{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:43:39Z","timestamp":1774352619970,"version":"3.50.1"},"reference-count":40,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:00:00Z","timestamp":1773446400000},"content-version":"vor","delay-in-days":72,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>There exists a broad class of networks that connect inputs to outputs. These networks include chemical transformation networks, electrical circuits, municipal water systems, and neural networks. The goals of this paper are to provide a theoretical foundation for evolutionary crossover on this class of graphs and connect crossover to informativeness, a measure of the connectedness of inputs to outputs. Informativeness is defined as a partially informative graph has at least one path from an input to some output, a very informative graph has a path from every input to some output, and a fully informative graph has a path from every input to every output. A neural network with nonzero weights and any number of layers is fully informative. As links are removed (assigned zero weight), it may become very, partially, or not informative (the complement of informativeness is actionability, which is a measure of how connected outputs are from inputs). We define a crossover operation on Input\/Output Directed Graphs (IOD Graphs) in which we find subgraphs with matching sets of forward and backward directed links to \u201cswap.\u201d With this operation, IOD Graphs can be subject to evolutionary computation methods. We show that fully informative parents may yield a noninformative child. We also show that under certain conditions, crossover compatible, partially informative parents yield partially informative children and very informative input parents with partially informative output parents yield very informative children. However, even under these conditions, full informativeness may not be retained. Similar results hold for actionability.<\/jats:p>","DOI":"10.1155\/cplx\/9057003","type":"journal-article","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:24:47Z","timestamp":1773487487000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Preservation of Input\/Output Directed Graph Informativeness Under Crossover"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0874-4437","authenticated-orcid":false,"given":"Andreas Duus","family":"Pape","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6652-7708","authenticated-orcid":false,"given":"J. David","family":"Schaffer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2670-5864","authenticated-orcid":false,"given":"Hiroki","family":"Sayama","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1060-1364","authenticated-orcid":false,"given":"Christoper","family":"Zosh","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2026,3,14]]},"reference":[{"key":"e_1_2_14_1_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-physchem-071119-040123"},{"key":"e_1_2_14_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00369-z"},{"key":"e_1_2_14_3_2","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)0733-9496(2002)128:2(140)"},{"key":"e_1_2_14_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11269-008-9267-3"},{"key":"e_1_2_14_5_2","doi-asserted-by":"crossref","unstructured":"MengX. WongS. H. YuanY. andLuS. Characterizing Flows in Large Wireless Data Networks Proceedings of the 10th Annual International Conference on Mobile Computing and Networking September 2004 Philadelphia PA 174\u2013186.","DOI":"10.1145\/1023720.1023738"},{"key":"e_1_2_14_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63173-9_56"},{"key":"e_1_2_14_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2008.08.004"},{"key":"e_1_2_14_8_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0093825"},{"key":"e_1_2_14_9_2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.99.1.22"},{"key":"e_1_2_14_10_2","doi-asserted-by":"publisher","DOI":"10.3758\/bf03196806"},{"key":"e_1_2_14_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.860134"},{"key":"e_1_2_14_12_2","volume-title":"Ontogeny and Phylogeny","author":"Gould S. J.","year":"1977"},{"key":"e_1_2_14_13_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1952.sp004764"},{"key":"e_1_2_14_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0893-6080(97)00011-7"},{"key":"e_1_2_14_15_2","doi-asserted-by":"crossref","unstructured":"BraunH.andWeisbrodJ. Evolving Neural Feedforward Networks Artificial Neural Nets and Genetic Algorithms: Proceedings of the International Conference April 1993 Innsbruck Austria Springer 25\u201332.","DOI":"10.1007\/978-3-7091-7533-0_5"},{"key":"e_1_2_14_16_2","unstructured":"BraunH.andRaggT. Enzo User Manual and Implementation Guide version 1.0 1997."},{"key":"e_1_2_14_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2012.04.010"},{"key":"e_1_2_14_18_2","article-title":"On the Preservation of Input\/Output Directed Graph Informativeness Under Crossover","volume":"3","author":"Pape A. D.","year":"2024","journal-title":"Social and Information Networks"},{"key":"e_1_2_14_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0378-4371(00)00479-9"},{"key":"e_1_2_14_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.08.014"},{"key":"e_1_2_14_21_2","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_2_14_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"e_1_2_14_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55337-0_5"},{"key":"e_1_2_14_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.03.042"},{"key":"e_1_2_14_25_2","doi-asserted-by":"crossref","unstructured":"UriotT.andIzzoD. Safe Crossover of Neural Networks Through Neuron Alignment Proceedings of the 2020 Genetic and Evolutionary Computation Conference July 2020 Canc\u00fan Mexico 435\u2013443.","DOI":"10.1145\/3377930.3390197"},{"key":"e_1_2_14_26_2","doi-asserted-by":"crossref","unstructured":"SchafferJ. D. WhitleyD. andEshelmanL. J. Combinations of Genetic Algorithms and Neural Networks: A Survey of the State of the Art Proceedings COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks June 1992 Baltimore Maryland IEEE 1\u201337.","DOI":"10.1109\/COGANN.1992.273950"},{"key":"e_1_2_14_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2021.126480"},{"key":"e_1_2_14_28_2","first-page":"163","volume-title":"Online Social Media Analysis and Visualization","author":"Topirceanu A.","year":"2015"},{"key":"e_1_2_14_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1052934.1052938"},{"key":"e_1_2_14_30_2","doi-asserted-by":"publisher","DOI":"10.1137\/040607551"},{"key":"e_1_2_14_31_2","doi-asserted-by":"publisher","DOI":"10.1137\/060664331"},{"key":"e_1_2_14_32_2","doi-asserted-by":"crossref","unstructured":"SallinenS. LuoJ. andRipeanuM. Real-Time Pagerank on Dynamic Graphs Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing June 2023 Orlando FL 239\u2013251.","DOI":"10.1145\/3588195.3593004"},{"key":"e_1_2_14_33_2","volume-title":"Genetic Programming III: Darwinian Invention and Problem Solving","author":"Koza J. R.","year":"1999"},{"key":"e_1_2_14_34_2","volume-title":"The Perceptron, A Perceiving and Recognizing Automaton Project Para","author":"Rosenblatt F.","year":"1957"},{"key":"e_1_2_14_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"e_1_2_14_36_2","first-page":"1","article-title":"Neural Architecture Search: A Survey","volume":"20","author":"Elsken T.","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_14_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2019.2924461"},{"key":"e_1_2_14_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2019.2919608"},{"key":"e_1_2_14_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100894"},{"key":"e_1_2_14_40_2","doi-asserted-by":"crossref","unstructured":"ZophB. VasudevanV. ShlensJ. andLeQ. V. Learning Transferable Architectures for Scalable Image Recognition 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City Utah 8697\u20138710.","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/cplx\/9057003","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/cplx\/9057003","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/cplx\/9057003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T09:51:45Z","timestamp":1774345905000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/cplx\/9057003"}},"subtitle":[],"editor":[{"given":"Simonetta","family":"Primario","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/cplx\/9057003"],"URL":"https:\/\/doi.org\/10.1155\/cplx\/9057003","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"value":"1076-2787","type":"print"},{"value":"1099-0526","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9057003"}}