{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T10:01:20Z","timestamp":1780308080230,"version":"3.54.0"},"reference-count":29,"publisher":"Walter de Gruyter GmbH","issue":"2","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deeply virtual exclusive scattering processes (DVES) serve as precise probes of nucleon quark and gluon distributions in coordinate space. These distributions are derived from generalized parton distributions (GPDs) via Fourier transform relative to proton momentum transfer. QCD factorization theorems enable DVES to be parameterized by Compton form factors (CFFs), which are convolutions of GPDs with perturbatively calculable kernels. Accurate extraction of CFFs from DVCS, benefiting from interference with the Bethe\u2013Heitler (BH) process and a simpler final state structure, is essential for inferring GPDs. This paper focuses on extracting CFFs from DVCS data using a variational autoencoder inverse mapper (VAIM) and its constrained variant (C-VAIM). VAIM is shown to be consistent with Markov Chain Monte Carlo (MCMC) methods in extracting multiple CFF solutions for given kinematics, while C-VAIM effectively captures correlations among CFFs across different kinematic values, providing more constrained solutions. This study represents a crucial first step towards a comprehensive analysis pipeline towards the extraction of GPDs.<\/jats:p>","DOI":"10.1515\/mcma-2026-3007","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:16:52Z","timestamp":1779880612000},"page":"205-219","source":"Crossref","is-referenced-by-count":0,"title":["Variational autoencoder inverse mapper for extraction of Compton form factors: Benchmarks and conditional learning"],"prefix":"10.1515","volume":"32","author":[{"given":"Douglas","family":"Adams","sequence":"first","affiliation":[{"name":"Department of Physics , University of Virginia , Charlottesville , VA 22904 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"MD Fayaz Bin","family":"Hossen","sequence":"additional","affiliation":[{"name":"Department of Computer Science , Old Dominion University , Norfolk , VA 23529 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Bautista","sequence":"additional","affiliation":[{"name":"Department of Physics , University of Virginia , Charlottesville , VA 22904 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gia-Wei","family":"Chern","sequence":"additional","affiliation":[{"name":"Department of Physics , University of Virginia , Charlottesville , VA 22904 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simonetta","family":"Liuti","sequence":"additional","affiliation":[{"name":"Department of Physics , University of Virginia , Charlottesville , VA 22904 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie","family":"Bo\u00ebr","sequence":"additional","affiliation":[{"name":"Department of Physics , Virginia Tech , Blacksburg , VA 24061 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marija","family":"\u010cui\u0107","sequence":"additional","affiliation":[{"name":"Department of Physics , University of Virginia , Charlottesville , VA 22904 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Engelhardt","sequence":"additional","affiliation":[{"name":"Department of Physics , New Mexico State University , Las Cruces , NM 88003 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary R.","family":"Goldstein","sequence":"additional","affiliation":[{"name":"Department of Physics and Astronomy , Tufts University , Medford , MA 02155 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huey-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Physics and Astronomy , Michigan State University , East Lansing , MI 48824 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaohang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science , Old Dominion University , Norfolk , VA 23529 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"2026060109070020987_j_mcma-2026-3007_ref_001","doi-asserted-by":"crossref","unstructured":"M.  Almaeen, Y.  Alanazi, N.  Sato, W.  Melnitchouk, M. P.  Kuchera and Y.  Li,\nVariational autoencoder inverse mapper: An end-to-end deep learning framework for inverse problems,\n2021 International Joint Conference on Neural Networks,\nIEEE Press, Piscataway (2021), 1\u20138.","DOI":"10.1109\/IJCNN52387.2021.9534012"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_002","doi-asserted-by":"crossref","unstructured":"M.  Almaeen, Y.  Alanazi, N.  Sato, W.  Melnitchouk and Y.  