[{"file":[{"relation":"main_file","file_size":877014,"date_created":"2026-01-27T12:43:25Z","access_level":"open_access","checksum":"c4b5a4a644228c6d1b0283e1368bce9e","content_type":"application/pdf","creator":"flocatel","success":1,"file_id":"21048","file_name":"4356_Unifying_Causal_Represent (1).pdf","date_updated":"2026-01-27T12:43:25Z"}],"publication_status":"published","date_created":"2025-02-05T09:23:25Z","ddc":["000"],"oa":1,"OA_type":"gold","conference":{"name":"ICLR: International Conference on Learning Representations","location":"Singapore","end_date":"2025-04-28","start_date":"2025-04-24"},"day":"22","_id":"19010","title":"Unifying causal representation learning with the invariance principle","publication":"13th International Conference on Learning Representations","year":"2025","corr_author":"1","date_updated":"2026-02-09T05:52:14Z","publisher":"ICLR","month":"01","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","author":[{"last_name":"Yao","id":"d3e02e50-48a8-11ee-8f62-c108061797fa","full_name":"Yao, Dingling","first_name":"Dingling"},{"first_name":"Dario","last_name":"Rancati","id":"feb58f2e-72ef-11ef-b75a-8f0894539cd0","full_name":"Rancati, Dario"},{"first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","full_name":"Cadei, Riccardo","last_name":"Cadei"},{"first_name":"Marco","full_name":"Fumero, Marco","id":"1c1593eb-393f-11ef-bb8e-ab4f1e979650","last_name":"Fumero"},{"last_name":"Locatello","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","first_name":"Francesco","orcid":"0000-0002-4850-0683"}],"external_id":{"arxiv":["2409.02772"]},"citation":{"mla":"Yao, Dingling, et al. “Unifying Causal Representation Learning with the Invariance Principle.” <i>13th International Conference on Learning Representations</i>, ICLR, 2025.","ieee":"D. Yao, D. Rancati, R. Cadei, M. Fumero, and F. Locatello, “Unifying causal representation learning with the invariance principle,” in <i>13th International Conference on Learning Representations</i>, Singapore, 2025.","short":"D. Yao, D. Rancati, R. Cadei, M. Fumero, F. Locatello, in:, 13th International Conference on Learning Representations, ICLR, 2025.","apa":"Yao, D., Rancati, D., Cadei, R., Fumero, M., &#38; Locatello, F. (2025). Unifying causal representation learning with the invariance principle. In <i>13th International Conference on Learning Representations</i>. Singapore: ICLR.","ista":"Yao D, Rancati D, Cadei R, Fumero M, Locatello F. 2025. Unifying causal representation learning with the invariance principle. 13th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","ama":"Yao D, Rancati D, Cadei R, Fumero M, Locatello F. Unifying causal representation learning with the invariance principle. In: <i>13th International Conference on Learning Representations</i>. ICLR; 2025.","chicago":"Yao, Dingling, Dario Rancati, Riccardo Cadei, Marco Fumero, and Francesco Locatello. “Unifying Causal Representation Learning with the Invariance Principle.” In <i>13th International Conference on Learning Representations</i>. ICLR, 2025."},"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"status":"public","type":"conference","license":"https://creativecommons.org/licenses/by/4.0/","oa_version":"Published Version","language":[{"iso":"eng"}],"file_date_updated":"2026-01-27T12:43:25Z","abstract":[{"text":"Causal representation learning aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A plethora of methods have been developed, each tackling carefully crafted problem settings that lead to different types of identifiability. The folklore is that these different settings are important, as they are often linked to different rungs of Pearl's causal hierarchy, although not all neatly fit. Our main contribution is to show that many existing causal representation learning approaches methodologically align the representation to known data symmetries. Identification of the variables is guided by equivalence classes across different \"data pockets\" that are not necessarily causal. This result suggests important implications, allowing us to unify many existing approaches in a single method that can mix and match different assumptions, including non-causal ones, based on the invariances relevant to our application. It also significantly benefits applicability, which we demonstrate by improving treatment effect estimation on real-world high-dimensional ecological data. Overall, this paper clarifies the role of causality assumptions in the discovery of causal variables and shifts the focus to preserving data