A Validation Methodology for XAI Decision Support Systems Against Relational Domain Properties
ABSTRACT The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a pervasiveness has led to changes in how AI is perceived, strengthening discussions on its societal consequences. Thus, a new class of requirements for...
Gespeichert in:
| Veröffentlicht in: | Journal of software : evolution and process Jg. 37; H. 10 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Chichester
Wiley Subscription Services, Inc
01.10.2025
|
| Schlagworte: | |
| ISSN: | 2047-7473, 2047-7481 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | ABSTRACT
The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a pervasiveness has led to changes in how AI is perceived, strengthening discussions on its societal consequences. Thus, a new class of requirements for AI‐based solutions emerged. Broadly speaking, those on “explainability” aim to provide a transparent representation of the (often opaque) reasoning method that an AI‐based solution uses when prompted. This work presents a methodology for validating a class of explainable AI (XAI) models, called deterministic rule‐based models, which are used for expressing an explainable approximation of classifiers based on machine learning. The validation methodology combines logical deduction with constraint‐based reasoning in numerical domains, and it either succeeds or returns quantitative estimations of the invalid deviations found. This information allows us to assess the correctness of an XAI model, or in the case of deviations, to evaluate if it still can be deemed acceptable. The validation methodology has been applied to a simulation‐based study where the decision‐making process copes with the spread of SARS‐COV‐2 inside a railway station. The considered case study is a controlled but nontrivial example that shows the overall applicability of the methodology. |
|---|---|
| AbstractList | The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a pervasiveness has led to changes in how AI is perceived, strengthening discussions on its societal consequences. Thus, a new class of requirements for AI‐based solutions emerged. Broadly speaking, those on “explainability” aim to provide a transparent representation of the (often opaque) reasoning method that an AI‐based solution uses when prompted. This work presents a methodology for validating a class of explainable AI (XAI) models, called deterministic rule‐based models, which are used for expressing an explainable approximation of classifiers based on machine learning. The validation methodology combines logical deduction with constraint‐based reasoning in numerical domains, and it either succeeds or returns quantitative estimations of the invalid deviations found. This information allows us to assess the correctness of an XAI model, or in the case of deviations, to evaluate if it still can be deemed acceptable. The validation methodology has been applied to a simulation‐based study where the decision‐making process copes with the spread of SARS‐COV‐2 inside a railway station. The considered case study is a controlled but nontrivial example that shows the overall applicability of the methodology. ABSTRACT The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a pervasiveness has led to changes in how AI is perceived, strengthening discussions on its societal consequences. Thus, a new class of requirements for AI‐based solutions emerged. Broadly speaking, those on “explainability” aim to provide a transparent representation of the (often opaque) reasoning method that an AI‐based solution uses when prompted. This