{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:40:25Z","timestamp":1759012825868,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DGE-2243822, IIS-2129008, IIS-1940759, IIS-1940757"],"award-info":[{"award-number":["DGE-2243822, IIS-2129008, IIS-1940759, IIS-1940757"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014037","name":"National Defense Science and Engineering Graduate","doi-asserted-by":"publisher","award":[""],"award-info":[{"award-number":[""]}],"id":[{"id":"10.13039\/100014037","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BIDS-Accenture Fellowship","award":[""],"award-info":[{"award-number":[""]}]},{"DOI":"10.13039\/100000879","name":"Alfred P. Sloan Foundation","doi-asserted-by":"publisher","award":[""],"award-info":[{"award-number":[""]}],"id":[{"id":"10.13039\/100000879","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Adobe","award":[""],"award-info":[{"award-number":[""]}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","award":[""],"award-info":[{"award-number":[""]}],"id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"name":"G-Research","award":[""],"award-info":[{"award-number":[""]}]},{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","award":[""],"award-info":[{"award-number":[""]}],"id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PromptQL","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Sigma Computing","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Snowflake","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747727","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Dataset Discovery with DataScout"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7553-770X","authenticated-orcid":false,"given":"Rachel","family":"Lin","sequence":"first","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8638-3863","authenticated-orcid":false,"given":"Bhavya","family":"Chopra","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5229-3913","authenticated-orcid":false,"given":"Wenjing","family":"Lin","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0919-9672","authenticated-orcid":false,"given":"Shreya","family":"Shankar","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0949-7290","authenticated-orcid":false,"given":"Madelon","family":"Hulsebos","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4538-4752","authenticated-orcid":false,"given":"Aditya G.","family":"Parameswaran","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Marcia\u00a0J Bates. 1989. The design of browsing and berrypicking techniques for the online search interface. Online review 13 5 (1989) 407\u2013424.","DOI":"10.1108\/eb024320"},{"key":"e_1_3_3_2_4_2","volume-title":"Proceedings 25th International Conference on Extending Database Technology (EDBT 2022)","author":"Bogatu Alex","year":"2022","unstructured":"Alex Bogatu, Norman\u00a0W Paton, Mark Douthwaite, and Andr\u00e9 Freitas. 2022. Voyager: Data discovery and integration for data science. In Proceedings 25th International Conference on Extending Database Technology (EDBT 2022)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3 2 (2006) 77\u2013101.","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2019. Reflecting on reflexive thematic analysis. Qualitative research in sport exercise and health 11 4 (2019) 589\u2013597.","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313685"},{"key":"e_1_3_3_2_8_2","unstructured":"Sonia Castelo R\u00e9mi Rampin A\u00e9cio Santos Aline Bessa Fernando Chirigati and Juliana Freire. 2021. Auctus: A dataset search engine for data augmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.05716 (2021)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Adriane Chapman Elena Simperl Laura Koesten George Konstantinidis Luis-Daniel Ib\u00e1\u00f1ez Emilia Kacprzak and Paul Groth. 2020. Dataset search: a survey. The VLDB Journal 29 1 (2020) 251\u2013272.","DOI":"10.1007\/s00778-019-00564-x"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589722"},{"key":"e_1_3_3_2_11_2","unstructured":"Mahdi Esmailoghli Christoph Schnell Ren\u00e9e\u00a0J Miller and Ziawasch Abedjan. 2023. Blend: A unified data discovery system. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.02656 (2023)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589409"},{"key":"e_1_3_3_2_13_2","unstructured":"Grace Fan Jin Wang Yuliang Li Dan Zhang and Ren\u00e9e Miller. 2022. Semantics-aware dataset discovery from data lakes with contextualized column-based representation learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.01922 (2022)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00094"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00213"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357074"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Alex Groce Todd Kulesza Chaoqiang Zhang Shalini Shamasunder Margaret Burnett Weng-Keen Wong Simone Stumpf Shubhomoy Das Amber Shinsel Forrest Bice et\u00a0al. 2013. You are the only possible oracle: Effective test selection for end users of interactive machine learning systems. IEEE Transactions on Software Engineering 40 3 (2013) 307\u2013323.","DOI":"10.1109\/TSE.2013.59"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047205"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139644082"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Marti\u00a0A Hearst. 2006. Clustering versus faceted categories for information exploration. Commun. ACM 49 4 (2006) 59\u201361.","DOI":"10.1145\/1121949.1121983"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Jonathan Herzig Thomas M\u00fcller Syrine Krichene and Julian\u00a0Martin Eisenschlos. 2021. Open domain question answering over tables via dense retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.12011 (2021).","DOI":"10.18653\/v1\/2021.naacl-main.43"},{"key":"e_1_3_3_2_22_2","unstructured":"Zezhou Huang Jiaxiang Liu Haonan Wang and Eugene Wu. 2023. The Fast and the Private: Task-based Dataset Search. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.05637 (2023)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3665939.3665959"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533135"},{"key":"e_1_3_3_2_26_2","unstructured":"Moe Kayali Fabian Wenz Nesime Tatbul and \u00c7a\u011fatay Demiralp. 2024. Mind the Data Gap: Bridging LLMs to Enterprise Data Integration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.20331 (2024)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Aamod Khatiwada Grace Fan Roee Shraga Zixuan Chen Wolfgang Gatterbauer Ren\u00e9e\u00a0J Miller and Mirek Riedewald. 