{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T08:24:00Z","timestamp":1772007840598,"version":"3.50.1"},"reference-count":59,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"LSST-DA"},{"DOI":"10.13039\/100001008","name":"Brinson Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100001008","id-type":"DOI","asserted-by":"crossref"}]},{"name":"WoodNext Foundation"},{"name":"Research Corporation for Science Advancement Foundation"},{"name":"National Science Foundation","award":["PHY-2019786"],"award-info":[{"award-number":["PHY-2019786"]}]},{"name":"U.S. Department of Energy, Office of Science, Office of High Energy Physics of U.S. Department of Energy","award":["DE-SC0012567"],"award-info":[{"award-number":["DE-SC0012567"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application of our approach using simulated total matter and gas density fields from three hydrodynamic simulation suites with different subgrid physics implementations.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae107d","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T22:53:15Z","timestamp":1759877595000},"page":"045020","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Detecting model misspecification in cosmology with scale-dependent normalizing flows"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3662-2263","authenticated-orcid":true,"given":"Aizhan","family":"Akhmetzhanova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6069-2999","authenticated-orcid":true,"given":"Carolina","family":"Cuesta-Lazaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9088-7845","authenticated-orcid":true,"given":"Siddharth","family":"Mishra-Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"mlstae107dbib1","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.jheap.2022.04.002","type":"journal-article","volume":"34","author":"Abdalla","year":"2022","journal-title":"J. High Energy Astrophys."},{"key":"mlstae107dbib2","doi-asserted-by":"publisher","first-page":"JCAP02(2025)021","DOI":"10.1088\/1475-7516\/2025\/02\/021","type":"journal-article","author":"Adame","year":"2025","journal-title":"J. Cosmol. Astropart. Phys."},{"key":"mlstae107dbib3","doi-asserted-by":"publisher","first-page":"7459","DOI":"10.1093\/mnras\/stad3646","type":"journal-article","volume":"527","author":"Akhmetzhanova","year":"2023","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib4","article-title":"Experiment tracking with weights and biases","author":"Biewald","year":"2020","type":"other"},{"key":"mlstae107dbib5","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1093\/mnras\/stac648","type":"journal-article","volume":"512","author":"Bird","year":"2022","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dark.2023.101193","type":"journal-article","volume":"40","author":"Cabass","year":"2023","journal-title":"Phys. Dark Univ."},{"key":"mlstae107dbib7","author":"Chisari","year":"2019","type":"preprint"},{"key":"mlstae107dbib8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.109.123531","type":"journal-article","volume":"109","author":"Cuesta-Lazaro","year":"2024","journal-title":"Phys. Rev. D"},{"key":"mlstae107dbib9","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2309624121","type":"journal-article","volume":"121","author":"Dai","year":"2024","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstae107dbib10","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1093\/mnras\/stz937","type":"journal-article","volume":"486","author":"Dav\u00e9","year":"2019","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib11","author":"Diao","year":"2025","type":"preprint"},{"key":"mlstae107dbib12","article-title":"PyTorch Lightning, 1.4","author":"The PyTorch Lightning team","year":"2019","type":"other"},{"key":"mlstae107dbib13","doi-asserted-by":"publisher","first-page":"A114","DOI":"10.1051\/0004-6361\/201116878","type":"journal-article","volume":"531","author":"Ferdosi","year":"2011","journal-title":"Astron. Astrophys."},{"key":"mlstae107dbib14","author":"Friedman","year":"2022","type":"preprint"},{"key":"mlstae107dbib15","doi-asserted-by":"publisher","first-page":"9052","DOI":"10.1109\/TPAMI.2024.3415112","type":"journal-article","volume":"46","author":"Gui","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstae107dbib16","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","type":"journal-article","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"mlstae107dbib17","doi-asserted-by":"publisher","first-page":"L33","DOI":"10.3847\/2041-8213\/abf2c7","type":"journal-article","volume":"911","author":"Hayat","year":"2021","journal-title":"Astrophys. J. Lett."},{"key":"mlstae107dbib18","first-page":"pp 770","author":"He","year":"2016","type":"conference-proceedings"},{"key":"mlstae107dbib19","doi-asserted-by":"publisher","first-page":"559","DOI":"10.33232\/001c.120559","type":"journal-article","volume":"7","author":"Ho","year":"2024","journal-title":"Open J. Astrophys."},{"key":"mlstae107dbib20","article-title":"Plausible adversarial attacks on direct parameter inference models in astrophysics","author":"Horowitz","year":"2022","type":"preprint"},{"key":"mlstae107dbib21","doi-asserted-by":"crossref","DOI":"10.1093\/rasti\/rzad028","type":"preprint","article-title":"A brief review of contrastive learning applied to astrophysics","author":"Huertas-Company","year":"2023"},{"key":"mlstae107dbib22","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","type":"journal-article","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"mlstae107dbib23","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1093\/mnras\/staa3594","type":"journal-article","volume":"501","author":"Jeffrey","year":"2021","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib24","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad1a4d","type":"journal-article","volume":"5","author":"Jeffrey","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae107dbib25","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2017","type":"preprint"},{"key":"mlstae107dbib26","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3233\/978-1-61499-649-1-87","type":"conference-proceedings","article-title":"Jupyter