work presents a methodology for validating a class of explainable AI (XAI) models, called deterministic rule‐based models, which are used for expressing an explainable approximation of classifiers based on machine learning. The validation methodology combines logical deduction with constraint‐based reasoning in numerical domains, and it either succeeds or returns quantitative estimations of the invalid deviations found. This information allows us to assess the correctness of an XAI model, or in the case of deviations, to evaluate if it still can be deemed acceptable. The validation methodology has been applied to a simulation‐based study where the decision‐making process copes with the spread of SARS‐COV‐2 inside a railway station. The considered case study is a controlled but nontrivial example that shows the overall applicability of the methodology. |
| Author | De Angelis, Emanuele Proietti, Maurizio Mongelli, Maurizio De Angelis, Guglielmo |
| Author_xml | – sequence: 1 givenname: Emanuele surname: De Angelis fullname: De Angelis, Emanuele organization: IASI‐CNR – sequence: 2 givenname: Guglielmo orcidid: 0000-0002-1076-0076 surname: De Angelis fullname: De Angelis, Guglielmo email: guglielmo.deangelis@iasi.cnr.it organization: IASI‐CNR – sequence: 3 givenname: Maurizio surname: Mongelli fullname: Mongelli, Maurizio organization: IEIIT‐CNR – sequence: 4 givenname: Maurizio surname: Proietti fullname: Proietti, Maurizio organization: IASI‐CNR |
| BookMark | eNp1kMtOwzAQRS1UJErpgj-wxIpFW7_iJMuo5VGpFagFxArLie2SKomDnQrl70kbxI7ZzGjm3KvRvQSDylYagGuMphghMvOlm4YIBewMDAli4SRkER78zSG9AGPv96grTjosGIKPBL7JIleyyW0F17r5tMoWdtdCYx18T5ZwobPcH4_bQ11b18Bt6xtdepjsZF75Bm50cVLLAi5s2e3gs7O1dk2u_RU4N7LwevzbR-D1_u5l_jhZPT0s58lqkpGYsQlNAxIToxEJJctSGWlFU6ywYrEyUZCmzLDMqEhmkhsUUc6xJNwwqiLMaWboCNz0vrWzXwftG7G3B9e95AUlPOAYoyDuqNueypz13mkjapeX0rUCI3FMUHQJilOCHTvr2e-80O3_oNiuN73iB1lgdLo |
| Cites_doi | 10.1007/978-3-540-78800-3_24 10.1016/J.COMCOM.2021.06.026 10.1145/1592434.1592438 10.1109/MS.1984.233702 10.1017/S1471068411000482 10.1007/978-3-642-21437-0_17 10.1109/TAI.2023.3323923 10.1109/TSMCB.2002.999805 10.1109/AITest58265.2023.00010 10.1007/978-3-319-23534-9_2 10.3389/fdata.2021.688969 10.1007/11731177_4 10.1016/0743‐1066(94)90033‐7 10.1145/2939672.2939778 10.1007/978-3-319-63387-9_5 10.1007/978-3-662-53413-7_8 10.1145/3236009 10.1016/j.jss.2022.111231 10.1145/2480362.2480713 10.1145/3143561 10.3390/make3030032 10.1145/3555803 10.1145/3583558 10.1145/41625.41635 10.1109/TAI.2024.3439048 10.1561/2500000051 10.1007/s10664‐024‐10565‐2 10.1109/TSE.2016.2532875 10.1007/978-1-4615-7288-6 10.1017/S1471068411000494 10.1007/978-3-642-83189-8 10.1017/S1471068421000211 10.1017/S1471068417000497 10.1007/978-981-19-6814-3 |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s). Journal of Software: Evolution and Process published by John Wiley & Sons Ltd. 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2025 The Author(s). Journal of Software: Evolution and Process published by John Wiley & Sons Ltd. – notice: 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 24P AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1002/smr.70054 |
| DatabaseName | Wiley Online Library Open Access CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts CrossRef |
| Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2047-7481 |
| EndPage | n/a |
| ExternalDocumentID | 10_1002_smr_70054 SMR70054 |
| Genre | article |
| GrantInformation_xml | – fundername: Gruppo Nazionale per il Calcolo Scientifico INdAM – fundername: POR FESR LAZIO 2014‐2020 – GRUPPI DI RICERCA 2020 funderid: OPENNESS (N. A0375‐2020‐36616) – fundername: Italian Recovery and Resilience Plan funderid: Future Artificial Intelligence Research (FAIR) (N. PE0000013) |
