{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:56:59Z","timestamp":1789628219031,"version":"build-2803163510"},"posted":{"date-parts":[[2026,8,3]]},"group-title":"Molecular Biology","reference-count":63,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,3]]},"abstract":"<jats:p>\n                  In this technical report, we introduce N\n                  <jats:sc>esso<\/jats:sc>\n                  -1, a\n                  <jats:italic>coarse-grained<\/jats:italic>\n                  cofolding framework for binding- affinity prediction. N\n                  <jats:sc>esso<\/jats:sc>\n                  -1 requires\n                  <jats:italic>\u223c<\/jats:italic>\n                  1 second per prediction on a single GPU. This offers more than one order of magnitude speed-up over the leading open-source baseline, Boltz-2, which significantly expands the regions of chemical space that can be explored during high-throughput virtual screening. Importantly, N\n                  <jats:sc>esso<\/jats:sc>\n                  -1 matches or surpasses the accuracy of Boltz-2 over the same benchmarks adopted in their study\u2014which we show reflect in-distribution scenarios\u2014as well as over more challenging out-of-distribution data encompassing the OpenBind affinity benchmark and 25 internal biochemical assays. Notably, N\n                  <jats:sc>esso<\/jats:sc>\n                  -1 maintains robust predictive accuracy even on assays with extremely low similarity to the training data. Moreover, we highlight examples where N\n                  <jats:sc>esso<\/jats:sc>\n                  -1 demonstrates meaningful selectivity, separating the binding affinities of identical compounds between on-targets and related off-targets. Nonetheless, zero-shot generalization to real- world medicinal chemistry remains an inherently challenging task; consequently, we acknowledge specific assays where the model\u2019s performance is limited. We\n                  <jats:bold>open-source<\/jats:bold>\n                  N\n                  <jats:sc>esso<\/jats:sc>\n                  -1: code and weights are available at\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/recursionpharma\/nesso\">https:\/\/github.com\/recursionpharma\/nesso<\/jats:ext-link>\n                <\/jats:p>","DOI":"10.64898\/2026.08.01.742196","type":"posted-content","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T13:25:28Z","timestamp":1785763528000},"source":"Crossref","is-referenced-by-count":1,"title":["Nesso-1: Accelerating Open-Source Binding Affinity Predictions"],"prefix":"10.64898","author":[{"given":"Nikhil","family":"Shenoy","sequence":"first","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0358-5200","authenticated-orcid":false,"given":"David","family":"Errington","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3257-4661","authenticated-orcid":false,"given":"Emmanuel","family":"Bengio","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5261-0657","authenticated-orcid":false,"given":"Kacper","family":"Kapu\u015bniak","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kerstin","family":"Klaeser","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4843-4468","authenticated-orcid":false,"given":"Yui Tik","family":"Pang","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Radenkovic","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9841-9867","authenticated-orcid":false,"given":"Prudencio","family":"Tossou","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Therence","family":"Bois","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1013-6556","authenticated-orcid":false,"given":"Andrew","family":"Wedlake","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2691-1379","authenticated-orcid":false,"given":"Francesco","family":"Di Giovanni","sequence":"additional","affiliation":[{"name":"Valence