{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:10Z","timestamp":1774352890401,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"Fair","award":["PE0000013"],"award-info":[{"award-number":["PE0000013"]}]},{"name":"SERICS","award":["PE00000014"],"award-info":[{"award-number":["PE00000014"]}]},{"name":"NEREO","award":["2022AEF- HAZ"],"award-info":[{"award-number":["2022AEF- HAZ"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730318","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"3367-3376","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unveiling DIME: Reproducibility, Generalizability, and Formal Analysis of Dimension Importance Estimation for Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8362-274X","authenticated-orcid":false,"given":"Cesare","family":"Campagnano","sequence":"first","affiliation":[{"name":"Pinecone, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7817-6140","authenticated-orcid":false,"given":"Antonio","family":"Mallia","sequence":"additional","affiliation":[{"name":"Pinecone, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-9055","authenticated-orcid":false,"given":"Fabrizio","family":"Silvestri","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1147-1148.","author":"Arguello Jaime","unstructured":"Jaime Arguello, Fernando Diaz, Jimmy Lin, and Andrew Trotman. 2015. SIGIR 2015 workshop on reproducibility, inexplicability, and generalizability of results (RIGOR). In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1147-1148."},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_5_1","volume-title":"DeeperImpact: Optimizing Sparse Learned Index Structures. arXiv preprint arXiv:2405.17093","author":"Basnet Soyuj","year":"2024","unstructured":"Soyuj Basnet, Jerry Gou, Antonio Mallia, and Torsten Suel. 2024. DeeperImpact: Optimizing Sparse Learned Index Structures. arXiv preprint arXiv:2405.17093 (2024)."},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_7_1","volume-title":"ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo- Irrelevance Feedback for Dense Retrieval. arXiv preprint arXiv:2412.14967","author":"D'Erasmo Giulio","year":"2024","unstructured":"Giulio D'Erasmo, Giovanni Trappolini, Nicola Tonellotto, and Fabrizio Silvestri. 2024. ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo- Irrelevance Feedback for Dense Retrieval. arXiv preprint arXiv:2412.14967 (2024)."},{"key":"e_1_3_2_1_8_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_9_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657691"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_12_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_14_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_15_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_17_1","first-page":"30233","article-title":"Matryoshka representation learning","volume":"35","author":"Kusupati Aditya","year":"2022","unstructured":"Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham Kakade, Prateek Jain, et al. 2022. Matryoshka representation learning. Advances in Neural Information Processing Systems 35 (2022), 30233-30249.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625334"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401262"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_24_1","volume-title":"Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.","author":"Multi-Functionality Multi-Linguality","year":"2024","unstructured":"Multi-Linguality Multi-Functionality Multi-Granularity. 2024. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. (2024)."},{"key":"e_1_3_2_1_25_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_26_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_28_1","unstructured":"Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends\u00ae in Information Retrieval 3 4 (2009) 333-389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_31_1","volume-title":"Relevance feedback in information retrieval. The SMART Retrieval System-Experiments in Automatic Document Processing","author":"Rocchio JJ","year":"1971","unstructured":"JJ Rocchio. 1971. Relevance feedback in information retrieval. The SMART Retrieval System-Experiments in Automatic Document Processing (1971)."},{"key":"e_1_3_2_1_32_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_33_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_34_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_36_1","volume-title":"Overview of the TREC 2004 Robust Retrieval Track. In TREC.","author":"Voorhees Ellen","year":"2004","unstructured":"Ellen Voorhees. 2004. Overview of the TREC 2004 Robust Retrieval Track. In TREC."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Ellen M. Voorhees. 1996. NIST TREC Disks 4 and 5: Retrieval Test Collections Document Set. doi:10.18434\/t47g6m","DOI":"10.18434\/t47g6m"},{"key":"e_1_3_2_1_38_1","volume-title":"Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2023. Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5860\/crl.59.3.287"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_42_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_43_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 Technical Report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_44_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Improved Learned Sparse Retrieval with Corpus-Specific Vocabularies. In European Conference on Information Retrieval. Springer, 181-194","author":"Yu Puxuan","year":"2024","unstructured":"Puxuan Yu, Antonio Mallia, and Matthias Petri. 2024. Improved Learned Sparse Retrieval with Corpus-Specific Vocabularies. In European Conference on Information Retrieval. Springer, 181-194."},{"key":"e_1_3_2_1_46_1","volume-title":"Multilingual Retrieval Without Compromise. arXiv preprint arXiv:2412.04506","author":"Yu Puxuan","year":"2024","unstructured":"Puxuan Yu, Luke Merrick, Gaurav Nuti, and Daniel Campos. 2024. Arctic-Embed 2.0: Multilingual Retrieval Without Compromise. arXiv preprint arXiv:2412.04506 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"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\/3726302.3730318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:11:06Z","timestamp":1755864666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":46,"alternative-id":["10.1145\/3726302.3730318","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730318","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"}}]}}