{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T14:01:23Z","timestamp":1776002483424,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["786461"],"award-info":[{"award-number":["786461"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["786461"],"award-info":[{"award-number":["786461"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In some fields of artificial intelligence, machine learning and statistics, the validation of new methods and algorithms is often hindered by the scarcity of suitable real-world datasets. Researchers must often turn to simulated data, which yields limited information about the applicability of the proposed methods to real problems. As a step forward, we have constructed two devices that allow us to quickly and inexpensively produce large datasets from non-trivial but well-understood physical systems. The devices, which we call causal chambers, are computer-controlled laboratories that allow us to manipulate and measure an array of variables from these physical systems, providing a rich testbed for algorithms from a variety of fields. We illustrate potential applications through a series of case studies in fields such as causal discovery, out-of-distribution generalization, change point detection, independent component analysis and symbolic regression. For applications to causal inference, the chambers allow us to carefully perform interventions. We also provide and empirically validate a causal model of each chamber, which can be used as ground truth for different tasks. The hardware and software are made open source, and the datasets are publicly available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/causalchamber.org\" ext-link-type=\"uri\">causalchamber.org<\/jats:ext-link> or through the Python package <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/pypi.org\/project\/causalchamber\/\" ext-link-type=\"uri\">causalchamber<\/jats:ext-link>.<\/jats:p>","DOI":"10.1038\/s42256-024-00964-x","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T10:04:28Z","timestamp":1736935468000},"page":"107-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Causal chambers as a real-world physical testbed for AI methodology"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9728-1125","authenticated-orcid":false,"given":"Juan L.","family":"Gamella","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-7511","authenticated-orcid":false,"given":"Jonas","family":"Peters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1782-6015","authenticated-orcid":false,"given":"Peter","family":"B\u00fchlmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"964_CR1","doi-asserted-by":"crossref","unstructured":"Spirtes, P., Glymour, C., Scheines, R. & Heckerman, D. Causation, Prediction, and Search (MIT Press, 2000).","DOI":"10.7551\/mitpress\/1754.001.0001"},{"key":"964_CR2","doi-asserted-by":"crossref","unstructured":"Pearl, J. Causality (Cambridge Univ. Press, 2009).","DOI":"10.1017\/CBO9780511803161"},{"key":"964_CR3","unstructured":"Peters, J., Janzing, D. & Sch\u00f6lkopf, B. Elements of Causal Inference: Foundations and Learning Algorithms (MIT Press, 2017)."},{"key":"964_CR4","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1126\/science.1165893","volume":"324","author":"M Schmidt","year":"2009","unstructured":"Schmidt, M. & Lipson, H. Distilling free-form natural laws from experimental data. Science 324, 81\u201385 (2009).","journal-title":"Science"},{"key":"964_CR5","unstructured":"La Cava, W. et al. Contemporary symbolic regression methods and their relative performance. In 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)."},{"key":"964_CR6","unstructured":"Locatello, F. et al. Challenging common assumptions in the unsupervised learning of disentangled representations. In Proc. 36th International Conference on Machine Learning 4114\u20134124 (PMLR, 2019)."},{"key":"964_CR7","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","volume":"109","author":"B Sch\u00f6lkopf","year":"2021","unstructured":"Sch\u00f6lkopf, B. et al. Toward causal representation learning. Proc. IEEE 109, 612\u2013634 (2021).","journal-title":"Proc. IEEE"},{"key":"964_CR8","unstructured":"Koh, P. W. et al. WILDS: a benchmark of in-the-wild distribution shifts. In Proc. 38th International Conference on Machine Learning, 5637\u20135664 (PMLR, 2021)."