{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T07:07:38Z","timestamp":1782803258141,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":141,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100000196","name":"Canada Foundation for Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100000196","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Engineering Research Council","award":["RGPIN-2016-06640"],"award-info":[{"award-number":["RGPIN-2016-06640"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3658955","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T13:14:21Z","timestamp":1717593261000},"page":"1055-1067","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Machine learning data practices through a data curation lens: An evaluation framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-5201","authenticated-orcid":false,"given":"Eshta","family":"Bhardwaj","sequence":"first","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5152-1971","authenticated-orcid":false,"given":"Harshit","family":"Gujral","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2351-0049","authenticated-orcid":false,"given":"Siyi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0620-3007","authenticated-orcid":false,"given":"Ciara","family":"Zogheib","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7370-0978","authenticated-orcid":false,"given":"Tegan","family":"Maharaj","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8364-0593","authenticated-orcid":false,"given":"Christoph","family":"Becker","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_3_1_1","volume-title":"RELLISUR: A Real Low-Light Image Super-Resolution Dataset. Advances in Neural Information Processing Systems.","author":"Aakerberg Andreas","year":"2021","unstructured":"Andreas Aakerberg, Kamal Nasrollahi, and Thomas\u00a0B. Moeslund. 2021. RELLISUR: A Real Low-Light Image Super-Resolution Dataset. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_2_1","doi-asserted-by":"publisher","DOI":"10.1086\/718327"},{"key":"e_1_3_2_3_3_1","doi-asserted-by":"publisher","DOI":"10.1140\/epjds"},{"key":"e_1_3_2_3_4_1","doi-asserted-by":"publisher","unstructured":"Shahriar Akter Grace McCarthy Shahriar Sajib Katina Michael Yogesh\u00a0K. Dwivedi John D\u2019Ambra and K.N. Shen. 2021. Algorithmic bias in data-driven innovation in the age of AI. International Journal of Information Management 60 (Oct. 2021) 102387. https:\/\/doi.org\/10.1016\/j.ijinfomgt.2021.102387","DOI":"10.1016\/j.ijinfomgt.2021.102387"},{"key":"e_1_3_2_3_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/1558689815570092"},{"key":"e_1_3_2_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN52536.2021.9566057"},{"key":"e_1_3_2_3_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41557-021-00716-z"},{"key":"e_1_3_2_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979041"},{"key":"e_1_3_2_3_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12525-022-00537-z"},{"key":"e_1_3_2_3_10_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14668.001.0001"},{"key":"e_1_3_2_3_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24209"},{"key":"e_1_3_2_3_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00041"},{"key":"e_1_3_2_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_3_14_1","first-page":"267","article-title":"Maintaining the Integrity of Digital Archives","volume":"31","author":"Besek M.","year":"2007","unstructured":"June\u00a0M. Besek and Philippa\u00a0S. Loengard. 2007. Maintaining the Integrity of Digital Archives. Columbia Journal of Law & the Arts 31 (2007), 267.","journal-title":"Columbia Journal of Law & the Arts"},{"key":"e_1_3_2_3_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06185-3"},{"key":"e_1_3_2_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468536"},{"key":"e_1_3_2_3_17_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a029. Curran Associates","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-Wei Chang, James\u00a0Y Zou, Venkatesh Saligrama, and Adam\u00a0T Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Advances in Neural Information Processing Systems, Vol.