Li,\nPoint cloud-based variational autoencoder inverse mappers (PC-VAIM) \u2014 an application on quantum chromodynamics global analysis,\n21st IEEE International Conference on Machine Learning and Applications,\nIEEE Press, Piscataway (2022), 1151\u20131158.","DOI":"10.1109\/ICMLA55696.2022.00187"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_003","doi-asserted-by":"crossref","unstructured":"M.  Almaeen, T.  Alghamdi, B.  Kriesten, D.  Adams, Y.  Li, H.-W.  Lin and S.  Liuti,\nVAIM-CFF: A variational autoencoder inverse mapper solution to Compton form factor extraction from deeply virtual exclusive reactions,\nEur. Phys. J. C 85 (2025), Article No. 499.","DOI":"10.1140\/epjc\/s10052-025-14091-3"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_004","doi-asserted-by":"crossref","unstructured":"A. V.  Belitsky and D.  Mueller,\nExclusive electroproduction revisited: Treating kinematical effects,\nPhys. Rev. D 82 (2010), Article ID 074010.","DOI":"10.1103\/PhysRevD.82.074010"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_005","doi-asserted-by":"crossref","unstructured":"A. V.  Belitsky, D.  Mueller and A.  Kirchner,\nTheory of deeply virtual Compton scattering on the nucleon,\nNucl. Phys. B 629 (2002), 323\u2013392.","DOI":"10.1016\/S0550-3213(02)00144-X"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_006","doi-asserted-by":"crossref","unstructured":"A. V.  Belitsky and A. V.  Radyushkin,\nUnraveling hadron structure with generalized parton distributions,\nPhys. Rep. 418 (2005), 1\u2013387.","DOI":"10.1016\/j.physrep.2005.06.002"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_007","doi-asserted-by":"crossref","unstructured":"D.  Blei, A.  Kucukelbir and J.  McAuliffe,\nVariational inference: A review for statisticians,\nJ. Amer. Statist. Assoc. 112 (2017), no. 518, 859\u2013877.","DOI":"10.1080\/01621459.2017.1285773"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_008","doi-asserted-by":"crossref","unstructured":"V. M.  Braun, A. N.  Manashov and B.  Pirnay,\nFinite-t and target mass corrections to deeply virtual Compton scattering,\nPhys. Rev. Lett. 109 (2012), Article ID 242001.","DOI":"10.1103\/PhysRevLett.109.242001"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_009","doi-asserted-by":"crossref","unstructured":"J. C.  Collins, L.  Frankfurt and M.  Strikman,\nFactorization for hard exclusive electroproduction of mesons in QCD,\nPhys. Rev. D 56 (1997), 2982\u20133006.","DOI":"10.1103\/PhysRevD.56.2982"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_010","doi-asserted-by":"crossref","unstructured":"J. C.  Collins and A.  Freund,\nProof of factorization for deeply virtual Compton scattering in QCD,\nPhys. Rev. D 59 (1999), Article ID 074009.","DOI":"10.1103\/PhysRevD.59.074009"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_011","doi-asserted-by":"crossref","unstructured":"G.  Cybenko,\nApproximation by superpositions of a sigmoidal function,\nMath. Control Signals Systems 2 (1989), no. 4, 303\u2013314.","DOI":"10.1007\/BF02551274"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_012","doi-asserted-by":"crossref","unstructured":"M.  Diehl,\nGeneralized parton distributions with helicity flip,\nEur. Phys. J. C 19 (2001), 485\u2013492.","DOI":"10.1007\/s100520100635"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_013","unstructured":"F.  Georges,\nDeeply virtual Compton scattering cross section at high Bjorken \n                  \n                     \n                        \n                           x\n                           B\n                        \n                     \n                     \n                     {x_{B}}\n                  \n               ,\nPhys. Rev. Lett. 128 (2022), no. 25, Article ID 252002."},{"key":"2026060109070020987_j_mcma-2026-3007_ref_014","doi-asserted-by":"crossref","unstructured":"Y.  Guo, X.  Ji and K.  Shiells,\nHigher-order kinematical effects in deeply virtual Compton scattering,\nJHEP 12 (2021), Paper No. 103.","DOI":"10.1007\/JHEP12(2021)103"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_015","doi-asserted-by":"crossref","unstructured":"G. E.  Hinton and R. R.  Salakhutdinov,\nReducing the dimensionality of data with neural networks,\nScience 313 (2006), no. 5786, 504\u2013507.","DOI":"10.1126\/science.1127647"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_016","doi-asserted-by":"crossref","unstructured":"K.  Hornik, M.  Stinchcombe and H.  White,\nMultilayer feedforward networks are universal approximators,\nNeural Networks 2 (1989), no. 5, 359\u2013366.","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_017","doi-asserted-by":"crossref","unstructured":"X.