| GroupedDBID | .3N .4S .GA .Y3 05W 0R~ 10A 1OC 24P 31~ 33P 3SF 50Z 52O 52U 8-0 8-1 8-3 8-4 8-5 930 A03 AAESR AAEVG AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCUV ABPVW ACAHQ ACBWZ ACCZN ACPOU ACRPL ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADMLS ADNMO ADOZA ADXAS ADZMN AEIGN AEIMD AEUYR AEYWJ AFBPY AFFPM AFGKR AFWVQ AFZJQ AGHNM AGQPQ AGYGG AHBTC AITYG AIURR AJXKR ALMA_UNASSIGNED_HOLDINGS ALVPJ AMBMR AMYDB ARCSS ATUGU AUFTA AZBYB AZFZN BAFTC BDRZF BHBCM BMNLL BMXJE BRXPI BY8 D-E D-F DCZOG DPXWK DR2 DRFUL DRSTM EBS EDO EJD F00 F01 F04 G-S G.N GODZA HGLYW HZ~ I-F LATKE LEEKS LH4 LITHE LOXES LUTES LW6 LYRES MEWTI MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 O66 O9- P2W P2X PQQKQ Q.N Q11 QB0 R.K ROL SUPJJ TUS W8V W99 WBKPD WIH WIK WOHZO WXSBR WYISQ WZISG ~WT AAYXX CITATION O8X 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c2944-3b5292fe027a4cba8ed3b1d1d49df85bb4f4cfd8aca6f083661a26f43d8163cf3 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001605462200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2047-7473 |
| IngestDate | Tue Oct 28 04:43:03 EDT 2025 Sat Nov 29 07:03:41 EST 2025 Tue Oct 28 09:52:34 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Language | English |
| License | Attribution |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2944-3b5292fe027a4cba8ed3b1d1d49df85bb4f4cfd8aca6f083661a26f43d8163cf3 |
| Notes | This work was supported by the project OPENNESS (N. A0375‐2020‐36616) funded by POR FESR LAZIO 2014‐2020 – GRUPPI DI RICERCA 2020, Future Artificial Intelligence Research (FAIR) (N. PE0000013) funded by Italian Recovery and Resilience Plan, and Gruppo Nazionale per il Calcolo Scientifico INdAM. Funding ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-1076-0076 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fsmr.70054 |
| PQID | 3265611059 |
| PQPubID | 2034650 |
| PageCount | 21 |
| ParticipantIDs | proquest_journals_3265611059 crossref_primary_10_1002_smr_70054 wiley_primary_10_1002_smr_70054_SMR70054 |
| PublicationCentury | 2000 |
| PublicationDate | October 2025 2025-10-00 20251001 |
| PublicationDateYYYYMMDD | 2025-10-01 |
| PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Chichester |
| PublicationPlace_xml | – name: Chichester |
| PublicationTitle | Journal of software : evolution and process |
| PublicationYear | 2025 |
| Publisher | Wiley Subscription Services, Inc |
| Publisher_xml | – name: Wiley Subscription Services, Inc |
| References | 2021; 7 2009; 41 2021; 4 2023; 55 2021; 3 2011 2002; 32 2008 2024; 30 2006 1972 2024 2022; 22 2012; 12 2018; 18 2022; 187 2023 2021; 179 2024; 5 1994; 19 2022 2021 2020 1984; 1 1987 2019 2016; 42 2018 2017 2016 2018; 51 2015 2013 2018; 31 e_1_2_15_21_1 e_1_2_15_42_1 e_1_2_15_40_1 e_1_2_15_3_1 e_1_2_15_29_1 e_1_2_15_27_1 e_1_2_15_48_1 e_1_2_15_25_1 e_1_2_15_46_1 e_1_2_15_23_1 e_1_2_15_44_1 e_1_2_15_9_1 e_1_2_15_7_1 e_1_2_15_5_1 Lundberg S. M. (e_1_2_15_39_1) 2017 e_1_2_15_10_1 e_1_2_15_31_1 e_1_2_15_18_1 e_1_2_15_16_1 e_1_2_15_37_1 e_1_2_15_50_1 e_1_2_15_14_1 e_1_2_15_35_1 e_1_2_15_52_1 e_1_2_15_33_1 Enderton H. (e_1_2_15_22_1) 1972 e_1_2_15_19_1 e_1_2_15_20_1 e_1_2_15_43_1 e_1_2_15_41_1 Bohanec M. (e_1_2_15_12_1) 2021 e_1_2_15_28_1 e_1_2_15_2_1 e_1_2_15_26_1 e_1_2_15_24_1 e_1_2_15_47_1 e_1_2_15_45_1 e_1_2_15_8_1 Singh G. (e_1_2_15_49_1) 2018 e_1_2_15_6_1 e_1_2_15_4_1 Ribeiro M. T. (e_1_2_15_38_1) 2018 e_1_2_15_32_1 e_1_2_15_30_1 e_1_2_15_17_1 e_1_2_15_15_1 e_1_2_15_13_1 e_1_2_15_36_1 e_1_2_15_51_1 e_1_2_15_11_1 e_1_2_15_34_1 e_1_2_15_53_1 |
