{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T10:40:02Z","timestamp":1755859202947,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730176","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:21:38Z","timestamp":1752456098000},"page":"2597-2601","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Counterfactual Model Selection in Contextual Bandits"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4326-8348","authenticated-orcid":false,"given":"Shion","family":"Ishikawa","sequence":"first","affiliation":[{"name":"Rakuten Group, Inc., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8430-5391","authenticated-orcid":false,"given":"Young-joo","family":"Chung","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc., San Mateo, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4583-5716","authenticated-orcid":false,"given":"Yun-Ching","family":"Liu","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0362-7156","authenticated-orcid":false,"given":"Yu","family":"Hirate","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"176","article-title":"Linear thompson sampling revisited","author":"Abeille Marc","year":"2017","unstructured":"Marc Abeille and Alessandro Lazaric. 2017. Linear thompson sampling revisited. In Artificial Intelligence and Statistics. PMLR, 176-184.","journal-title":"Artificial Intelligence and Statistics. PMLR"},{"key":"e_1_3_2_2_2_1","volume-title":"Conference on Learning Theory. PMLR, 12-38","author":"Agarwal Alekh","year":"2017","unstructured":"Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, and Robert E Schapire. 2017. Corralling a band of bandit algorithms. In Conference on Learning Theory. PMLR, 12-38."},{"key":"e_1_3_2_2_3_1","volume-title":"Thompson Sampling for Contextual Bandits with Linear Payoffs. CoRR abs\/1209.3352","author":"Agrawal Shipra","year":"2012","unstructured":"Shipra Agrawal and Navin Goyal. 2012. Thompson Sampling for Contextual Bandits with Linear Payoffs. CoRR abs\/1209.3352 (2012). arXiv:1209.3352 http:\/\/arxiv.org\/abs\/1209.3352"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3088510"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"P Auer. 2002. Finite-time Analysis of the Multiarmed Bandit Problem.","DOI":"10.1023\/A:1013689704352"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208-214","author":"Chu Wei","year":"2011","unstructured":"Wei Chu, Lihong Li, Lev Reyzin, and Robert Schapire. 2011. Contextual bandits with linear payoff functions. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208-214."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104482.3104620"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.171377"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Kassraie Parnian","year":"2024","unstructured":"Parnian Kassraie, Nicolas Emmenegger, Andreas Krause, and Aldo Pacchiano. 2024. Anytime model selection in linear bandits. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 1282, 37 pages."},{"key":"e_1_3_2_2_11_1","first-page":"10328","article-title":"Model selection in contextual stochastic bandit problems","volume":"33","author":"Pacchiano Aldo","year":"2020","unstructured":"Aldo Pacchiano, My Phan, Yasin Abbasi Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, and Csaba Szepesvari. 2020. Model selection in contextual stochastic bandit problems. Advances in Neural Information Processing Systems 33 (2020), 10328-10337.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_12_1","volume-title":"Eligibility Traces for Off-Policy Policy Evaluation","author":"Precup Doina","year":"2000","unstructured":"Doina Precup, Richard Sutton, and Satinder Singh. 2000. Eligibility Traces for Off-Policy Policy Evaluation. Computer Science Department Faculty Publication Series (06 2000)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","unstructured":"P.R. Rosenbaum and D.B. Rubin. 1983. The central role of the propensity score in observational studies for causal effects. 70 1 (1983) 41-55. doi:10.1093\/biomet\/70.1.41","DOI":"10.1093\/biomet\/70.1.41"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.)","volume":"1","author":"Saito Yuta","year":"2021","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2021. Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off- Policy Evaluation. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/33e75ff09dd601bbe69f351039152189-Paper-round2.pdf"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474245"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767707"},{"key":"e_1_3_2_2_17_1","volume-title":"Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges. Statistical science: a review journal of the Institute of Mathematical Statistics 30, 2","author":"Villar Sof\u00eda S","year":"2015","unstructured":"Sof\u00eda S Villar, Jack Bowden, and James Wason. 2015. Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges. Statistical science: a review journal of the Institute of Mathematical Statistics 30, 2 (2015), 199."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T10:00:18Z","timestamp":1755856818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":17,"alternative-id":["10.1145\/3726302.3730176","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730176","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}