symmetries.","lang":"eng"}],"quality_controlled":"1","article_processing_charge":"No","OA_place":"publisher","department":[{"_id":"FrLo"}],"scopus_import":"1","has_accepted_license":"1","acknowledgement":"We thank Jiaqi Zhang, Francesco Montagna, David Lopez-Paz, Kartik Ahuja, Thomas Kipf, Sara\r\nMagliacane, Julius von Kügelgen, Kun Zhang, and Bernhard Schölkopf for extremely helpful discussion. Riccardo Cadei was supported by a Google Research Scholar Award to Francesco Locatello. We acknowledge the Third Bellairs Workshop on Causal Representation Learning held at the Bellairs Research Institute, February 9/16, 2024, and a debate on the difference between interventions and counterfactuals in disentanglement and CRL that took place during Dhanya Sridhar’s lecture, which motivated us to significantly broaden the scope of the paper. We thank Dhanya and all participants of the workshop.","date_published":"2025-01-22T00:00:00Z","arxiv":1},{"publication_identifier":{"issn":["1049-5258"]},"title":"The third pillar of causal analysis? A measurement perspective on causal representations","date_updated":"2026-02-10T12:08:52Z","publisher":"Neural Information Processing Systems Foundation","corr_author":"1","year":"2025","publication":"39th Annual Conference on Neural Information Processing Systems","author":[{"first_name":"Dingling","id":"d3e02e50-48a8-11ee-8f62-c108061797fa","full_name":"Yao, Dingling","last_name":"Yao"},{"last_name":"Huang","id":"989c2a06-fb4e-11ef-a992-ab766442255b","full_name":"Huang, Shimeng","orcid":"0000-0001-6919-821X","first_name":"Shimeng"},{"first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","full_name":"Cadei, Riccardo","last_name":"Cadei"},{"full_name":"Zhang, Kun","last_name":"Zhang","first_name":"Kun"},{"orcid":"0000-0002-4850-0683","first_name":"Francesco","full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello"}],"month":"12","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","external_id":{"arxiv":["2505.17708"]},"citation":{"mla":"Yao, Dingling, et al. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025.","ieee":"D. Yao, S. Huang, R. Cadei, K. Zhang, and F. Locatello, “The third pillar of causal analysis? A measurement perspective on causal representations,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","apa":"Yao, D., Huang, S., Cadei, R., Zhang, K., &#38; Locatello, F. (2025). The third pillar of causal analysis? A measurement perspective on causal representations. In <i>39th Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation.","short":"D. Yao, S. Huang, R. Cadei, K. Zhang, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","ista":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. 2025. The third pillar of causal analysis? A measurement perspective on causal representations. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","ama":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. The third pillar of causal analysis? A measurement perspective on causal representations. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025.","chicago":"Yao, Dingling, Shimeng Huang, Riccardo Cadei, Kun Zhang, and Francesco Locatello. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025."},"publication_status":"epub_ahead","oa":1,"ddc":["000"],"date_created":"2026-01-29T14:24:56Z","_id":"21068","day":"15","conference":{"location":"San Diego, CA, United States","name":"NeurIPS: Neural Information Processing Systems","end_date":"2025-12-07","start_date":"2025-12-02"},"OA_type":"green","OA_place":"repository","department":[{"_id":"FrLo"}],"date_published":"2025-12-15T00:00:00Z","arxiv":1,"acknowledgement":"This research was funded in whole or in part by the Austrian Science Fund (FWF) 10.55776/COE12. For open access purposes, the author has applied a CC BY public copyright license to any accepted manuscript version arising from this submission.