\u00a029. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/a486cd07e4ac3d270571622f4f316ec5-Abstract.html"},{"key":"e_1_3_2_3_18_1","volume-title":"Little Data","author":"Borgman L.","unstructured":"Christine\u00a0L. Borgman. 2017. Big Data, Little Data, No Data: Scholarship in the Networked World. MIT Press."},{"key":"e_1_3_2_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479582"},{"key":"e_1_3_2_3_20_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency. PMLR, 77\u201391","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency. PMLR, 77\u201391. https:\/\/proceedings.mlr.press\/v81\/buolamwini18a.html"},{"key":"e_1_3_2_3_21_1","doi-asserted-by":"publisher","DOI":"10.5334\/dsj-2015-002"},{"key":"e_1_3_2_3_22_1","unstructured":"Digital\u00a0Curation Centre. [n. d.]. What is digital curation?https:\/\/www.dcc.ac.uk\/about\/digital-curation."},{"key":"e_1_3_2_3_23_1","volume-title":"A Dataset for Answering Time-Sensitive Questions. Advances in Neural Information Processing Systems","author":"Chen Wenhu","year":"2021","unstructured":"Wenhu Chen, Xinyi Wang, and William\u00a0Yang Wang. 2021. A Dataset for Answering Time-Sensitive Questions. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_3_24_1","doi-asserted-by":"publisher","DOI":"10.1037\/1040-3590.6.4.284"},{"key":"e_1_3_2_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479010"},{"key":"e_1_3_2_3_26_1","doi-asserted-by":"publisher","DOI":"10.7861\/futurehosp.6-2-94"},{"key":"e_1_3_2_3_27_1","volume-title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers. Advances in Neural Information Processing Systems.","author":"Dell Melissa","year":"2023","unstructured":"Melissa Dell, Jacob Carlson, Tom Bryan, Emily Silcock, Abhishek Arora, Zejiang Shen, Luca D\u2019Amico-Wong, Quan Le, Pablo Querubin, and Leander Heldring. 2023. American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_28_1","unstructured":"Digital Curation Centre. [n. d.]. Glossary. https:\/\/www.dcc.ac.uk\/about\/digital-curation\/glossary"},{"key":"e_1_3_2_3_29_1","volume-title":"Data Feminism","author":"D\u2019Ignazio Catherine","unstructured":"Catherine D\u2019Ignazio and Lauren\u00a0F. Klein. 2023. Data Feminism. MIT Press."},{"key":"e_1_3_2_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2019.01.021"},{"key":"e_1_3_2_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2988715"},{"key":"e_1_3_2_3_32_1","volume-title":"Reliability and Authenticity: The Concepts and Their Implications. Archivaria (May","author":"Duranti Luciana","year":"1995","unstructured":"Luciana Duranti. 1995. Reliability and Authenticity: The Concepts and Their Implications. Archivaria (May 1995), 5\u201310. https:\/\/archivaria.ca\/index.php\/archivaria\/article\/view\/12063"},{"key":"e_1_3_2_3_33_1","doi-asserted-by":"publisher","DOI":"10.2481\/dsj.4.106"},{"key":"e_1_3_2_3_34_1","volume-title":"The InterPARES 2 Project (2002-2007): An Overview. Archivaria","author":"Duranti Luciana","year":"2007","unstructured":"Luciana Duranti. 2007. The InterPARES 2 Project (2002-2007): An Overview. Archivaria (2007), 113\u2013121. https:\/\/www.archivaria.ca\/index.php\/archivaria\/article\/view\/13155"},{"key":"e_1_3_2_3_35_1","volume-title":"The Protection of the Integrity of Electronic Records: An Overview of the UBC-MAS Research Project. Archivaria (Oct","author":"Duranti Luciana","year":"1996","unstructured":"Luciana Duranti and Heather MacNeil. 1996. The Protection of the Integrity of Electronic Records: An Overview of the UBC-MAS Research Project. Archivaria (Oct. 1996), 46\u201367. https:\/\/archivaria.ca\/index.php\/archivaria\/article\/view\/12153"},{"key":"e_1_3_2_3_36_1","unstructured":"GO FAIR. 2017. F1: (Meta) data are assigned globally unique and persistent identifiers. https:\/\/www.go-fair.org\/fair-principles\/f1-meta-data-assigned-globally-unique-persistent-identifiers\/."},{"key":"e_1_3_2_3_37_1","unstructured":"GO FAIR. 2017. I3: (Meta)data include qualified references to other (meta)data. https:\/\/www.go-fair.org\/fair-principles\/i3-metadata-include-qualified-references-metadata\/."