},{"key":"964_CR9","first-page":"15464","volume":"33","author":"JL Gamella","year":"2020","unstructured":"Gamella, J. L. & Heinze-Deml, C. Active invariant causal prediction: experiment selection through stability. Adv. Neural Inf. Process. Syst. 33, 15464\u201315475 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"964_CR10","unstructured":"G\u00f6bler, K. et al. causalAssembly: generating realistic production data for benchmarking causal discovery. In Causal Learning and Reasoning 609\u2013642 (PMLR, 2024)."},{"key":"964_CR11","unstructured":"Cheng, Y. et al. CausalTime: realistically generated time-series for benchmarking of causal discovery. In The Twelfth International Conference on Learning Representations (2023)."},{"key":"964_CR12","doi-asserted-by":"publisher","first-page":"eaay2631","DOI":"10.1126\/sciadv.aay2631","volume":"6","author":"Silviu-Marian Udrescu","year":"2020","unstructured":"Udrescu, Silviu-Marian & Tegmark, M. AI Feynman: a physics-inspired method for symbolic regression. Sci. Adv. 6, eaay2631 (2020).","journal-title":"Sci. Adv."},{"key":"964_CR13","doi-asserted-by":"publisher","first-page":"e13397","DOI":"10.1371\/journal.pone.0013397","volume":"5","author":"A Greenfield","year":"2010","unstructured":"Greenfield, A., Madar, A., Ostrer, H. & Bonneau, R. Dream4: combining genetic and dynamic information to identify biological networks and dynamical models. PLoS ONE 5, e13397 (2010).","journal-title":"PLoS ONE"},{"key":"964_CR14","first-page":"6955","volume":"32","author":"R Tu","year":"2019","unstructured":"Tu, R., Zhang, K., Bertilson, B., Kjellstrom, H. & Zhang, C. Neuropathic pain diagnosis simulator for causal discovery algorithm evaluation. Adv. Neural Inf. Process. Syst. 32, 6955 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"964_CR15","unstructured":"Gamella, J. L. Dataset repository for the causal chambers. GitHub https:\/\/github.com\/juangamella\/causal-chamber (2024)."},{"key":"964_CR16","first-page":"63","volume":"87","author":"SL Lauritzen","year":"2001","unstructured":"Lauritzen, S. L. Causal inference from graphical models. Monogr. Stat. Appl. Prob. 87, 63\u2013108 (2001).","journal-title":"Monogr. Stat. Appl. Prob."},{"key":"964_CR17","unstructured":"Gamella J. L. Experiments repository for the causal chambers. GitHub https:\/\/github.com\/juangamella\/causal-chamber-paper (2024)."},{"key":"964_CR18","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1214\/09-SS057","volume":"3","author":"J Pearl","year":"2009","unstructured":"Pearl, J. Causal inference in statistics: an overview. Statist. Surv. 3, 96\u2013146 (2009).","journal-title":"Statist. Surv."},{"key":"964_CR19","doi-asserted-by":"publisher","first-page":"524","DOI":"10.3389\/fgene.2019.00524","volume":"10","author":"C Glymour","year":"2019","unstructured":"Glymour, C., Zhang, K. & Spirtes, P. Review of causal discovery methods based on graphical models. Front. Genet. 10, 524 (2019).","journal-title":"Front. Genet."},{"key":"964_CR20","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1146\/annurev-statistics-031017-100630","volume":"5","author":"C Heinze-Deml","year":"2018","unstructured":"Heinze-Deml, C., Maathuis, M. H. & Meinshausen, N. Causal structure learning. Annu. Rev. Stat. Appl. 5, 371\u2013391 (2018).","journal-title":"Annu. Rev. Stat. Appl."},{"key":"964_CR21","first-page":"1","volume":"17","author":"JM Mooij","year":"2016","unstructured":"Mooij, J. M., Peters, J., Janzing, D., Zscheischler, J. & Sch\u00f6lkopf, B. Distinguishing cause from effect using observational data: methods and benchmarks. J. Mach. Learn. Res. 17, 1\u2013102 (2016).","journal-title":"J. Mach. Learn. Res."},{"key":"964_CR22","doi-asserted-by":"publisher","first-page":"075310","DOI":"10.1063\/1.5025050","volume":"28","author":"J Runge","year":"2018","unstructured":"Runge, J. Causal network reconstruction from time series: from theoretical assumptions to practical estimation. Chaos 28, 075310 (2018).","journal-title":"Chaos"},{"key":"964_CR23","doi-asserted-by":"publisher","first-page":"2885","DOI":"10.1214\/21-AOS2064","volume":"49","author":"S Bongers","year":"2021","unstructured":"Bongers, S., Forr\u00e9, P., Peters, J. & Mooij, J. M. Foundations of structural causal models with cycles and latent variables. Ann. Stat.49, 2885\u20132915 (2021).","journal-title":"Ann. Stat."