\r\n","has_accepted_license":"1","alternative_title":["Advances in Neural Information Processing Systems"],"intvolume":"        38","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"related_material":{"link":[{"relation":"software","url":"https://github.com/shimenghuang/a-measurement-perspective-of-crl"}]},"volume":38,"type":"conference","status":"public","abstract":[{"text":"Causal reasoning and discovery, two fundamental tasks of causal analysis,\r\noften face challenges in applications due to the complexity, noisiness, and highdimensionality of real-world data. Despite recent progress in identifying latent\r\ncausal structures using causal representation learning (CRL), what makes learned\r\nrepresentations useful for causal downstream tasks and how to evaluate them are\r\nstill not well understood. In this paper, we reinterpret CRL using a measurement\r\nmodel framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under\r\nwhich learned representations support downstream causal reasoning and provides\r\na principled basis for quantitatively assessing the quality of representations using\r\na new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX\r\nacross diverse causal inference scenarios, including numerical simulations and\r\nreal-world ecological video analysis, demonstrating that the proposed framework\r\nand corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks. Reproducible code can\r\nbe found at https://github.com/shimenghuang/a-measurement-perspective-of-crl.","lang":"eng"}],"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2505.17708","open_access":"1"}],"oa_version":"Preprint","article_processing_charge":"No","quality_controlled":"1"},{"type":"conference","status":"public","volume":38,"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"intvolume":"        38","alternative_title":["Advances in Neural Information Processing Systems"],"quality_controlled":"1","article_processing_charge":"No","language":[{"iso":"eng"}],"oa_version":"Published Version","abstract":[{"lang":"eng","text":"In many scientific experiments, the data annotating cost constraints the pace for testing novel hypotheses. Yet, modern machine learning pipelines offer a promising solution—provided their predictions yield correct conclusions. We focus on Prediction-Powered Causal Inferences (PPCI), i.e., estimating the treatment effect in an unlabeled target experiment, relying on training data with the same outcome annotated but potentially different treatment or effect modifiers. We first show that conditional calibration guarantees valid PPCI at population level. Then, we introduce a sufficient representation constraint transferring validity across experiments, which we propose to enforce in practice in Deconfounded Empirical Risk Minimization, our new model-agnostic training objective. We validate our method on synthetic and real-world scientific data, solving impossible problem instances for Empirical Risk Minimization even with standard invariance constraints. In particular, for the first time, we achieve valid causal inference on a scientific experiment with complex recording and no human annotations, fine-tuning a foundational model on our similar annotated experiment."}],"file_date_updated":"2026-01-29T14:35:02Z","OA_place":"publisher","has_accepted_license":"1","date_published":"2025-12-15T00:00:00Z","acknowledgement":"We thank the Causal Learning and Artificial Intelligence group at ISTA for the continuous feedback on the project and valuable discussions. We thank the Social Immunity group at ISTA, particularly Jinook Oh, for the annotation program and Michaela Hoenigsberger for supporting our ecological experiment. Riccardo Cadei is supported by a Google Research Scholar Award and a Google Initiated Gift to Francesco Locatello. This research was funded in part by the Austrian Science Fund (FWF) 10.55776/COE12). It was further partially supported by the ISTA Interdisciplinary Project Committee for the collaborative project “ALED” between Francesco Locatello and Sylvia Cremer. For open access purposes, the author has applied a CC BY public copyright license to any author accepted manuscript version arising from this submission.","department":[{"_id":"FrLo"},{"_id":"SyCr"}],"file":[{"content_type":"application/pdf","checksum":"92467fa566cd36671a6a3b9e71ae0f71","creator":"flocatel","relation":"main_file","file_size":8489023,"date_created":"2026-01-29T14:35:02Z","access_level":"open_access","file_id":"21077","file_name":"17546_Prediction_Powered_Causa.pdf","success":1,"date_updated":"2026-01-29T14:35:02Z"}],"publication_status":"epub_ahead","conference":{"end_date":"2025-12-07","start_date":"2025-12-02","location":"San Diego, CA, United States","name":"NeurIPS: Neural Information Processing Systems"},"OA_type":"gold","_id":"21076","day":"15","ddc":["000"],"date_created":"2026-01-29T14:35:11Z","oa":1,"publication":"39th Annual Conference on Neural Information Processing Systems","publisher":"Neural Information Processing Systems Foundation","date_updated":"2026-02-16T11:39:33Z","year":"2025","publication_identifier":{"issn":["1049-5258"]},"title":"Prediction-powered causal inferences","citation":{"ieee":"R. Cadei <i>et al.