Notebooks\u2014a publishing format for reproducible computational workflows","author":"Kluyver","year":"2016"},{"key":"mlstae107dbib27","author":"Lanzieri","year":"2024","type":"preprint"},{"key":"mlstae107dbib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.98.063511","type":"journal-article","volume":"98","author":"Leclercq","year":"2018","journal-title":"Phys. Rev. D"},{"key":"mlstae107dbib29","author":"Lehman","year":"2024","type":"preprint"},{"key":"mlstae107dbib30","article-title":"SimBIG: field-level simulation-based inference of galaxy clustering","author":"Lemos","year":"2023b","type":"preprint"},{"key":"mlstae107dbib31","first-page":"pp 19256","author":"Lemos","year":"2023a","type":"conference-proceedings"},{"key":"mlstae107dbib32","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","type":"preprint"},{"key":"mlstae107dbib33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","type":"preprint"},{"key":"mlstae107dbib34","doi-asserted-by":"publisher","first-page":"4017","DOI":"10.1093\/mnras\/stab2484","type":"journal-article","volume":"508","author":"Maksimova","year":"2021","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib35","doi-asserted-by":"publisher","first-page":"64","DOI":"10.3847\/1538-4357\/ad8bc3","type":"journal-article","volume":"978","author":"Mudur","year":"2024","journal-title":"Astrophys. J."},{"key":"mlstae107dbib36","author":"Nalisnick","year":"2018","type":"preprint"},{"key":"mlstae107dbib37","author":"Nguyen","year":"2024","type":"preprint"},{"key":"mlstae107dbib38","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1093\/mnras\/stac351","type":"journal-article","volume":"513","author":"Ni","year":"2022","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib39","doi-asserted-by":"publisher","first-page":"136","DOI":"10.3847\/1538-4357\/ad022a","type":"journal-article","volume":"959","author":"Ni","year":"2023","journal-title":"Astrophys. J."},{"key":"mlstae107dbib40","doi-asserted-by":"publisher","first-page":"2539","DOI":"10.1093\/mnras\/stac3620","type":"journal-article","volume":"524","author":"Pakmor","year":"2023","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib41","article-title":"Fast \u03b5-free inference of simulation models with bayesian conditional density estimation","author":"Papamakarios","year":"2018","type":"preprint"},{"key":"mlstae107dbib42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1912.02762","type":"journal-article","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach.: Learn. Res."},{"key":"mlstae107dbib43","doi-asserted-by":"publisher","first-page":"4990","DOI":"10.1093\/mnras\/stae1450","type":"journal-article","volume":"531","author":"Parker","year":"2024","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib44","first-page":"pp 8024","type":"conference-proceedings","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"mlstae107dbib45","doi-asserted-by":"publisher","first-page":"4077","DOI":"10.1093\/mnras\/stx2656","type":"journal-article","volume":"473","author":"Pillepich","year":"2018","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib46","author":"Polanska","year":"2024","type":"preprint"},{"key":"mlstae107dbib47","first-page":"pp 1530","author":"Rezende","year":"2015","type":"conference-proceedings"},{"key":"mlstae107dbib48","doi-asserted-by":"publisher","first-page":"L7","DOI":"10.3847\/2041-8213\/ac5c5b","type":"journal-article","volume":"934","author":"Riess","year":"2022","journal-title":"Astrophys. J. Lett."},{"key":"mlstae107dbib49","first-page":"pp 395","type":"conference-proceedings","volume":"vol 735","author":"Skilling","year":"2004"},{"key":"mlstae107dbib50","first-page":"pp 2256","author":"Sohl-Dickstein","year":"2015","type":"conference-proceedings"},{"key":"mlstae107dbib51","author":"Song","year":"2020","type":"preprint"},{"key":"mlstae107dbib52","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab7e1a","type":"journal-article","volume":"1","author":"Tran","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae107dbib53","doi-asserted-by":"publisher","first-page":"71","DOI":"10.3847\/1538-4357\/abf7ba","type":"journal-article","volume":"915","author":"Villaescusa-Navarro","year":"2021","journal-title":"Astrophys. J."},{"key":"mlstae107dbib54","doi-asserted-by":"publisher","first-page":"61","DOI":"10.3847\/1538-4365\/ac5ab0","type":"journal-article","volume":"259","author":"Villaescusa-Navarro","year":"2022","journal-title":"Astrophys. J. Suppl. Series"},{"key":"mlstae107dbib55","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","type":"journal-article","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"mlstae107dbib56","doi-asserted-by":"publisher","first-page":"3291","DOI":"10.1093\/mnras\/stw2944","type":"journal-article","volume":"465","author":"Weinberger","year":"2017","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae107dbib57","article-title":"PyTorch image models","author":"Wightman","year":"2019","type":"other"},{"key":"mlstae107dbib58","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-024-02117-4","type":"preprint","article-title":"Generalized out-of-distribution detection: a survey","author":"Yang","year":"2024"},{"key":"mlstae107dbib59","article-title":"Understanding failures in out-of-distribution detection with deep generative models","author":"Zhang","year":"2021","type":"preprint"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:49:27Z","timestamp":1761562167000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae107d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":59,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,10,27]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae107d","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"Detecting model misspecification in cosmology with scale-dependent normalizing flows","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-08-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}