2023. Santos: Relationship-based semantic table union search. Proceedings of the ACM on Management of Data 1 1 (2023) 1\u201325.","DOI":"10.1145\/3588689"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Laura Koesten Kathleen Gregory Paul Groth and Elena Simperl. 2021. Talking datasets\u2013understanding data sensemaking behaviours. International journal of human-computer studies 146 (2021) 102562.","DOI":"10.1016\/j.ijhcs.2020.102562"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Laura Koesten Elena Simperl Tom Blount Emilia Kacprzak and Jeni Tennison. 2020. Everything you always wanted to know about a dataset: Studies in data summarisation. International journal of human-computer studies 135 (2020) 102367.","DOI":"10.1016\/j.ijhcs.2019.10.004"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025838"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545693"},{"key":"e_1_3_3_2_32_2","unstructured":"Andrew Kuznetsov Michael\u00a0Xieyang Liu and Aniket Kittur. 2024. Tasks Time and Tools: Quantifying Online Sensemaking Efforts Through a Survey-based Study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.07206 (2024)."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/1056808.1057069"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518896"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657877"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642149"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42 4 (2018) 824\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Gary Marchionini. 2006. Exploratory search: from finding to understanding. Commun. ACM 49 4 (2006) 41\u201346.","DOI":"10.1145\/1121949.1121979"},{"key":"e_1_3_3_2_39_2","unstructured":"Fengran Mo Kelong Mao Ziliang Zhao Hongjin Qian Haonan Chen Yiruo Cheng Xiaoxi Li Yutao Zhu Zhicheng Dou and Jian-Yun Nie. 2024. A survey of conversational search. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.15576 (2024)."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1718918.1718987"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/2187809"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Paul Ouellette Aidan Sciortino Fatemeh Nargesian Bahar\u00a0Ghadiri Bashardoost Erkang Zhu Ken\u00a0Q Pu and Ren\u00e9e\u00a0J Miller. 2021. RONIN: data lake exploration. Proceedings of the VLDB Endowment 14 12 (2021).","DOI":"10.14778\/3476311.3476364"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3406522.3446046"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445618"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Peter Pirolli and Stuart Card. 1999. Information foraging. Psychological review 106 4 (1999) 643.","DOI":"10.1037\/\/0033-295X.106.4.643"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195173321.001.0001"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3020183"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380193"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Francesca Rossi Kristen\u00a0Brent Venable and Toby Walsh. 2008. Preferences in constraint satisfaction and optimization. AI magazine 29 4 (2008) 58\u201358.","DOI":"10.1609\/aimag.v29i4.2202"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/169059.169209"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-396981-1.00002-1"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606806"},{"key":"e_1_3_3_2_53_2","volume-title":"Designing The user interface: Strategies for effective human-computer interaction, 4\/e (New Edition)","author":"Shneiderman Ben","year":"1987","unstructured":"Ben Shneiderman. 1987. Designing The user interface: Strategies for effective human-computer interaction, 4\/e (New Edition). Pearson Education India."},{"key":"e_1_3_3_2_54_2","unstructured":"skrub data. 2025. skrub: A library for data cleaning and preprocessing. https:\/\/github.com\/skrub-data\/skrub. Accessed: 2025-04-07."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Greg Smith Mary Czerwinski Brian Meyers Daniel Robbins George Robertson and Desney\u00a0S Tan. 2006. FacetMap: A scalable search and browse visualization. IEEE Transactions on visualization and computer graphics 12 5 (2006) 797\u2013804.","DOI":"10.1109\/TVCG.2006.142"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Katrina Sostek Daniel\u00a0M Russell Nitesh Goyal Tarfah Alrashed Stella Dugall and Natasha Noy. 2024. Discovering datasets on the web scale: Challenges and recommendations for Google Dataset Search. Harvard Data Science ReviewSpecial Issue 4 (2024).","DOI":"10.1162\/99608f92.4c3e11ca"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642400"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606756"},{"key":"e_1_3_3_2_59_2","unstructured":"Nitya Tarakad. 2024. A Peek Inside: How Snowflake\u2019s New Universal Search Feature Was Built. Snowflake Builders Blog: Data Engineers App Developers AI\/ML & Data Science (February 2024). https:\/\/medium.com\/snowflake\/a-peek-inside-how-snowflakes-new-universal-search-feature-was-built-dfd1188176d0"},{"key":"e_1_3_3_2_60_2","volume-title":"Faceted search","author":"Tunkelang Daniel","year":"2022","unstructured":"Daniel Tunkelang. 2022. Faceted search. Springer Nature."},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Iris Vessey. 1991. Cognitive fit: A theory-based analysis of the graphs versus tables literature. Decision sciences 22 2 (1991) 219\u2013240.","DOI":"10.1111\/j.1540-5915.1991.tb00344.x"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3053175"},{"key":"e_1_3_3_2_63_2","unstructured":"Chi Zhang. 2024. Adding Intelligence to Databricks Search. Databricks Blog (March 2024). https:\/\/www.databricks.com\/blog\/adding-intelligence-to-databricks-search"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271776"},{"key":"e_1_3_3_2_65_2","unstructured":"Yihang Zhao Albert Mero\u00f1o-Pe\u00f1uela and Elena Simperl. 2024. User Experience in Dataset Search Platform Interfaces. arXiv e-prints (2024) arXiv\u20132403."}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Busan Republic of Korea","acronym":"UIST '25"},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747727","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:07:39Z","timestamp":1759010859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747727"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":64,"alternative-id":["10.1145\/3746059.3747727","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747727","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}