</i>, “Prediction-powered causal inferences,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","mla":"Cadei, Riccardo, et al. “Prediction-Powered Causal Inferences.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025.","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 Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation.","short":"R. Cadei, I. Demirel, P. De Bartolomeis, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","ista":"Cadei R, Demirel I, De Bartolomeis P, Lindorfer L, Cremer S, Schmid C, Locatello F. 2025. Prediction-powered causal inferences. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","chicago":"Cadei, Riccardo, Ilker Demirel, Piersilvio De Bartolomeis, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, and Francesco Locatello. “Prediction-Powered Causal Inferences.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025.","ama":"Cadei R, Demirel I, De Bartolomeis P, et al. Prediction-powered causal inferences. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025."},"author":[{"last_name":"Cadei","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","full_name":"Cadei, Riccardo","first_name":"Riccardo"},{"full_name":"Demirel, Ilker","last_name":"Demirel","first_name":"Ilker"},{"full_name":"De Bartolomeis, Piersilvio","last_name":"De Bartolomeis","first_name":"Piersilvio"},{"last_name":"Lindorfer","full_name":"Lindorfer, Lukas","id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455","first_name":"Lukas"},{"first_name":"Sylvia","orcid":"0000-0002-2193-3868","full_name":"Cremer, Sylvia","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","last_name":"Cremer"},{"full_name":"Schmid, Cordelia","last_name":"Schmid","first_name":"Cordelia"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"12"},{"type":"conference","status":"public","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"volume":38,"intvolume":"        38","related_material":{"record":[{"status":"public","id":"18895","relation":"research_data"},{"status":"for_moderation","relation":"is_continued_by","id":"19509"}],"link":[{"url":"https://github.com/CausalLearningAI/ISTAnt","relation":"software"}]},"quality_controlled":"1","article_processing_charge":"No","oa_version":"Published Version","language":[{"iso":"eng"}],"file_date_updated":"2025-01-27T11:42:24Z","abstract":[{"text":"Machine Learning and AI have the potential to transform data-driven\r\nscientific discovery, enabling accurate predictions for several scientific\r\nphenomena. As many scientific questions are inherently causal, this paper looks\r\nat the causal inference task of treatment effect estimation, where the outcome\r\nof interest is recorded in high-dimensional observations in a Randomized\r\nControlled Trial (RCT). Despite being the simplest possible causal setting and\r\na perfect fit for deep learning, we theoretically find that many common choices\r\nin the literature may lead to biased estimates. To test the practical impact of\r\nthese considerations, we recorded ISTAnt, the first real-world benchmark for\r\ncausal inference downstream tasks on high-dimensional observations as an RCT\r\nstudying how garden ants (Lasius neglectus) respond to microparticles applied\r\nonto their colony members by hygienic grooming. Comparing 6 480 models\r\nfine-tuned from state-of-the-art visual backbones, we find that the sampling\r\nand modeling choices significantly affect the accuracy of the causal estimate,\r\nand that classification accuracy is not a proxy thereof. We further validated\r\nthe analysis, repeating it on a synthetically generated visual data set\r\ncontrolling the causal model. Our results suggest that future benchmarks should\r\ncarefully consider real downstream scientific questions, especially causal\r\nones. Further, we highlight guidelines for representation learning methods to\r\nhelp answer causal questions in the sciences.","lang":"eng"}],"OA_place":"publisher","has_accepted_license":"1","acknowledgement":"We thank Piersilvio De Bartolomeis, and the full Causal Learning and Artificial Intelligence (CLAI) group at ISTA for the extremely helpful discussions. Riccardo Cadei was supported by a Google Research Scholar Award and a Google Initiated Gift to Francesco Locatello. We thank the Social Immunity team at ISTA particularly Michaela Hönigsberger and Wilfrid Jean Louis, for supporting the ecological experiment and Farnaz Beikzadeh Abbasi, Luisa Fiebig and Martin Estermann for annotating ant behavior in