},{"key":"964_CR24","unstructured":"Claassen, T. & Mooij, J. M. Establishing Markov equivalence in cyclic directed graphs. In Proc. 39th Conference on Uncertainty in Artificial Intelligence 433\u2013442 (PMLR, 2023)."},{"key":"964_CR25","first-page":"2003","volume":"7","author":"S Shimizu","year":"2006","unstructured":"Shimizu, S., Hoyer, P. O., Hyv\u00e4rinen, A. & Kerminen, A. A linear non-Gaussian acyclic model for causal discovery. J. Mach. Learn. Res. 7, 2003\u20132030 (2006).","journal-title":"J. Mach. Learn. Res."},{"key":"964_CR26","first-page":"211","volume":"21","author":"P Spirtes","year":"1999","unstructured":"Spirtes, P., Meek, C. & Richardson, T. An algorithm for causal inference in the presence of latent variables and selection bias. Comput. Causation Discov. 21, 211\u2013252 (1999).","journal-title":"Comput. Causation Discov."},{"key":"964_CR27","first-page":"507","volume":"3","author":"DM Chickering","year":"2002","unstructured":"Chickering, D. M. Optimal structure identification with greedy search. J. Mach. Learn. Res. 3, 507\u2013554 (2002).","journal-title":"J. Mach. Learn. Res."},{"key":"964_CR28","unstructured":"Squires, C., Wang, Y. & Uhler, C. Permutation-based causal structure learning with unknown intervention targets. In Proc. 36th Conference on Uncertainty in Artificial Intelligence 1039\u20131048 (PMLR, 2020)."},{"key":"964_CR29","unstructured":"Runge, J. Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets. In Proc. 36th Conference on Uncertainty in Artificial Intelligence 1388\u20131397 (PMLR, 2020)."},{"key":"964_CR30","unstructured":"Nagarajan, V., Andreassen, A. & Neyshabur, B. Understanding the failure modes of out-of-distribution generalization. In Proc. 8th International Conference on Learning Representations (2020)."},{"key":"964_CR31","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R. et al. Shortcut learning in deep neural networks. Nat. Mach. Intell. 2, 665\u2013673 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"964_CR32","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1111\/rssb.12398","volume":"83","author":"D Rothenh\u00e4usler","year":"2021","unstructured":"Rothenh\u00e4usler, D., Meinshausen, N., B\u00fchlmann, P. & Peters, J. Anchor regression: heterogeneous data meet causality. J. R. Stat. Soc. B 83, 215\u2013246 (2021).","journal-title":"J. R. Stat. Soc. B"},{"key":"964_CR33","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/0893-6080(88)90014-7","volume":"1","author":"K Fukushima","year":"1988","unstructured":"Fukushima, K. Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw. 1, 119\u2013130 (1988).","journal-title":"Neural Netw."},{"key":"964_CR34","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1111\/rssb.12167","volume":"78","author":"J Peters","year":"2016","unstructured":"Peters, J., B\u00fchlmann, P. & Meinshausen, N. Causal inference by using invariant prediction: identification and confidence intervals. J. R. Stat. Soc. B 78, 947\u20131012 (2016).","journal-title":"J. R. Stat. Soc. B"},{"key":"964_CR35","doi-asserted-by":"publisher","first-page":"107299","DOI":"10.1016\/j.sigpro.2019.107299","volume":"167","author":"C Truong","year":"2020","unstructured":"Truong, C., Oudre, L. & Vayatis, N. Selective review of offline change point detection methods. Signal Process. 167, 107299 (2020).","journal-title":"Signal Process."},{"key":"964_CR36","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s10115-016-0987-z","volume":"51","author":"S Aminikhanghahi","year":"2017","unstructured":"Aminikhanghahi, S. & Cook, D. J. A survey of methods for time series change point detection. Knowl. Inf. Syst. 51, 339\u2013367 (2017).","journal-title":"Knowl. Inf. Syst."},{"key":"964_CR37","first-page":"1","volume":"24","author":"M Londschien","year":"2023","unstructured":"Londschien, M., B\u00fchlmann, P. & Kov\u00e1cs, S. Random forests for change point detection. J. Mach. Learn. Res. 24, 1\u201345 (2023).","journal-title":"J. Mach. Learn. Res."