{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:09:02Z","timestamp":1784138942280,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809885","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3642-3646","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PrepRet: Automated Data Preparation Pipeline Selection for Neural Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8968-2972","authenticated-orcid":false,"given":"Jing","family":"Chang","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7611-1735","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL] https:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_1_2_1","volume-title":"Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144","author":"Bonifacio Luiz","year":"2022","unstructured":"Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"Efficient and robust automated machine learning. Advances in neural information processing systems","author":"Feurer Matthias","year":"2015","unstructured":"Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. 2015. Efficient and robust automated machine learning. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_4_1","volume-title":"SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_6_1","volume-title":"Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=jKN1pXi7b0"},{"key":"e_1_3_2_1_7_1","volume-title":"Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkE3y85ee","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkE3y85ee"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_10_1","volume-title":"A few brief notes on deepimpact, coil, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin and Xueguang Ma. 2021. A few brief notes on deepimpact, coil, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.423"},{"key":"e_1_3_2_1_12_1","volume-title":"The concrete distribution: A continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712","author":"Maddison Chris J","year":"2016","unstructured":"Chris J Maddison, Andriy Mnih, and Yee Whye Teh. 2016. The concrete distribution: A continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 (2016)."},{"key":"e_1_3_2_1_13_1","unstructured":"Rodrigo Nogueira Wei Yang Jimmy Lin and Kyunghyun Cho. 2019. Document Expansion by Query Prediction. arXiv:1904.08375 [cs.IR] https:\/\/arxiv.org\/abs\/1904.08375"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.)","volume":"1","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:29:12Z","timestamp":1784136552000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":15,"alternative-id":["10.1145\/3805712.3809885","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809885","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}