ISTAnt.","arxiv":1,"date_published":"2024-09-25T00:00:00Z","department":[{"_id":"SyCr"},{"_id":"FrLo"},{"_id":"GradSch"}],"scopus_import":"1","file":[{"date_updated":"2025-01-27T11:42:24Z","success":1,"file_name":"2024_ICML_Cadei.pdf","file_id":"18896","file_size":4453014,"relation":"main_file","access_level":"open_access","date_created":"2025-01-27T11:42:24Z","creator":"dernst","content_type":"application/pdf","checksum":"beedf05388bbdb7ddda81ec3d5ec7026"}],"publication_status":"published","OA_type":"gold","conference":{"end_date":"2024-07-26","start_date":"2024-07-26","name":"ICML: International Conference on Machine Learning"},"day":"25","_id":"18847","date_created":"2025-01-14T07:27:26Z","ddc":["000","570"],"oa":1,"publication":"ICML 2024 Workshop AI4Science","corr_author":"1","year":"2024","publisher":"Curran Associates","date_updated":"2025-07-10T11:51:50Z","title":"Smoke and mirrors in causal downstream tasks","external_id":{"arxiv":["2405.17151"]},"citation":{"ieee":"R. Cadei, L. Lindorfer, S. Cremer, C. Schmid, and F. Locatello, “Smoke and mirrors in causal downstream tasks,” in <i>ICML 2024 Workshop AI4Science</i>, 2024, vol. 38.","mla":"Cadei, Riccardo, et al. “Smoke and Mirrors in Causal Downstream Tasks.” <i>ICML 2024 Workshop AI4Science</i>, vol. 38, Curran Associates, 2024.","apa":"Cadei, R., Lindorfer, L., Cremer, S., Schmid, C., &#38; Locatello, F. (2024). Smoke and mirrors in causal downstream tasks. In <i>ICML 2024 Workshop AI4Science</i> (Vol. 38). Curran Associates.","short":"R. Cadei, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello, in:, ICML 2024 Workshop AI4Science, Curran Associates, 2024.","ista":"Cadei R, Lindorfer L, Cremer S, Schmid C, Locatello F. 2024. Smoke and mirrors in causal downstream tasks. ICML 2024 Workshop AI4Science. ICML: International Conference on Machine Learning vol. 38.","chicago":"Cadei, Riccardo, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, and Francesco Locatello. “Smoke and Mirrors in Causal Downstream Tasks.” In <i>ICML 2024 Workshop AI4Science</i>, Vol. 38. Curran Associates, 2024.","ama":"Cadei R, Lindorfer L, Cremer S, Schmid C, Locatello F. Smoke and mirrors in causal downstream tasks. In: <i>ICML 2024 Workshop AI4Science</i>. Vol 38. Curran Associates; 2024."},"month":"09","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","author":[{"last_name":"Cadei","full_name":"Cadei, Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","first_name":"Riccardo"},{"first_name":"Lukas","full_name":"Lindorfer, Lukas","id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455","last_name":"Lindorfer"},{"first_name":"Sylvia","orcid":"0000-0002-2193-3868","full_name":"Cremer, Sylvia","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","last_name":"Cremer"},{"first_name":"Cordelia","last_name":"Schmid","full_name":"Schmid, Cordelia"},{"first_name":"Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"}]},{"date_published":"2024-10-23T00:00:00Z","citation":{"ieee":"R. Cadei, F. Locatello, S. Cremer, L. Lindorfer, and C. Schmid, “ISTAnt.” Institute of Science and Technology Austria, 2024.","mla":"Cadei, Riccardo, et al. <i>ISTAnt</i>. Institute of Science and Technology Austria, 2024, doi:<a href=\"https://doi.org/10.6084/M9.FIGSHARE.26484934.V2\">10.6084/M9.FIGSHARE.26484934.V2</a>.","apa":"Cadei, R., Locatello, F., Cremer, S., Lindorfer, L., &#38; Schmid, C. (2024). ISTAnt. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.6084/M9.FIGSHARE.26484934.V2\">https://doi.org/10.6084/M9.FIGSHARE.26484934.V2</a>","short":"R. Cadei, F. Locatello, S. Cremer, L. Lindorfer, C. Schmid, (2024).","ista":"Cadei R, Locatello F, Cremer S, Lindorfer L, Schmid C. 2024. ISTAnt, Institute of Science and Technology Austria, <a href=\"https://doi.org/10.6084/M9.FIGSHARE.26484934.V2\">10.6084/M9.FIGSHARE.26484934.V2</a>.","chicago":"Cadei, Riccardo, Francesco Locatello, Sylvia Cremer, Lukas Lindorfer, and Cordelia Schmid. “ISTAnt.” Institute of Science and Technology Austria, 2024. <a href=\"https://doi.org/10.6084/M9.FIGSHARE.26484934.V2\">https://doi.org/10.6084/M9.FIGSHARE.26484934.V2</a>.","ama":"Cadei R, Locatello F, Cremer S, Lindorfer L, Schmid C. ISTAnt. 