},{"key":"964_CR38","doi-asserted-by":"publisher","first-page":"100844","DOI":"10.1016\/j.patter.2023.100844","volume":"4","author":"A Hyv\u00e4rinen","year":"2023","unstructured":"Hyv\u00e4rinen, A., Khemakhem, I. & Morioka, H. Nonlinear independent component analysis for principled disentanglement in unsupervised deep learning. Patterns 4, 100844 (2023).","journal-title":"Patterns"},{"key":"964_CR39","doi-asserted-by":"crossref","unstructured":"Hyv\u00e4rinen, A., Karhunen, J. & Oja, E. Independent Component Analysis (Wiley Interscience, 2001).","DOI":"10.1002\/0471221317"},{"key":"964_CR40","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","volume":"13","author":"A Hyv\u00e4rinen","year":"2000","unstructured":"Hyv\u00e4rinen, A. & Oja, E. Independent component analysis: algorithms and applications. Neural Netw. 13, 411\u2013430 (2000).","journal-title":"Neural Netw."},{"key":"964_CR41","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1109\/72.761722","volume":"10","author":"A Hyv\u00e4rinen","year":"1999","unstructured":"Hyv\u00e4rinen, A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Netw. 10, 626\u2013634 (1999).","journal-title":"IEEE Trans. Neural Netw."},{"key":"964_CR42","first-page":"17429","volume":"33","author":"M Cranmer","year":"2020","unstructured":"Cranmer, M. et al. Discovering symbolic models from deep learning with inductive biases. Adv. Neural Inf. Process. Syst. 33, 17429\u201317442 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"964_CR43","first-page":"10269","volume":"35","author":"Pierre-Alexandre Kamienny","year":"2022","unstructured":"Kamienny, Pierre-Alexandre, d\u2019Ascoli, St\u00e9phane, Lample, G. & Charton, Fran\u00e7ois End-to-end symbolic regression with transformers. Adv. Neural Inf. Process. Syst. 35, 10269\u201310281 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"964_CR44","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"GE Karniadakis","year":"2021","unstructured":"Karniadakis, G. E. et al. Physics-informed machine learning. Nat. Rev. Phys. 3, 422\u2013440 (2021).","journal-title":"Nat. Rev. Phys."},{"key":"964_CR45","doi-asserted-by":"publisher","first-page":"30055","DOI":"10.1073\/pnas.1912789117","volume":"117","author":"K Cranmer","year":"2020","unstructured":"Cranmer, K., Brehmer, J. & Louppe, G. The frontier of simulation-based inference. Proc. Natl Acad. Sci. USA 117, 30055\u201330062 (2020).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"964_CR46","first-page":"14809","volume":"34","author":"N Takeishi","year":"2021","unstructured":"Takeishi, N. & Kalousis, A. Physics-integrated variational autoencoders for robust and interpretable generative modeling. Adv. Neural Inf. Process. Syst. 34, 14809\u201314821 (2021).","journal-title":"Adv."},{"key":"964_CR47","unstructured":"Wehenkel, A. et al. Robust hybrid learning with expert augmentation. In Transactions on Machine Learning Research (2023)."},{"key":"964_CR48","doi-asserted-by":"publisher","first-page":"124012","DOI":"10.1088\/1742-5468\/ac3ae5","volume":"2021","author":"Y Yin","year":"2021","unstructured":"Yin, Y. et al. Augmenting physical models with deep networks for complex dynamics forecasting. J. Stat. Mech. Theory Exp.2021, 124012 (2021).","journal-title":"J. Stat. Mech. Theory Exp."},{"key":"964_CR49","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L. \u00e9on, Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998).","journal-title":"Proc. IEEE"},{"key":"964_CR50","doi-asserted-by":"publisher","unstructured":"Gamella, J. L. juangamella\/causal-chamber-paper: v1.0.0-alpha. Zenodo https:\/\/doi.org\/10.5281\/zenodo.14050466 (2024).","DOI":"10.5281\/zenodo.14050466"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00964-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00964-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00964-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T16:24:54Z","timestamp":1739550294000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00964-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["964"],"URL":"https:\/\/doi.org\/10.1038\/s42256-024-00964-x","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"assertion":[{"value":"17 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}