-D.  Ji,\nGauge-invariant decomposition of nucleon spin,\nPhys. Rev. Lett. 78 (1997), 610\u2013613.","DOI":"10.1103\/PhysRevLett.78.610"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_018","doi-asserted-by":"crossref","unstructured":"J. J.  Kelly,\nSimple parametrization of nucleon form factors,\nPhys. Rev. C 70 (2004), Article ID 068202.","DOI":"10.1103\/PhysRevC.70.068202"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_019","doi-asserted-by":"crossref","unstructured":"D. P.  Kingma and M.  Welling,\nAn introduction to variational autoencoders,\npreprint (2019), https:\/\/arxiv.org\/abs\/1906.02691.","DOI":"10.1561\/9781680836233"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_020","unstructured":"D.  Kingma and M.  Welling,\nAuto-encoding variational Bayes,\nProceedings of the 2nd International Conference on Learning Representations,\nICLR, Banff (2014), http:\/\/arxiv.org\/abs\/1312.6114v10."},{"key":"2026060109070020987_j_mcma-2026-3007_ref_021","unstructured":"B.  Kriesten and S.  Liuti,\nNovel Rosenbluth extraction framework for Compton form factors from deeply virtual exclusive experiments,\npreprint (2020), https:\/\/arxiv.org\/abs\/2011.04484."},{"key":"2026060109070020987_j_mcma-2026-3007_ref_022","doi-asserted-by":"crossref","unstructured":"B.  Kriesten and S.  Liuti,\nTheory of deeply virtual Compton scattering off the unpolarized proton,\nPhys. Rev. D 105 (2022), Article ID 016015.","DOI":"10.1103\/PhysRevD.105.016015"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_023","doi-asserted-by":"crossref","unstructured":"B.  Kriesten, S.  Liuti, L.  Calero-Diaz, D.  Keller, A.  Meyer, G. R.  Goldstein and J. O.  Gonzalez-Hernandez,\nExtraction of generalized parton distribution observables from deeply virtual electron proton scattering experiments,\nPhys. Rev. D 101 (2020), no. 5, Article ID 054021.","DOI":"10.1103\/PhysRevD.101.054021"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_024","doi-asserted-by":"crossref","unstructured":"K.  Kumericki, S.  Liuti and H.  Moutarde,\nGPD phenomenology and DVCS fitting \u2014 entering the high-precision era,\npreprint (2016), https:\/\/arxiv.org\/abs\/1602.02763.","DOI":"10.1140\/epja\/i2016-16157-3"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_025","doi-asserted-by":"crossref","unstructured":"C.  Liu and J.  Zhu,\nGeometry in sampling methods: A review on manifold MCMC and particle-based variational inference methods,\nAdvancements in Bayesian Methods and Implementation,\nHandbook of Statist. 47,\nElsevier, Amsterdam (2022), 239\u2013293.","DOI":"10.1016\/bs.host.2022.07.004"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_026","doi-asserted-by":"crossref","unstructured":"D.  M\u00fcller, D.  Robaschik, B.  Geyer, F.-M.  Dittes and J.  Ho\u0159ej\u0161i,\nWave functions, evolution equations and evolution kernels from light ray operators of QCD,\nFortschr. Phys. 42 (1994), 101\u2013141.","DOI":"10.1002\/prop.2190420202"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_027","unstructured":"T.  O\u2019Malley, E.  Bursztein, J.  Long, F.  Chollet, H.  Jin and L.  Invernizzi,\nKerasTuner,\n(2019), https:\/\/github.com\/keras-team\/keras-tuner."},{"key":"2026060109070020987_j_mcma-2026-3007_ref_028","doi-asserted-by":"crossref","unstructured":"A. V.  Radyushkin,\nNonforward parton distributions,\nPhys. Rev. D 56 (1997), 5524\u20135557.","DOI":"10.1103\/PhysRevD.56.5524"},{"key":"2026060109070020987_j_mcma-2026-3007_ref_029","unstructured":"K.  Sohn, H.  Lee and X.  Yan,\nLearning structured output representation using deep conditional generative models,\nAdvances in Neural Information Processing Systems. Vol. 28,\nACM, New York (2015), 3483\u20133491."}],"container-title":["Monte Carlo Methods and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/mcma-2026-3007\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/mcma-2026-3007\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T09:07:58Z","timestamp":1780304878000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/mcma-2026-3007\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6,1]]},"published-print":{"date-parts":[[2026,6,1]]}},"alternative-id":["10.1515\/mcma-2026-3007"],"URL":"https:\/\/doi.org\/10.1515\/mcma-2026-3007","relation":{},"ISSN":["0929-9629","1569-3961"],"issn-type":[{"value":"0929-9629","type":"print"},{"value":"1569-3961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]}}}