Labs, Recursion"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026080521451132000_2026.08.01.742196v1.1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5c03222"},{"key":"2026080521451132000_2026.08.01.742196v1.2","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.21334"},{"key":"2026080521451132000_2026.08.01.742196v1.3","doi-asserted-by":"publisher","DOI":"10.1021\/jm0306430"},{"issue":"1","key":"2026080521451132000_2026.08.01.742196v1.4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13321-021-00522-2","article-title":"Gnina 1.0: molecular docking with deep learning","volume":"13","year":"2021","journal-title":"Journal of cheminformatics"},{"issue":"4","key":"2026080521451132000_2026.08.01.742196v1.5","doi-asserted-by":"crossref","first-page":"2630","DOI":"10.1021\/acs.jctc.1c00136","article-title":"Reliable and accurate solution to the induced fit docking problem for protein\u2013ligand binding","volume":"17","year":"2021","journal-title":"Journal of Chemical Theory and Computation"},{"key":"2026080521451132000_2026.08.01.742196v1.6","unstructured":"OpenBind Consortium. OpenBind Structure\u2013Affinity Data Release: Enterovirus A71 2A Protease, May 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.7","doi-asserted-by":"publisher","DOI":"10.1063\/1.449208"},{"key":"2026080521451132000_2026.08.01.742196v1.8","doi-asserted-by":"publisher","DOI":"10.1021\/ja512751q"},{"key":"2026080521451132000_2026.08.01.742196v1.9","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.7b00083"},{"key":"2026080521451132000_2026.08.01.742196v1.10","doi-asserted-by":"crossref","unstructured":"David F Hahn , Christopher I Bayly , Melissa L Boby , Hannah E Bruce Macdonald , John D Chodera , Vytautas Gapsys , Antonia SJS Mey , David L Mobley , Laura Perez Benito , Christina EM Schindler , et al. Best practices for constructing, preparing, and evaluating protein-ligand binding affinity benchmarks [article v1. 0]. Living journal of computational molecular science, 4(1):1497, 2022.","DOI":"10.33011\/livecoms.4.1.1497"},{"issue":"1","key":"2026080521451132000_2026.08.01.742196v1.11","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1038\/s42004-023-01019-9","article-title":"The maximal and current accuracy of rigorous protein-ligand binding free energy calculations","volume":"6","year":"2023","journal-title":"Communications Chemistry"},{"key":"2026080521451132000_2026.08.01.742196v1.12","unstructured":"Wentao Li , Chao Lu , Meng Wu , Xuan Wu , Yu Xia , Ziqing Zhang , Xingyuan Xu , Youjun Xu , Yang Chen , Chang Han , et al. Physics-based vs ai-based free energy prediction for protein-ligand potency: Public benchmarks and internal project evidence. ChemRxiv, 2026."},{"issue":"22","key":"2026080521451132000_2026.08.01.742196v1.13","doi-asserted-by":"crossref","first-page":"22858","DOI":"10.1021\/acsomega.5c00151","article-title":"Acceleration of the gromacs free-energy perturbation calculations on gpus","volume":"10","year":"2025","journal-title":"ACS omega"},{"issue":"4","key":"2026080521451132000_2026.08.01.742196v1.14","doi-asserted-by":"crossref","first-page":"1823","DOI":"10.1021\/acs.jctc.5c01451","article-title":"Boltz-abfe: Free energy perturbation without crystal structures","volume":"22","year":"2026","journal-title":"Journal of Chemical Theory and Computation"},{"key":"2026080521451132000_2026.08.01.742196v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-021-03819-2"},{"key":"2026080521451132000_2026.08.01.742196v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-024-07487-W"},{"key":"2026080521451132000_2026.08.01.742196v1.17","doi-asserted-by":"publisher","DOI":"10.1126\/science.abj8754"},{"key":"2026080521451132000_2026.08.01.742196v1.18","doi-asserted-by":"publisher","DOI":"10.1126\/sci-ence.adl2528"},{"key":"2026080521451132000_2026.08.01.742196v1.19","unstructured":"Chai Discovery team , Jacques Boitreaud , Jack Dent , Matthew McPartlon , Joshua Meier , Vinicius Reis , Alex Rogozhonikov , and Kevin Wu . Chai-1: Decoding the molecular interactions of life. BioRxiv, pages 2024\u201310, 2024."