| References_xml | – volume: 32 start-page: 281 issue: 3 year: 2002 end-page: 295 article-title: A Framework for Validation of Rule‐Based Systems publication-title: IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) – start-page: 191 year: 2021 end-page: 211 – volume: 4 year: 2021 article-title: Principles and Practice of Explainable Machine Learning publication-title: Frontiers in Big Data – volume: 18 start-page: 126 issue: 2 year: 2018 end-page: 166 article-title: Predicate Pairing for Program Verification publication-title: Theory and Practice of Logic Programming – volume: 5 start-page: 2627 issue: 6 year: 2024 end-page: 2637 article-title: Rule‐Based Out‐of‐Distribution Detection publication-title: IEEE Transactions on Artificial Intelligence – start-page: 4768 year: 2017 end-page: 4777 – volume: 187 year: 2022 article-title: Discovering Boundary Values of Feature‐Based Machine Learning Classifiers Through Exploratory Datamorphic Testing publication-title: Journal of Systems and Software – year: 1987 – volume: 31 year: 2018 – start-page: 337 year: 2008 end-page: 340 – year: 2024 – start-page: 1 year: 2023 end-page: 8 – start-page: 200 year: 2011 end-page: 214 – start-page: 97 year: 2017 end-page: 117 – volume: 3 start-page: 615 issue: 3 year: 2021 end-page: 661 article-title: Classification of Explainable Artificial Intelligence Methods Through Their Output Formats publication-title: Machine Learning and Knowledge Extraction – volume: 7 start-page: 1 issue: 1–2 year: 2021 end-page: 157 article-title: Introduction to Neural Network Verification publication-title: Foundations and Trends in Programming Languages – start-page: 147 year: 2016 end-page: 169 – volume: 30 start-page: 18 issue: 1 year: 2024 article-title: How Do ML Practitioners Perceive Explainability? An Interview Study of Practices and Challenges publication-title: Empirical Software Engineering – start-page: 24 year: 2015 end-page: 51 – volume: 42 start-page: 805 issue: 9 year: 2016 end-page: 824 article-title: A Survey on Metamorphic Testing publication-title: IEEE Transactions on Software Engineering – start-page: 23 year: 2006 end-page: 30 – volume: 51 start-page: 1 issue: 1 year: 2018 end-page: 27 article-title: Metamorphic Testing: A Review of Challenges and Opportunities publication-title: ACM Computing Surveys – volume: 12 start-page: 35 issue: 1–2 year: 2012 end-page: 66 article-title: SICStus Prolog—The First 25 Years publication-title: Theory and Practice of Logic Programming – volume: 51 start-page: 1 issue: 5 year: 2018 end-page: 42 article-title: A Survey of Methods for Explaining Black Box Models publication-title: ACM Computing Surveys – volume: 55 start-page: 1 issue: 13s year: 2023 end-page: 42 article-title: From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI publication-title: ACM Computing Surveys – volume: 179 start-page: 166 year: 2021 end-page: 174 article-title: Design of Countermeasure to Packet Falsification in Vehicle Platooning by Explainable Artificial Intelligence publication-title: Computer Communications – volume: 41 start-page: 21:1 issue: 4 year: 2009 end-page: 21:54 article-title: Software Model Checking publication-title: ACM Computing Surveys – volume: 22 start-page: 974 issue: 6 year: 2022 end-page: 1042 article-title: Analysis and Transformation of Constrained Horn Clauses for Program Verification publication-title: Theory and Practice of Logic Programming – year: 2022 – year: 2020 – year: 2023 – year: 1972 – volume: 12 start-page: 67 issue: 1–2 year: 2012 end-page: 96 article-title: SWI‐Prolog publication-title: Theory and Practice of Logic Programming – start-page: 1893 year: 2013 end-page: 1899 – volume: 19 start-page: 503 issue: 20 year: 1994 end-page: 581 article-title: Constraint Logic Programming: A Survey publication-title: Journal of Logic Programming – volume: 1 start-page: 75 issue: 1 year: 1984 end-page: 88 article-title: Verifying and Validating Software Requirements and Design Specifications publication-title: IEEE Software – start-page: 1527 year: 2018 end-page: 1535 – volume: 55 start-page: 1 issue: 9 year: 2023 end-page: 46 article-title: Trustworthy AI: From Principles to Practices publication-title: ACM Computing Surveys – start-page: 1135 year: 2016 end-page: 1144 – year: 2019 – volume: 5 start-page: 4310 issue: 9 year: 2024 end-page: 4314 article-title: From Explainable Artificial Intelligence (xAI) to Understandable Artificial Intelligence (uAI) publication-title: IEEE Transactions on Artificial Intelligence – start-page: 111 year: 1987 end-page: 119 – ident: e_1_2_15_32_1 – ident: e_1_2_15_53_1 doi: 10.1007/978-3-540-78800-3_24 – ident: e_1_2_15_46_1 – ident: e_1_2_15_35_1 doi: 10.1016/J.COMCOM.2021.06.026 – volume-title: A Mathematical Introduction to Logic year: 1972 ident: e_1_2_15_22_1 – ident: e_1_2_15_4_1 – ident: e_1_2_15_16_1 doi: 10.1145/1592434.1592438 – ident: e_1_2_15_37_1 doi: 10.1109/MS.1984.233702 – ident: e_1_2_15_26_1 doi: 10.1017/S1471068411000482 – ident: e_1_2_15_31_1 – start-page: 1527 volume-title: Proceedings of the AAAI Conference on Artificial Intelligence year: 2018 ident: e_1_2_15_38_1 – start-page: 191 volume-title: From Data and Models to Decision Support Systems: Lessons and Advice for the Future year: 2021 ident: e_1_2_15_12_1 – ident: e_1_2_15_27_1 doi: 10.1007/978-3-642-21437-0_17 – ident: e_1_2_15_36_1 doi: 10.1109/TAI.2023.3323923 – ident: e_1_2_15_41_1 doi: 10.1109/TSMCB.2002.999805 – ident: e_1_2_15_29_1 – ident: e_1_2_15_3_1 – ident: e_1_2_15_28_1 – ident: e_1_2_15_47_1 doi: 10.1109/AITest58265.2023.00010 – ident: e_1_2_15_9_1 – ident: e_1_2_15_17_1 doi: 10.1007/978-3-319-23534-9_2 – ident: e_1_2_15_15_1 doi: 10.3389/fdata.2021.688969 – volume-title: Advances in Neural Information Processing Systems year: 2018 ident: e_1_2_15_49_1 – ident: e_1_2_15_21_1 doi: 10.1007/11731177_4 – ident: e_1_2_15_20_1 doi: 10.1016/0743‐1066(94)90033‐7 – ident: e_1_2_15_7_1 doi: 10.1145/2939672.2939778 – ident: e_1_2_15_33_1 – ident: e_1_2_15_48_1 doi: 10.1007/978-3-319-63387-9_5 – ident: e_1_2_15_51_1 doi: 10.1007/978-3-662-53413-7_8 – ident: e_1_2_15_8_1 doi: 10.1145/3236009 – ident: e_1_2_15_44_1 doi: 10.1016/j.jss.2022.111231 – ident: e_1_2_15_11_1 doi: 10.1145/2480362.2480713 – ident: e_1_2_15_43_1 doi: 10.1145/3143561 – ident: e_1_2_15_14_1 doi: 10.3390/make3030032 – ident: e_1_2_15_6_1 doi: 10.1145/3555803 – ident: e_1_2_15_13_1 doi: 10.1145/3583558 – ident: e_1_2_15_30_1 – ident: e_1_2_15_34_1 – ident: e_1_2_15_2_1 – ident: e_1_2_15_19_1 doi: 10.1145/41625.41635 – ident: e_1_2_15_5_1 doi: 10.1109/TAI.2024.3439048 – ident: e_1_2_15_45_1 doi: 10.1561/2500000051 – ident: e_1_2_15_40_1 doi: 10.1007/s10664‐024‐10565‐2 – ident: e_1_2_15_42_1 doi: 10.1109/TSE.2016.2532875 – ident: e_1_2_15_24_1 doi: 10.1007/978-1-4615-7288-6 – ident: e_1_2_15_25_1 doi: 10.1017/S1471068411000494 – ident: e_1_2_15_10_1 – ident: e_1_2_15_23_1 doi: 10.1007/978-3-642-83189-8 – start-page: 4768 volume-title: NIPS'17 year: 2017 ident: e_1_2_15_39_1 – ident: e_1_2_15_18_1 doi: 10.1017/S1471068421000211 – ident: e_1_2_15_52_1 doi: 10.1017/S1471068417000497 – ident: e_1_2_15_50_1 doi: 10.1007/978-981-19-6814-3 |
| SSID | ssj0000620545 |
| Score | 2.334107 |
| Snippet | ABSTRACT
