{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:03:27Z","timestamp":1775840607033,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","funder":[{"name":"Ministry of Economic Development of the Russian Federation","award":["000000C313925P4E0002"],"award-info":[{"award-number":["000000C313925P4E0002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792928","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"8637-8640","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting IPS-based Algorithms for Off-Policy Evaluation of Contextual Bandits"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2474-3821","authenticated-orcid":false,"given":"Daria","family":"Korovaitceva","sequence":"first","affiliation":[{"name":"HSE University, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2792-634X","authenticated-orcid":false,"given":"Marina","family":"Sheshukova","sequence":"additional","affiliation":[{"name":"HSE University, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3679-5311","authenticated-orcid":false,"given":"Evgeny","family":"Frolov","sequence":"additional","affiliation":[{"name":"Personalization Technologies, Moscow, Russian Federation and HSE University, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0203-2028","authenticated-orcid":false,"given":"Sergey","family":"Samsonov","sequence":"additional","affiliation":[{"name":"HSE University, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56027-9_7"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS500"},{"key":"e_1_3_2_1_3_1","volume-title":"Automated Off-Policy Estimator Selection via Supervised Learning. arXiv preprint arXiv:2406.18022","author":"Felicioni Nicol\u00f2","year":"2024","unstructured":"Nicol\u00f2 Felicioni, Michael Benigni, and Maurizio Ferrari Dacrema. 2024. Automated Off-Policy Estimator Selection via Supervised Learning. arXiv preprint arXiv:2406.18022 (2024)."},{"key":"e_1_3_2_1_4_1","first-page":"30250","article-title":"Off-policy evaluation with deficient support using side information","volume":"35","author":"Felicioni Nicol\u00f2","year":"2022","unstructured":"Nicol\u00f2 Felicioni, Maurizio Ferrari Dacrema, Marcello Restelli, and Paolo Cremonesi. 2022. Off-policy evaluation with deficient support using side information. Advances in Neural Information Processing Systems, Vol. 35 (2022), 30250-30264.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics","volume":"258","author":"Guzman-Olivares Daniel","year":"2025","unstructured":"Daniel Guzman-Olivares, Philipp Schmidt, Jacek Golebiowski, and Artur Bekasov. 2025. Clustering context in off-policy evaluation. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, Vol. 258."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_7_1","volume-title":"Intrinsically efficient, stable, and bounded off-policy evaluation for reinforcement learning. Advances in neural information processing systems","author":"Kallus Nathan","year":"2019","unstructured":"Nathan Kallus and Masatoshi Uehara. 2019. Intrinsically efficient, stable, and bounded off-policy evaluation for reinforcement learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 640-648","author":"Kuzborskij Ilja","year":"2021","unstructured":"Ilja Kuzborskij, Claire Vernade, Andras Gyorgy, and Csaba Szepesv\u00e1ri. 2021. Confident off-policy evaluation and selection through self-normalized importance weighting. In International Conference on Artificial Intelligence and Statistics. PMLR, 640-648."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90276-0"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"e_1_3_2_1_11_1","volume-title":"Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. arXiv preprint arXiv:2008.07146","author":"Saito Yuta","year":"2020","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2020. Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. arXiv preprint arXiv:2008.07146 (2020)."},{"key":"e_1_3_2_1_12_1","first-page":"9","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-policy evaluation for large action spaces via embeddings. In Proceedings of the 39th International Conference on Machine Learning, Vol. 162. 19089-19122."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474245"},{"key":"e_1_3_2_1_14_1","volume-title":"Learning from logged implicit exploration data. Advances in neural information processing systems","author":"Strehl Alex","year":"2010","unstructured":"Alex Strehl, John Langford, Lihong Li, and Sham M Kakade. 2010. Learning from logged implicit exploration data. Advances in neural information processing systems, Vol. 23 (2010)."},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. The Self-Normalized Estimator for Counterfactual Learning. In Advances in Neural Information Processing Systems, Vol. 28. Curran Associates, Inc. endthebibl"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:14:12Z","timestamp":1775837652000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":15,"alternative-id":["10.1145\/3774904.3792928","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792928","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}