfXUQDBAEOm2Fb0ne374vN9B3AqYx5Jq_LJtOzTOIsyKk0UURtC00aaPHRKTJMRG4_5dJre-KSwsr7tXock3U79Kdkt4fbCbEKtSBWj81VYQ3fHbcGG27tJI7XLXG2yIMLWjCfMp8r8PMZXd9RwzG9hUedthu3_fecWbHp2Sc6X02EbVkyxA-26cgPxC3kXxGh0Ta0Dy4i_oEWkVychyGLJ8kif2Hz3skeksuchuiLloqjkO7GB7BI7ZAT3YCTf5kk9Lsis0aIt9-BheHl_cUV9qQWq0RgVDZRCLqClVQtETpgYpfI0cTHFnLNchRlXUobSxCrrI2XLB4h7qmVgMsUGMoj2oVU8F-YASBAoaUUMtQ5VzFMcGQGxRAm9cZBm_Q6c1YiLl6Wihmi0ky12ArETDjsx70C3Norwq6sUkf0PwoenHejVRmhe_z7a4d-aH8FGaO3oUg-70EIUzTGs67dqVr6euFn3AdqX1AY
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB60CnqxPrFaNQdvGui-utmjiKXitojW0lvIa6Ggq7iLtf_eJM2yKnrQw542GZaZJPNtZuYbgFMWkoAZls9YsA4OZSAxU0GATQhNKKYy3zIxjdN4OCSTSXLrisKKKtu9Cknak_pTsVtETMJshA1JVYxny7ASao9lGPPv7sc11W5se5N5gR4dkyh2pTI_y_jqjmqM-S0sar1Nr_m_79yEDYcu0cViOWzBksq3oVl1bkBuI-8ATdMBNg5MIpeghZhjJ0EaxaLFlT4y9e7FOWLc3IeIEhXzvGTvyASyCz1BIn0Ga_CtnvjjHE1rLtpiFx56V6PLPnatFrDQxiixx7nGAoIZtkCNCSPFeZZENqaYkTjjviScMZ-pkMuOhmxZNyGdRDBPSR53mRfsQSN_ztU-IM_jzJAYCuHzkCRaslaIAUraG3uJ7LTgrNI4fVkwatCaO9nojmrdUas7OmtBuzIKdburoIH5D9IPSVpwXhmhfv27tIO_DT-Btf5okNL0enhzCOu-saktQ2xDQ2tUHcGqeCunxeuxXYEf1JbW6g
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB60inixPrFadQ_e7GLzajZHUYtiLQW19LbsK1DQWEyw9t-7kyakih7EQ07ZHcLMbubbnZlvAE6FzzyBLJ-hEm3qa09TYTyPYghNGWFiN2diGvbCfp-NRtFgoYo_z3YvQ5LzmgZkaUqy84mOzxcK3wKGybMBRcKqkE6XYcXHRHo8rz8MK9rdMO9T5nh2dMiCsCib-VnGV9dU4c1vIdLc83Tr___mTdgoUCe5mC-TLVgyyTbUy44OpNjgO8B7vXuKjk2TInGLiIK1hFh0S-ZX_QTr4NMWERLvSVRG0lmSiQ-CAe7UTtDE_pstKDcv8nlGxhVHbboLT93rx8sbWrRgoMoaKaOOlBYjKIEsghYrBkbKOAryWGPMwli6mkkhXGF8qdsWysWdiLUjJRyjZdgRjrcHteQ1MftAHEcKJDdUypU-i6xkqxAEUNZLO5FuN-Cs1D6fzJk2eMWpjLrjVnc81x2fNqBZGogXuy7lHp6P7MOiBrRKg1Svf5d28LfhJ7A2uOry3m3_7hDWXTRpXp3YhJpVqDmCVfWejdO343wxfgL99N_O
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=LLM-based+program+analysis+for+source+codes%2C+abstract+syntax+trees+and+webassembly+instructions&rft.jtitle=Cluster+computing&rft.au=Deng%2C+Liangjun&rft.au=Zhong%2C+Qi&rft.au=Qiu%2C+Yao&rft.au=Chen%2C+Jingxue&rft.date=2025-11-01&rft.pub=Springer+US&rft.issn=1386-7857&rft.eissn=1573-7543&rft.volume=28&rft.issue=14&rft_id=info:doi/10.1007%2Fs10586-025-05557-w&rft.externalDocID=10_1007_s10586_025_05557_w
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1386-7857&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1386-7857&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1386-7857&client=summon