},{"key":"2026080521451132000_2026.08.01.742196v1.20","first-page":"1","article-title":"Neuralplexer3: accurate biomolecular complex structure prediction with flow models","volume":"38","year":"2026","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026080521451132000_2026.08.01.742196v1.21","doi-asserted-by":"crossref","unstructured":"Jeremy Wohlwend , Gabriele Corso , Saro Passaro , Noah Getz , Mateo Reveiz , Ken Leidal , Wojtek Swiderski , Liam Atkinson , Tally Portnoi , Itamar Chinn , et al. Boltz-1 democratizing biomolecular interaction modeling. BioRxiv, pages 2024\u201311, 2025.","DOI":"10.1101\/2024.11.19.624167"},{"key":"2026080521451132000_2026.08.01.742196v1.22","unstructured":"Alejandro Dobles , Nina Jovic , Kenneth Leidal , Pranav Murugan , David C Williams , Drausin Wulsin , Nate Gruver , Christina X Ji , Korrawat Pruegsanusak , Gianluca Scarpellini , et al. Pearl: A foundation model for placing every atom in the right location. arXiv preprint arXiv:2510.24670, 2025."},{"key":"2026080521451132000_2026.08.01.742196v1.23","unstructured":"ByteDance AML AI4Science Team, Xinshi Chen , Yuxuan Zhang , Chan Lu , Wenzhi Ma , Jiaqi Guan , Chengyue Gong , Jincai Yang , Hanyu Zhang , Ke Zhang , et al. Protenix-advancing structure prediction through a comprehensive AlphaFold3 reproduction. BioRxiv, pages 2025\u201301, 2025."},{"key":"2026080521451132000_2026.08.01.742196v1.24","doi-asserted-by":"crossref","unstructured":"Saro Passaro , Gabriele Corso , Jeremy Wohlwend , Mateo Reveiz , Stephan Thaler , Vignesh Ram Somnath , Noah Getz , Tally Portnoi , Julien Roy , Hannes Stark , et al. Boltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv, 2025.","DOI":"10.1101\/2025.06.14.659707"},{"key":"2026080521451132000_2026.08.01.742196v1.25","doi-asserted-by":"crossref","unstructured":"Dominykas Lukauskis , Naail Kashif-Khan , Christopher Tame , and Andrew Potterton . Optimizing molecular glues using free energy perturbation and cofolding methods. ChemRxiv, 2025.","DOI":"10.26434\/chemrxiv-2025-tb29n"},{"key":"2026080521451132000_2026.08.01.742196v1.26","unstructured":"Shunzhou Wan , Xibei Zhang , Xiao Xue , and Peter V Coveney . On the reliability of ai methods in drug discovery: Evaluation of Boltz-2 for structure and binding affinity prediction. arXiv preprint arXiv:2603.05532, 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.27","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c02630"},{"key":"2026080521451132000_2026.08.01.742196v1.28","unstructured":"Venkata Sai Sreyas Adury , Pratyush Tiwary , Xinyu Gu , and Mrinal Shekhar . Early-enrichment hit discovery via reversible-work c (t) estimation in metadynamics (ctmd). bioRxiv, pages 2026\u201302, 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.29","unstructured":"Maxwell Kleinsasser , Brayden J Halverson , Edward Kraft , Sean Francis-Lyon , Sarah E Hugo , Mackenzie R Roman , Ben Miller , Andrew D Blevins , and Ian K Quigley . Hermes: Large del datasets train generalizable protein-ligand binding prediction models. arXiv preprint arXiv:2602.13503, 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.30","unstructured":"Kairi Furui and Masahito Ohue . Boltzina: Efficient and accurate virtual screening via docking- guided binding prediction with Boltz-2. arXiv preprint arXiv:2508.17555, 2025."},{"key":"2026080521451132000_2026.08.01.742196v1.31","unstructured":"Jiaqi Guan , Wesley Wei Qian , Xingang Peng , Yufeng Su , Jian Peng , and Jianzhu Ma . 3D equivariant diffusion for target-aware molecule generation and affinity prediction. In 11th International Conference on Learning Representations, ICLR 2023, 2023."