{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:29:52Z","timestamp":1774308592792,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3759307","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:46:13Z","timestamp":1757155573000},"page":"1307-1310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["<i>t<\/i>\n            -Testing the Waters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6256-5814","authenticated-orcid":false,"given":"Olivier","family":"Jeunen","sequence":"first","affiliation":[{"name":"Aampe, Antwerp, Belgium"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56069-9_34"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742563"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671556"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098024"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108591034"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Michael\u00a0P Fay and Michael\u00a0A Proschan. 2010. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Stat Surv 4 (2010) 1\u201339.","DOI":"10.1214\/09-SS051"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-87857-7"},{"key":"e_1_3_3_2_9_2","unstructured":"Ronald\u00a0Aylmer Fisher. 1921. Statistical methods for research workers. Statistical methods for research workers.1st Ed (1921)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Sander Greenland Stephen\u00a0J. Senn Kenneth\u00a0J. Rothman John\u00a0B. Carlin Charles Poole Steven\u00a0N. Goodman and Douglas\u00a0G. Altman. 2016. Statistical tests P values confidence intervals and power: a guide to misinterpretations. European Journal of Epidemiology 31 4 (01 Apr 2016) 337\u2013350. 10.1007\/s10654-016-0149-3","DOI":"10.1007\/s10654-016-0149-3"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Quentin\u00a0F. Gronau Akash Raj K.\u00a0N. and Eric-Jan Wagenmakers. 2021. Informed Bayesian Inference for the A\/B Test. Journal of Statistical Software 100 17 (2021) 1\u201339. 10.18637\/jss.v100.i17","DOI":"10.18637\/jss.v100.i17"},{"key":"e_1_3_3_2_12_2","first-page":"8637","volume-title":"Advances in Neural Information Processing Systems","author":"Guo Yongyi","year":"2021","unstructured":"Yongyi Guo, Dominic Coey, Mikael Konutgan, Wenting Li, Chris Schoener, and Matt Goldman. 2021. Machine Learning for Variance Reduction in Online Experiments. In Advances in Neural Information Processing Systems , Vol.\u00a034. Curran Associates, Inc., 8637\u20138648."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Olivier Jeunen. 2023. A Common Misassumption in Online Experiments with Machine Learning Models. SIGIR Forum 57 1 Article 13 (dec 2023) 9\u00a0pages. 10.1145\/3636341.3636358","DOI":"10.1145\/3636341.3636358"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688036"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671512"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671631"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623341"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539160"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108653985"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Nicholas Larsen Jonathan Stallrich Srijan Sengupta Alex Deng Ron Kohavi and Nathaniel\u00a0T. Stevens. 2024. Statistical Challenges in Online Controlled Experiments: A Review of A\/B Testing Methodology. The American Statistician 78 2 (2024) 135\u2013149. 10.1080\/00031305.2023.2257237","DOI":"10.1080\/00031305.2023.2257237"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Blakeley\u00a0B. McShane David Gal Andrew Gelman Christian Robert and Jennifer\u00a0L. Tackett. 2019. Abandon Statistical Significance. The American Statistician 73 sup1 (2019) 235\u2013245. 10.1080\/00031305.2018.1527253","DOI":"10.1080\/00031305.2018.1527253"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Donald\u00a0B Rubin. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of educational Psychology 66 5 (1974) 688.","DOI":"10.1037\/h0037350"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Juliet\u00a0Popper Shaffer. 1995. Multiple Hypothesis Testing. Annual Review of Psychology 46 1 (1995) 561\u2013584. 10.1146\/annurev.ps.46.020195.003021","DOI":"10.1146\/annurev.ps.46.020195.003021"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671543"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Ronald\u00a0L. Wasserstein Allen\u00a0L. Schirm and Nicole\u00a0A. Lazar. 2019. Moving to a World Beyond \u201cp<0.05\u201d. The American Statistician 73 sup1 (2019) 1\u201319. 10.1080\/00031305.2019.1583913","DOI":"10.1080\/00031305.2019.1583913"}],"event":{"name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","location":"Prague Czech Republic","acronym":"RecSys '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3759307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:42:18Z","timestamp":1757158938000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3759307"}},"subtitle":["Empirically Validating Assumptions for Reliable A\/B-Testing"],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":24,"alternative-id":["10.1145\/3705328.3759307","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3759307","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}