2024. doi:<a href=\"https://doi.org/10.6084/M9.FIGSHARE.26484934.V2\">10.6084/M9.FIGSHARE.26484934.V2</a>"},"author":[{"first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","full_name":"Cadei, Riccardo","last_name":"Cadei"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683"},{"orcid":"0000-0002-2193-3868","first_name":"Sylvia M","full_name":"Cremer, Sylvia M","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","last_name":"Cremer"},{"id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455","full_name":"Lindorfer, Lukas","last_name":"Lindorfer","first_name":"Lukas"},{"last_name":"Schmid","full_name":"Schmid, Cordelia","first_name":"Cordelia"}],"doi":"10.6084/M9.FIGSHARE.26484934.V2","month":"10","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","department":[{"_id":"SyCr"},{"_id":"FrLo"},{"_id":"GradSch"}],"publisher":"Institute of Science and Technology Austria","date_updated":"2025-01-27T11:58:38Z","OA_place":"repository","corr_author":"1","year":"2024","title":"ISTAnt","article_processing_charge":"No","_id":"18895","day":"23","OA_type":"gold","oa":1,"abstract":[{"lang":"eng","text":"ISTAnt is a new ecological dataset for social immunity and represents the first real-world benchmark for causal inference downstream tasks on high-dimensional observations. It analyzes grooming behavior in the ant Lasius neglectus in groups of three worker ants. The workers for the experiment were obtained from their laboratory stock colony, which had been collected from the field in 2022 in the Botanical Garden Jena, Germany. Ant collection and all experimental work were performed in compliance with international, national and institutional regulations and ethical guidelines. For the experiment, the body surface of one of the three ants was treated with a suspension of either of two microparticle types (diameter ~5 µm) to induce grooming by the two nestmates, which were individually color-coded by application of a dot of blue or orange paint, respectively. The three ants were housed in small plastic containers (diameter 28mm, height 30mm) with moistened, plastered ground and the interior walls covered with PTFE (polytetrafluoroethane) to hamper climbing by the ants. Filming occurred in a temperature- and humidity-controlled room at 23°C within a custom-made filming box with controlled lighting and ventilation conditions. We set up nine ant groups at a time (always containing both treatments) and placed them randomly on positions 1-9 marked on the floor in a 3x3 grid, about 3mm from each other. The experiment was performed on two consecutive days. Videos were acquired using a USB camera (FLIR blackfly S BFS-U3-120S4C, Teledyne FLIR) with a high-performance lens (HP Series 25mm Focal Length, Edmund optics 86-572) in OBS studio 29.0.0 \\citep{bailey2017obs} at a framerate of 30 FPS and a resolution of 2500x2500 pixels. From each original video (105x105 mm), we generated nine individual videos .mkv (each ~32x32 mm, 770x770 pixels) by determining exact coordinates per container from one frame in GIMP 2.10.36 and cropping of the videos with FFmpeg 6.1.1. Annotation was performed over two consecutive days by three observers who had not been involved in the experimental setup or recording and were unaware of the treatment assignments to ensure bias-free behavioral annotation. They annotated the behavior of the ants during video observations, using custom-made software that saves the start and end frames of behaviors marked in a .csv file (see 'annotations' folder). In one of the videos, one of the nestmates' legs got inadvertently stuck to its body surface during the color-coding, interfering with its behavior, so the video was discarded. This left 44 videos from 5 independent setups (n=24 of treatment 1 and n=20 of treatment 2) of 10 minutes each for a total of 792 000 annotated frames (see 'video' folder). For each video, we provide the following information: the number of the set to which it belongs (1-5); the number of the position within the set reflecting the position of the ant group under the camera (1-9), for which we also provide ‘coordinates’ in the 3x3 grid (taking values -1/0/1 for both X and Y axis); treatment (1 or 2); the hour of the day when the recording was started (in 24h CEST); experimental day (A or B); the top left coordinate of the cropping square from the original video (CropX/CropY); the person annotating the video (given as A, B, C); the date of annotation (1: first day, 2: second day) and in which order the videos were annotated by each person, both reflecting a possible training effect of the person (see 'experiments_settings.csv' file)."}],"ddc":["570"],"main_file_link":[{"url":"https://10.6084/M9.FIGSHARE.26484934.V2","open_access":"1"}],"oa_version":"Published Version","date_created":"2025-01-27T11:45:43Z","status":"public","type":"research_data_reference","related_material":{"record":[{"id":"18847","relation":"used_in_publication","status":"public"}]}}]