},{"key":"e_1_3_2_3_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/2056305118763366"},{"key":"e_1_3_2_3_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00182"},{"key":"e_1_3_2_3_40_1","unstructured":"Samir\u00a0Yitzhak Gadre Gabriel Ilharco Alex Fang Jonathan Hayase Georgios Smyrnis Thao Nguyen Ryan Marten Mitchell Wortsman Dhruba Ghosh Jieyu Zhang Eyal Orgad Rahim Entezari Giannis Daras Sarah\u00a0M. Pratt Vivek Ramanujan Yonatan Bitton Kalyani Marathe Stephen Mussmann Richard Vencu Mehdi Cherti Ranjay Krishna Pang\u00a0Wei Koh Olga Saukh Alexander Ratner Shuran Song Hannaneh Hajishirzi Ali Farhadi Romain Beaumont Sewoong Oh Alex Dimakis Jenia Jitsev Yair Carmon Vaishaal Shankar and Ludwig Schmidt. 2023. DataComp: In search of the next generation of multimodal datasets. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_41_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJPPM-08-2020-0427"},{"key":"e_1_3_2_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372862"},{"key":"e_1_3_2_3_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16809-3"},{"key":"e_1_3_2_3_45_1","unstructured":"GO FAIR. [n. d.]. R1.2: (Meta)data are associated with detailed provenance. https:\/\/www.go-fair.org\/fair-principles\/r1-2-metadata-associated-detailed-provenance\/"},{"key":"e_1_3_2_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00245"},{"key":"e_1_3_2_3_47_1","volume-title":"Computing Inter-Rater Reliability for Observational Data: An Overview and Tutorial. Tutorials in quantitative methods for psychology 8, 1","author":"Hallgren A.","year":"2012","unstructured":"Kevin\u00a0A. Hallgren. 2012. Computing Inter-Rater Reliability for Observational Data: An Overview and Tutorial. Tutorials in quantitative methods for psychology 8, 1 (2012), 23\u201334. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC3402032\/"},{"key":"e_1_3_2_3_48_1","unstructured":"Eric Hambro Roberta Raileanu Danielle Rothermel Vegard Mella Tim Rockt\u00e4schel Heinrich Kuttler and Naila Murray. 2022. Dungeons and Data: A Large-Scale NetHack Dataset. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_49_1","volume-title":"Building Machine Learning Pipelines. \"O\u2019Reilly Media","author":"Hapke Hannes","unstructured":"Hannes Hapke and Catherine Nelson. 2020. Building Machine Learning Pipelines. \"O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_2_3_50_1","unstructured":"Sheikh Md\u00a0Shakeel Hassan Arthur Feeney Akash Dhruv Jihoon Kim Youngjoon Suh Jaiyoung Ryu Yoonjin Won and Aparna Chandramowlishwaran. 2023. BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555760"},{"key":"e_1_3_2_3_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"e_1_3_2_3_53_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.01.012"},{"key":"e_1_3_2_3_55_1","doi-asserted-by":"publisher","DOI":"10.2218\/ijdc.v3i1.48"},{"key":"e_1_3_2_3_56_1","doi-asserted-by":"publisher","DOI":"10.2218\/ijdc.v4i2.93"},{"key":"e_1_3_2_3_57_1","doi-asserted-by":"publisher","unstructured":"Sarah Higgins. 2012. The lifecycle of data management. In Managing Research Data (1 ed.) Graham Pryor (Ed.). Facet 17\u201346. https:\/\/doi.org\/10.29085\/9781856048910.003","DOI":"10.29085\/9781856048910.003"},{"key":"e_1_3_2_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"e_1_3_2_3_59_1","unstructured":"Thibaut Horel Lorenzo Masoero Raj Agrawal Daria Roithmayr and Trevor Campbell. 2021. The CPD Data Set: Personnel Use of Force and Complaints in the Chicago Police Department. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_60_1","unstructured":"Rodrigo Hormazabal Changyoung Park Soonyoung Lee Sehui Han Yeonsik Jo Jaewan Lee Ahra Jo Seung\u00a0Hwan Kim Jaegul Choo Moontae Lee and Honglak Lee. 2022. CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_61_1","unstructured":"Xuanwen Huang Yang Yang Yang Wang Chunping Wang Zhisheng Zhang Jiarong Xu Lei Chen and Michalis Vazirgiannis. 