The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a... The global adoption of artificial intelligence (AI) has increased dramatically in recent years, becoming commonplace in many fields. Such a pervasiveness has... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Index Database Publisher |
| SubjectTerms | Artificial intelligence constraint logic programming Decision support systems Deviation Explainable artificial intelligence Machine learning Methodology Railway stations Reasoning rule‐based classifier validation |
| Title | A Validation Methodology for XAI Decision Support Systems Against Relational Domain Properties |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fsmr.70054 https://www.proquest.com/docview/3265611059 |
| Volume | 37 |
| WOSCitedRecordID | wos001605462200001&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: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 2047-7481 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000620545 issn: 2047-7473 databaseCode: DRFUL dateStart: 20120101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3NT8IwGMbfIHjwIn5GFEljPHiZbF23dfG0iEQTIASFcHJp185wAAxD_37bbgM9mJh4W7buI23f9bd37fMAXFOJpQwJ0b_-mUWEzS0qQmHZwk6xk_gJNaveJ71gMKDTaTiswF25FibXh9gk3HRkmPe1DnDGs_ZWNDSbr24DTRw7UHMcl2rfBkyGmwSL7WN1UE9hxFqNQGGzWyoL2bi9OfvneLSFzO-oasaabv1fT3kA-wVioijvE4dQkYsjqJf2DaiI5mN4jdBEUXhuqoT6xkraJNmRAlk0jZ5QpzDgQdr7U3E6KvTNUfTGZoorUTmVTt2us5yrfWiok_srrdJ6AuPuw8v9o1XYLVgJ1q3lcg-HOJXqQ5WRhDMqhcsd4QgSipR6nJOUJKmgLGF-qkWtfYdhPyWuoArqktQ9hepiuZBngNRBBSYeCynjhPuEeYHkXJV2ZRAIIhtwVVZ6_J6rasS5fjKOVY3FpsYa0CybIy4CK4sVbSri01DYgBtT8b9fIH7uj8zG-d-LXsAe1g6_ZrpeE6rr1Ye8hN3kcz3LVi3Tw1pQ64y6494XqP7VrA |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3PT8IwFMdfUEz04m8j_myMBy_T0ZWtS7wQkUAEQhAIJ5d27QwHwID69_vabaAHExNvy9b9yOt762dv7fcBXHNNtQ4ZM7_-hcOUKx2uQuW4yk1oOfZjble9D1tBp8NHo7BbgPt8LUyqD7FMuJnIsO9rE-AmIX23Ug1dTOa3gUGONSgydCP072KtVx-0ljkW16d42MxipEaQAMnZy8WFXHq3PP_nkLTizO-0aoeb-s7_HnQXtjPMJNXUL_agoKf7sJOXcCBZRB_AS5UMkcTTwkqkbctJ20Q7QZglo2qT1LIiPMTU_0RWJ5nGOam-ijGyJcmn0-HtarMJ7iNdk-CfG6XWQxjUH_sPDScrueDE1PSYJys0pInGj1XBYim4Vp4sq7JioUp4RUqWsDhRXMTCT4ywtV8W1E-YpziCXZx4R7A-nU31MRA8iHBSESEXkkmfiUqgpcTWng4CxXQJrnKrR2-pskaUaijTCC0WWYuV4CzvjygLrkWExInUZ8CwBDfW8r9fIHpu9-zGyd-bXsJmo99uRa1m5-kUtqip-Gun753B-vv8Q5_DRvz5Pl7MLzKH-wKsStmS |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3NT8IwGMbfIBjjRfyMKGpjPHiZjK5sXeKFiEQiEIJCOLm0a2s48BFA_37bbgM9mJh4W7buI23f9bd37fMA3FCJpQwJMb_-mUOEyx0qQuG4wlW4Gvsxtaveh-2g26WjUdjLwX22FibRh1gn3Exk2Pe1CXA5F6qyUQ1dThZ3gUGOLSgQYyKTh0Kj3xy01zkW18f6sJnFiI0ggSZnLxMXcnFlff7PIWnDmd9p1Q43zeL_HnQf9lLMRPWkXxxATk4PoZhZOKA0oo_grY6GmsQTYyXUsXbSNtGONMyiUb2FGqkJDzL-n5rVUapxjurvbKzZEmXT6fTtGrOJ3od6JsG_MEqtxzBoPr4-PDmp5YITY9NiHq_hECupP1YZiTmjUni8KqqChELRGudEkVgJymLmKyNs7VcZ9hXxBNVgFyvvBPLT2VSeAtIHNZzUWEgZJ9wnrBZIznVpTwaBILIE11mtR_NEWSNKNJRxpGsssjVWgnLWHlEaXMtIE6emPgOGJbi1Nf_7BaKXTt9unP296BXs9BrNqN3qPp_DLjaGv3b2Xhnyq8WHvIDt-HM1Xi4u0_72BXCj2Q0 |
| 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=A+Validation+Methodology+for+XAI+Decision+Support+Systems+Against+Relational+Domain+Properties&rft.jtitle=Journal+of+software+%3A+evolution+and+process&rft.au=De%C2%A0Angelis%2C+Emanuele&rft.au=De%C2%A0Angelis%2C+Guglielmo&rft.au=Mongelli%2C+Maurizio&rft.au=Proietti%2C+Maurizio&rft.date=2025-10-01&rft.issn=2047-7473&rft.eissn=2047-7481&rft.volume=37&rft.issue=10&rft.epage=n%2Fa&rft_id=info:doi/10.1002%2Fsmr.70054&rft.externalDBID=10.1002%252Fsmr.70054&rft.externalDocID=SMR70054 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2047-7473&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2047-7473&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2047-7473&client=summon |