},{"issue":"36","key":"2026080521451132000_2026.08.01.742196v1.32","doi-asserted-by":"crossref","first-page":"14954","DOI":"10.1039\/D4SC03523B","article-title":"Pilot: equivariant diffusion for pocket-conditioned de novo ligand generation with multi-objective guidance via importance sampling","volume":"15","year":"2024","journal-title":"Chemical Science"},{"key":"2026080521451132000_2026.08.01.742196v1.33","doi-asserted-by":"crossref","unstructured":"Julian Cremer , Tuan Le , Mohammad M Ghahremanpour , Emilia S-lugocka , Filipe Menezes , and Djork-Arn\u00e9 Clevert . Flowr. root: a flow matching based foundation model for joint multi-purpose structure-aware 3d ligand generation and affinity prediction. arXiv preprint arXiv:2510.02578, 2025.","DOI":"10.1038\/s41467-026-74130-9"},{"key":"2026080521451132000_2026.08.01.742196v1.34","unstructured":"Matteo Rossi , Ryan Pederson , Miles Wang-Henderson , Ben Kaufman , Edward C Williams , Carl Underkoffler , Owen Lewis Howell , Adrian Layer , Stephan Thaler , Narbe Mardirossian , et al. Terrabind: Fast and accurate binding affinity prediction through coarse structural representations. arXiv preprint arXiv:2602.07735, 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.35","unstructured":"Jeffrey Ouyang-Zhang , Pranav Murugan , Daniel J Diaz , Gianluca Scarpellini , Richard Strong Bowen , Nate Gruver , Adam Klivans , Philipp Kr\u00e4henb\u00fchl , Aleksandra Faust , and Maruan Al- Shedivat . Triangle multiplication is all you need for biomolecular structure representations. arXiv preprint arXiv:2510.18870, 2025."},{"key":"2026080521451132000_2026.08.01.742196v1.36","doi-asserted-by":"crossref","unstructured":"Salvatore Candido , Thomas Hayes , Alexander Derry , Roshan Rao , Zeming Lin , Robert Verkuil , Bryan Z Wu , Jin Sub Lee , Elise S Bruguera , Jehan A Keval , et al. Language modeling materializes a world model of protein biology. bioRxiv, pages 2026\u201306, 2026.","DOI":"10.64898\/2026.06.03.729735"},{"key":"2026080521451132000_2026.08.01.742196v1.37","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"2026080521451132000_2026.08.01.742196v1.38","unstructured":"Protein data bank: the single global archive for 3d macromolecular structure data. Nucleic acids research, 47(D1):D520\u2013D528, 2019."},{"key":"2026080521451132000_2026.08.01.742196v1.39","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAD1011"},{"key":"2026080521451132000_2026.08.01.742196v1.40","doi-asserted-by":"crossref","unstructured":"Pablo Lemos , Zane Beckwith , Sasaank Bandi , Maarten Van Damme , Jordan Crivelli-Decker , Benjamin J. Shields , Thomas Merth , Punit K Jha , Nicola De Mitri , Tiffany Callahan , AJ Nish , Paul Abruzzo , Romelia Salomon-Ferrer , and Martin Ganahl . SAIR: Enabling deep learning for protein-ligand interactions with a synthetic structural dataset. In The Fourteenth International Conference on Learning Representations, 2026.","DOI":"10.1101\/2025.06.17.660168"},{"key":"2026080521451132000_2026.08.01.742196v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkl999"},{"key":"2026080521451132000_2026.08.01.742196v1.42","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1004"},{"key":"2026080521451132000_2026.08.01.742196v1.43","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac956"},{"key":"2026080521451132000_2026.08.01.742196v1.44","doi-asserted-by":"publisher","DOI":"10.1126\/science.adk5864"},{"key":"2026080521451132000_2026.08.01.742196v1.45","doi-asserted-by":"publisher","DOI":"10.1126\/science.abm3452"},{"key":"2026080521451132000_2026.08.01.742196v1.46","doi-asserted-by":"crossref","unstructured":"Peter J Huber . Robust estimation of a location parameter. In Breakthroughs in statistics: Methodology and distribution, pages 492\u2013518. Springer, 1992.","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"2026080521451132000_2026.08.01.742196v1.47","unstructured":"Sheng Xu , Qiantai Feng , Lifeng Qiao , Hao Wu , Tao Shen , Yu Cheng , Shuangjia Zheng , and Siqi Sun . Foldbench: An all-atom benchmark for biomolecular structure prediction. bioRxiv, pages 2025\u201305, 2025."