2022. DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_62_1","unstructured":"Zhe Huang Liang Wang Giles Blaney Christopher Slaughter Devon McKeon Ziyu Zhou Robert Jacob and Michael\u00a0C. Hughes. 2021. The Tufts fNIRS Mental Workload Dataset & Benchmark for Brain-Computer Interfaces that Generalize. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445918"},{"key":"e_1_3_2_3_64_1","unstructured":"Information and Privacy Commissioner of Ontario. [n. d.]. Consent may be implied in some cases. https:\/\/www.ipc.on.ca\/part-x-cyfsa\/consent-and-capacity\/elements-of-consent\/consent-may-be-implied-in-some-cases\/"},{"key":"e_1_3_2_3_65_1","volume-title":"CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets. Advances in Neural Information Processing Systems.","author":"Islam Md\u00a0Mofijul","year":"2022","unstructured":"Md\u00a0Mofijul Islam, Reza\u00a0Manuel Mirzaiee, Alexi Gladstone, Haley\u00a0N. Green, and Tariq Iqbal. 2022. CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2021.3113860"},{"key":"e_1_3_2_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372829"},{"key":"e_1_3_2_3_68_1","doi-asserted-by":"publisher","DOI":"10.5172\/mra.455.1.1.27"},{"key":"e_1_3_2_3_70_1","volume-title":"Venkatesh Ramesh, Philippe Brouillard, Yaniv Gurwicz, Chandni Nagda, Jakob Runge, Peer Nowack, and David Rolnick.","author":"Kaltenborn Julia","year":"2023","unstructured":"Julia Kaltenborn, Charlotte Emilie\u00a0Elektra Lange, Venkatesh Ramesh, Philippe Brouillard, Yaniv Gurwicz, Chandni Nagda, Jakob Runge, Peer Nowack, and David Rolnick. 2023. ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_71_1","doi-asserted-by":"publisher","DOI":"10.1561\/0500000064"},{"key":"e_1_3_2_3_72_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4217148"},{"key":"e_1_3_2_3_73_1","unstructured":"Kim Martineau. 2021. What is synthetic data?https:\/\/research.ibm.com\/blog\/what-is-synthetic-data"},{"key":"e_1_3_2_3_74_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0115253"},{"key":"e_1_3_2_3_75_1","volume-title":"Reused and Recycled: The Life of a Dataset in Machine Learning Research. Advances in Neural Information Processing Systems","author":"Koch Bernard","year":"2021","unstructured":"Bernard Koch, Emily Denton, Alex Hanna, and Jacob\u00a0G Foster. 2021. Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_3_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300330"},{"key":"e_1_3_2_3_77_1","unstructured":"Zhengfei Kuang Yunzhi Zhang Hong-Xing Yu Samir Agarwala Shangzhe Wu and Jiajun Wu. 2023. Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_78_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi2336"},{"key":"e_1_3_2_3_79_1","unstructured":"Stefan Larson Gordon Lim Yutong Ai David Kuang and Kevin Leach. 2022. Evaluating Out-of-Distribution Performance on Document Image Classifiers. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_80_1","volume-title":"Proc. of 2021 AAAI\/ACM Conf. on AI, Ethics, and Society. ACM, Virtual Event USA, 695\u2013703","author":"Leavy Susan","year":"2021","unstructured":"Susan Leavy, Eugenia Siapera, and Barry O\u2019Sullivan. 2021. Ethical Data Curation for AI: An Approach based on Feminist Epistemology and Critical Theories of Race. In Proc. of 2021 AAAI\/ACM Conf. on AI, Ethics, and Society. ACM, Virtual Event USA, 695\u2013703. https:\/\/dl.acm.org\/doi\/10.1145\/3461702.3462598"},{"key":"e_1_3_2_3_81_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-019-03228-6"},{"key":"e_1_3_2_3_82_1","unstructured":"Jiyoung Lee Seungho Kim Seunghyun Won Joonseok Lee Marzyeh Ghassemi James Thorne Jaeseok Choi O.-Kil Kwon and Edward Choi. 2023. VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_83_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119298"},{"key":"e_1_3_2_3_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534147"},{"key":"e_1_3_2_3_85_1","unstructured":"Calvin Liang. 