[{"day":"01","conference":{"name":"NeurIPS: Neural Information Processing Systems","start_date":"2025-12-02","location":"San Diego, CA, United States","end_date":"2025-12-07"},"title":"Prediction-Powered Causal Inferences","intvolume":"        38","arxiv":1,"dataavailabilitystatement":"We share all the code implementation in the supplementary material.\r\nOur new experimental ecology dataset preview is anonymously shared on Figshare at\r\nhttps://figshare.com/s/9a490b6f6eeebd73350b. We further rely on ISTAnt dataset publicly\r\navailable at https://doi.org/10.6084/m9.figshare.26484934.v2. The synthetic experiments\r\non CausalMNIST relies on MNIST dataset LeCun [1998], publicly available. Additional\r\nexperimental details are reported in Section 5 and Appendices B-C.","quality_controlled":"1","status":"public","_id":"22832","article_processing_charge":"No","month":"12","fulldoi":"https://doi.org/10.52202/085713-2479","publisher":"Neural Information Processing Systems Foundation","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2026-09-17T06:56:40Z","date_created":"2026-09-06T22:02:01Z","supplementarymaterial":"yes","citation":{"ieee":"R. Cadei <i>et al.</i>, “Prediction-Powered Causal Inferences,” in <i>39th Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38, pp. 82200–82229.","ista":"Cadei R, Demirel I, De Bartolomeis P, Lindorfer L, Cremer S, Schmid C, Locatello F. 2025. Prediction-Powered Causal Inferences. 39th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38, 82200–82229.","ama":"Cadei R, Demirel I, De Bartolomeis P, et al. Prediction-Powered Causal Inferences. In: <i>39th Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025:82200-82229. doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>","apa":"Cadei, R., Demirel, I., De Bartolomeis, P., Lindorfer, L., Cremer, S., Schmid, C., &#38; Locatello, F. (2025). Prediction-Powered Causal Inferences. In <i>39th Conference on Neural Information Processing Systems</i> (Vol. 38, pp. 82200–82229). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>","chicago":"Cadei, Riccardo, Ilker Demirel, Piersilvio De Bartolomeis, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, and Francesco Locatello. “Prediction-Powered Causal Inferences.” In <i>39th Conference on Neural Information Processing Systems</i>, 38:82200–229. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>.","mla":"Cadei, Riccardo, et al. “Prediction-Powered Causal Inferences.” <i>39th Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, pp. 82200–29, doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>.","short":"R. Cadei, I. Demirel, P. De Bartolomeis, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello, in:, 39th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025, pp. 82200–82229."},"volume":38,"corr_author":"1","year":"2025","OA_place":"repository","doi":"10.52202/085713-2479","publication_status":"published","oa_version":"Preprint","alternative_title":["Advances in Neural Information Processing Systems"],"department":[{"_id":"FrLo"},{"_id":"GradSch"},{"_id":"SyCr"}],"scopus_import":"1","researchdata_availability":"yes","type":"conference","OA_type":"green","acknowledgement":"We thank the Causal Learning and Artificial Intelligence group at ISTA for the continuous feedback\r\non the project and valuable discussions. We thank the Social Immunity group at ISTA, particularly\r\nJinook Oh, for the annotation program and Michaela Hoenigsberger for supporting our ecological\r\nexperiment. Riccardo Cadei is supported by a Google Research Scholar Award and a Google Initiated\r\nGift to Francesco Locatello. This research was funded in part by the Austrian Science Fund (FWF)\r\n10.55776/COE12). It was further partially supported by the ISTA Interdisciplinary Project Committee\r\nfor the collaborative project “ALED” between Francesco Locatello and Sylvia Cremer. For open\r\naccess purposes, the author has applied a CC BY public copyright license to any author accepted\r\nmanuscript version arising from this submission.\r\n","project":[{"grant_number":"COE12","name":"Bilateral Artificial Intelligence (Locatello)","_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6"}],"publication_identifier":{"issn":["1049-5258"],"isbn":["9798331338275"]},"das_tickbox":"1","external_id":{"arxiv":["2502.06343"]},"publication":"39th Conference on Neural Information Processing Systems","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2502.06343"}],"date_published":"2025-12-01T00:00:00Z","language":[{"iso":"eng"}],"abstract":[{"text":"In many scientific experiments, the data annotating cost constraints the pace\r\nfor testing novel hypotheses. Yet, modern machine learning pipelines offer a\r\npromising solution—provided their predictions yield correct conclusions. We\r\nfocus on Prediction-Powered Causal Inferences (PPCI), i.e., estimating the\r\ntreatment effect in an unlabeled target experiment, relying on training data with\r\nthe same outcome annotated but potentially different treatment or effect modifiers.\r\nWe first show that conditional calibration guarantees valid PPCI at population\r\nlevel. Then, we introduce a sufficient representation constraint transferring validity\r\nacross experiments, which we propose to enforce in practice in Deconfounded\r\nEmpirical Risk Minimization, our new model-agnostic training objective. We\r\nvalidate our method on synthetic and real-world scientific data, solving impossible\r\nproblem instances for Empirical Risk Minimization even with standard invariance\r\nconstraints. In particular, for the first time, we achieve valid causal inference\r\non a scientific experiment with complex recording and no human annotations,\r\nfine-tuning a foundational model on our similar annotated experiment.","lang":"eng"}],"author":[{"full_name":"Cadei, Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","first_name":"Riccardo","last_name":"Cadei"},{"first_name":"Ilker","last_name":"Demirel","full_name":"Demirel, Ilker"},{"last_name":"De Bartolomeis","first_name":"Piersilvio","full_name":"De Bartolomeis, Piersilvio"},{"full_name":"Lindorfer, Lukas","last_name":"Lindorfer","id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455","first_name":"Lukas"},{"full_name":"Cremer, Sylvia","last_name":"Cremer","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","first_name":"Sylvia","orcid":"0000-0002-2193-3868"},{"full_name":"Schmid, Cordelia","first_name":"Cordelia","last_name":"Schmid"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco"}],"page":"82200-82229"}]