},{"issue":"9","key":"2026080521451132000_2026.08.01.742196v1.48","doi-asserted-by":"crossref","first-page":"3130","DOI":"10.1039\/D3SC04185A","article-title":"Posebusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences","volume":"15","year":"2024","journal-title":"Chemical Science"},{"key":"2026080521451132000_2026.08.01.742196v1.49","doi-asserted-by":"crossref","unstructured":"Peter \u0160krinjar , J\u00e9r\u00f4me Eberhardt , Janani Durairaj , and Torsten Schwede . Have protein-ligand co-folding methods moved beyond memorisation? BioRxiv, pages 2025\u201302, 2025.","DOI":"10.1101\/2025.02.03.636309"},{"key":"2026080521451132000_2026.08.01.742196v1.50","unstructured":"NVIDIA. cuequivariance. https:\/\/github.com\/NVIDIA\/cuEquivariance, 2024."},{"key":"2026080521451132000_2026.08.01.742196v1.51","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01569"},{"key":"2026080521451132000_2026.08.01.742196v1.52","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac035"},{"key":"2026080521451132000_2026.08.01.742196v1.53","doi-asserted-by":"publisher","DOI":"10.1021\/ci100436p"},{"key":"2026080521451132000_2026.08.01.742196v1.54","unstructured":"Richard J Gowers , Irfan Alibay , David WH Swenson , Michael M Henry , Benjamin Ries , Hannah M Baumann , James RB Eastwood , Joshua A Mitchell , David Dotson , Joshua T Horton , et al. The open free energy library. Zenodo, 2023."},{"issue":"17","key":"2026080521451132000_2026.08.01.742196v1.55","doi-asserted-by":"crossref","first-page":"8330","DOI":"10.1021\/acs.jctc.5c00861","article-title":"Optimizing absolute binding free energy calculations for production usage","volume":"21","year":"2025","journal-title":"Journal of Chemical Theory and Computation"},{"issue":"1","key":"2026080521451132000_2026.08.01.742196v1.56","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1002\/prot.70061","article-title":"Assessment of pharmaceutical protein\u2013ligand pose and affinity predictions in casp16","volume":"94","year":"2026","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"key":"2026080521451132000_2026.08.01.742196v1.57","unstructured":"Isomorphic Labs Team. Accurate Predictions of Novel Biomolecular Interactions with IsoDDE, February 2026."},{"issue":"11","key":"2026080521451132000_2026.08.01.742196v1.58","doi-asserted-by":"crossref","first-page":"5563","DOI":"10.1021\/acs.jcim.0c00449","article-title":"Accurate prediction of GPCR ligand binding affinity with free energy perturbation","volume":"60","year":"2020","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2026080521451132000_2026.08.01.742196v1.59","doi-asserted-by":"crossref","unstructured":"Bj\u00f6rn Mattsson and W. Patrick Walters . Identifying and addressing systematic data leakage in protein-ligand affinity benchmarks. BioRxiv, 2026.","DOI":"10.64898\/2026.06.29.735309"},{"key":"2026080521451132000_2026.08.01.742196v1.60","doi-asserted-by":"publisher","DOI":"10.1038\/s42004-025-01428-y"},{"key":"2026080521451132000_2026.08.01.742196v1.61","unstructured":"Aureka AI OpenDDE project. Folding, reasoning, and scaling with open-source drug discovery engine, 2026."},{"key":"2026080521451132000_2026.08.01.742196v1.62","unstructured":"Hyosoon Jang , Hyunjin Seo , Yunhui Jang , Seonghyun Park , and Sungsoo Ahn . Boltz is a strong baseline for atom-level representation learning."},{"key":"2026080521451132000_2026.08.01.742196v1.63","unstructured":"Emmanuel Bengio , Sanjeev Raja , Yui Tik Pang , Kerstin Klaeser , Cristian Gabellini , Nikhil Shenoy , Francesco Di Giovanni , and Prudencio Tossou . Aquagen: Scaling generative models to molecular dynamics precision on thousands of atoms. arXiv preprint arXiv:2607.03513, 2026."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.01.742196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:45:47Z","timestamp":1785991547000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.01.742196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":63,"URL":"https:\/\/doi.org\/10.64898\/2026.08.01.742196","relation":{},"subject":[],"published":{"date-parts":[[2026,8,3]]},"subtype":"preprint"}}