2021. Reflexivity positionality and disclosure in HCI. https:\/\/medium.com\/@caliang\/reflexivity-positionality-and-disclosure-in-hci-3d95007e9916"},{"key":"e_1_3_2_3_86_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00516-1"},{"key":"e_1_3_2_3_87_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0486-7"},{"key":"e_1_3_2_3_88_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02430-6"},{"key":"e_1_3_2_3_89_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2018.08.010"},{"key":"e_1_3_2_3_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533175"},{"key":"e_1_3_2_3_91_1","unstructured":"Zelun Luo Zane Durante Linden Li Wanze Xie Ruochen Liu Emily Jin Zhuoyi Huang Lun\u00a0Yu Li Jiajun Wu Juan\u00a0Carlos Niebles Ehsan Adeli and Li Fei-Fei. 2022. MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376445"},{"key":"e_1_3_2_3_93_1","unstructured":"Utkarsh Mall Bharath Hariharan and Kavita Bala. 2022. Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_94_1","unstructured":"Matthew Stewart. 2023. The Olympics of AI: Benchmarking Machine Learning Systems. https:\/\/towardsdatascience.com\/the-olympics-of-ai-benchmarking-machine-learning-systems-c4b2051fbd2b"},{"key":"e_1_3_2_3_95_1","unstructured":"Mantas Mazeika Eric Tang Andy Zou Steven Basart Jun\u00a0Shern Chan Dawn Song David Forsyth Jacob Steinhardt and Dan Hendrycks. 2022. How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_96_1","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.1.1.30"},{"key":"e_1_3_2_3_97_1","volume-title":"The Stanford Encyclopedia of Philosophy (winter 2023 ed.), Edward\u00a0N","author":"McIntyre Alison","year":"2023","unstructured":"Alison McIntyre. 2023. Doctrine of Double Effect. In The Stanford Encyclopedia of Philosophy (winter 2023 ed.), Edward\u00a0N. Zalta and Uri Nodelman (Eds.). Metaphysics Research Lab, Stanford University. https:\/\/plato.stanford.edu\/archives\/win2023\/entries\/double-effect\/"},{"key":"e_1_3_2_3_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_3_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492853"},{"key":"e_1_3_2_3_100_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib"},{"key":"e_1_3_2_3_101_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_3_102_1","doi-asserted-by":"publisher","DOI":"10.2218\/ijdc.v3i1.42"},{"key":"e_1_3_2_3_103_1","unstructured":"Nafise\u00a0Sadat Moosavi Andreas R\u00fcckl\u00e9 Dan Roth and Iryna Gurevych. 2021. SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300356"},{"key":"e_1_3_2_3_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517644"},{"key":"e_1_3_2_3_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445402"},{"key":"e_1_3_2_3_107_1","doi-asserted-by":"publisher","DOI":"10.17723\/aarc.77.1.m49r46526847g587"},{"key":"e_1_3_2_3_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528574"},{"key":"e_1_3_2_3_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533378"},{"key":"e_1_3_2_3_110_1","volume-title":"\u201cPurposeful Work","author":"Palmer L","year":"2013","unstructured":"Carole\u00a0L Palmer, Nicholas\u00a0M Weber, Trevor Mu\u00f1oz, and Allen\u00a0H Renear. 2013. Foundations of Data Curation: The Pedagogy and Practice of \u201cPurposeful Work\u201d with Research Data. (2013)."},{"key":"e_1_3_2_3_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191551"},{"key":"e_1_3_2_3_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287567"},{"key":"e_1_3_2_3_113_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100336"},{"key":"e_1_3_2_3_115_1","unstructured":"Guilherme Penedo Quentin Malartic Daniel Hesslow Ruxandra Cojocaru Hamza Alobeidli Alessandro Cappelli Baptiste Pannier Ebtesam Almazrouei and Julien Launay. 2023. The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_116_1","volume-title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers. Advances in Neural Information Processing Systems","author":"Peng Kenny","year":"2021","unstructured":"Kenny Peng, Arunesh Mathur, and Arvind Narayanan. 2021. Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_3_117_1","volume-title":"Digital curation: a life-cycle approach to managing and preserving usable digital information","author":"Pennock Maureen","year":"2007","unstructured":"Maureen Pennock. 2007. Digital curation: a life-cycle approach to managing and preserving usable digital information.Library and Archives Journal 1 (2007)."},{"key":"e_1_3_2_3_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702298"},{"key":"e_1_3_2_3_119_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10502-014-9236-y"},{"key":"e_1_3_2_3_120_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594014"},{"key":"e_1_3_2_3_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485128"},{"key":"e_1_3_2_3_122_1","unstructured":"Nataniel Ruiz. 2019. Learning to Simulate. https:\/\/towardsdatascience.com\/learning-to-simulate-c53d8b393a56"},{"key":"e_1_3_2_3_123_1","unstructured":"Yuta Saito Shunsuke Aihara Megumi Matsutani and Yusuke Narita. 2021. Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_124_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_3_125_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476058"},{"key":"e_1_3_2_3_126_1","unstructured":"Tal Schuster Ashwin Kalyan Alex Polozov and Adam\u00a0Tauman Kalai. 2021. Programming Puzzles. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_127_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287598"},{"key":"e_1_3_2_3_128_1","volume-title":"Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities. Advances in Neural Information Processing Systems 35 (Dec","author":"Shen Zejiang","year":"2022","unstructured":"Zejiang Shen, Kyle Lo, Lauren Yu, Nathan Dahlberg, Margo Schlanger, and Doug Downey. 2022. Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities. Advances in Neural Information Processing Systems 35 (Dec. 2022), 13158\u201313173. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/552ef803bef9368c29e53c167de34b55-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_3_129_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372870"},{"key":"e_1_3_2_3_130_1","unstructured":"Megan Stanley John Bronskill Krzysztof Maziarz Hubert Misztela Jessica Lanini Marwin Segler Nadine Schneider and Marc Brockschmidt. 2021. FS-Mol: A Few-Shot Learning Dataset of Molecules. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_131_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465416.3483305"},{"key":"e_1_3_2_3_132_1","doi-asserted-by":"publisher","DOI":"10.1177\/0891243220966600"},{"key":"e_1_3_2_3_133_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555139"},{"key":"e_1_3_2_3_134_1","doi-asserted-by":"publisher","DOI":"10.1177\/01634437211060226"},{"key":"e_1_3_2_3_135_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-021-09583-1"},{"key":"e_1_3_2_3_136_1","unstructured":"Junjue Wang Zhuo Zheng Ailong Ma Xiaoyan Lu and Yanfei Zhong. 2021. LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_137_1","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.1996.11518099"},{"key":"e_1_3_2_3_138_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_3_2_3_139_1","unstructured":"Xuhai Xu Han Zhang Yasaman\u00a0S. Sefidgar Yiyi Ren Xin Liu Woosuk Seo Jennifer Brown Kevin\u00a0Scott Kuehn Mike\u00a0A. Merrill Paula\u00a0S. Nurius Shwetak Patel Tim Althoff Margaret\u00a0E. Morris Eve\u00a0A. Riskin Jennifer Mankoff and Anind Dey. 2022. GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_3_140_1","doi-asserted-by":"publisher","DOI":"10.1108\/10650750710831466"},{"key":"e_1_3_2_3_141_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41578-022-00490-5"},{"key":"e_1_3_2_3_142_1","unstructured":"Serena Yeung and Joaquin Vanschoren. 2021. Announcing the NeurIPS 2021 Datasets and Benchmarks Track. https:\/\/neuripsconf.medium.com\/announcing-the-neurips-2021-datasets-and-benchmarks-track-644e27c1e66c"},{"key":"e_1_3_2_3_143_1","unstructured":"Zenodo - Research. Shared.[n. d.]. FAIR Principles. https:\/\/about.zenodo.org\/principles\/"}],"event":{"name":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3658955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:57Z","timestamp":1750287057000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":141,"alternative-id":["10.1145\/3630106.3658955","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3658955","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}