{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:49:10Z","timestamp":1782762550063,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":154,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2016-06640"],"award-info":[{"award-number":["RGPIN-2016-06640"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2025-07063"],"award-info":[{"award-number":["RGPIN-2025-07063"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Canada Foundation for Innovation","doi-asserted-by":"publisher","award":["No Number"],"award-info":[{"award-number":["No Number"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ontario Research Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3812411","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"6903-6955","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-5201","authenticated-orcid":false,"given":"Eshta","family":"Bhardwaj","sequence":"first","affiliation":[{"name":"Faculty of Information, University of Toronto, Toronto, Ontario, 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, Toronto, Ontario, 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, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. https:\/\/alliedmedia.org\/projects\/our-data-bodies-odb"},{"key":"e_1_3_2_1_2_1","unstructured":"2021. Call For Datasets and Benchmarks - NeurIPS. https:\/\/web.archive.org\/web\/20210407213644\/https:\/\/neurips.cc\/Conferences\/2021\/CallForDatasetsBenchmarks"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. Call For Datasets and Benchmarks - NeurIPS. https:\/\/web.archive.org\/web\/20220521130452\/https:\/\/neurips.cc\/Conferences\/2022\/CallForDatasetsBenchmarks"},{"key":"e_1_3_2_1_4_1","unstructured":"2023. Call For Datasets and Benchmarks - NeurIPS. https:\/\/web.archive.org\/web\/20230325021706\/https:\/\/neurips.cc\/Conferences\/2023\/CallForDatasetsBenchmarks"},{"key":"e_1_3_2_1_5_1","unstructured":"2024. Call For Datasets and Benchmarks - NeurIPS. https:\/\/neurips.cc\/Conferences\/2024\/CallForDatasetsBenchmarks"},{"key":"e_1_3_2_1_6_1","volume-title":"Stephen Ra, Richard Bonneau, and Mohammed AlQuraishi.","author":"Ahdritz Gustaf","year":"2023","unstructured":"Gustaf Ahdritz, Nazim Bouatta, Sachin Kadyan, Lukas Jarosch, Dan Berenberg, Ian Fisk, Andrew Martin Watkins, Stephen Ra, Richard Bonneau, and Mohammed AlQuraishi. 2023. OpenProteinSet: Training data for structural biology at scale. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.1004"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375688"},{"key":"e_1_3_2_1_9_1","volume-title":"Corpus-Assisted Discourse Studies","author":"Ancarno Clyde","unstructured":"Clyde Ancarno. 2020. Corpus-Assisted Discourse Studies. In The Cambridge Handbook of Discourse Studies, Alexandra Georgakopoulou and Anna De Fina (Eds.). Cambridge University Press, Cambridge, 165\u2013185."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Gabriele Bammer. 2017. Toolkits for transdisciplinary research. https:\/\/i2insights.org\/2017\/07\/25\/toolkits-for-transdisciplinarity\/","DOI":"10.14512\/gaia.25.2.2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979041"},{"key":"e_1_3_2_1_12_1","unstructured":"Bj\u00f6rn Barz and Joachim Denzler. 2021. WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14668.001.0001"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593974"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658955"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1698"},{"key":"e_1_3_2_1_18_1","volume-title":"Natural language processing with Python. O'Reilly","author":"Bird Steven","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python. O'Reilly, Cambridge."},{"key":"e_1_3_2_1_19_1","volume-title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Bordes Florian","unstructured":"Florian Bordes, Shashank Shekhar, Mark Ibrahim, Diane Bouchacourt, Pascal Vincent, and Ari S. Morcos. 2023. PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_20_1","volume-title":"Pascalian meditations","author":"Bourdieu Pierre","unstructured":"Pierre Bourdieu. 2000. Pascalian meditations. Stanford University Press, Stanford, Calif."},{"key":"e_1_3_2_1_21_1","volume-title":"Science of Science and Reflexivity","author":"Bourdieu Pierre","unstructured":"Pierre Bourdieu. 2004. Science of Science and Reflexivity. University of Chicago Press, Chicago, IL."},{"key":"e_1_3_2_1_22_1","volume-title":"QUINTA: Reflexive Sensibility For Responsible AI Research and Data-Driven Processes. doi:abs\/2509.16347v1","author":"Boyd Alicia E","year":"2023","unstructured":"Alicia E Boyd. 2023. QUINTA: Reflexive Sensibility For Responsible AI Research and Data-Driven Processes. doi:abs\/2509.16347v1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479582"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/capr.12360"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10805-024-09539-2"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11135-021-01182-y"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501998"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-023-02178-5"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Kasia S. Chmielinski Sarah Newman Matt Taylor Josh Joseph Kemi Thomas Jessica Yurkofsky and Yue Chelsea Qiu. 2022. The Dataset Nutrition Label (2nd Gen): Leveraging Context to Mitigate Harms in Artificial Intelligence. doi:10.48550\/arXiv.2201.03954","DOI":"10.48550\/arXiv.2201.03954"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS-D-24-0203.1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732058"},{"key":"e_1_3_2_1_33_1","volume-title":"Randall","author":"Curran Melissa","year":"2021","unstructured":"Melissa Curran and Ashley K. Randall. 2021. Positionality Statements. https:\/\/onlinelibrary.wiley.com\/pb-assets\/assets\/14756811\/Positionality-Statements.pdf"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/1369118X.2024.2315285"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18778\/1733-8077.8.1.04"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1177\/20539517251330191"},{"key":"e_1_3_2_1_37_1","volume-title":"Eli VanderBilt, Aniruddha Kembhavi","author":"Deitke Matt","year":"2023","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, and Ali Farhadi. 2023. Objaverse-XL: A Universe of 10M+ 3D Objects. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_38_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'Amico-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_1_39_1","doi-asserted-by":"publisher","DOI":"10.1177\/20539517211035955"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23903"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2844110"},{"key":"e_1_3_2_1_43_1","unstructured":"Catherine D'Ignazio and Lauren Klein. 2020. 7. Show Your Work. In Data Feminism. https:\/\/data-feminism.mitpress.mit.edu\/pub\/0vgzaln4\/release\/3"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-6-35"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11805.001.0001"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29332-0_8"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/01419870.2011.606910"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.0033-0124.1994.00080.x"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1177\/146879410200200205"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2648.2009.05173.x"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1177\/14687941221098922"},{"key":"e_1_3_2_1_52_1","volume-title":"Philipp Christian Petersen, and Julius Berner","author":"Frieder Simon","year":"2023","unstructured":"Simon Frieder, Luca Pinchetti, Alexis Chevalier, Ryan-Rhys Griffiths, Tommaso Salvatori, Thomas Lukasiewicz, Philipp Christian Petersen, and Julius Berner. 2023. Mathematical Capabilities of ChatGPT. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_53_1","volume-title":"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.","author":"Gadre Samir Yitzhak","year":"2023","unstructured":"Samir Yitzhak 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 M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei 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_1_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23101301"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0724"},{"key":"e_1_3_2_1_56_1","volume-title":"Hanna Wallach, Hal Daum\u00e9 III, and Kate Crawford.","author":"Gebru Timnit","year":"2018","unstructured":"Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daum\u00e9 III, and Kate Crawford. 2018. Datasheets for Datasets. arXiv:1803.09010 (2018). http:\/\/arxiv.org\/abs\/1803.09010 arXiv:1803.09010 [cs]."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc\/fqac075"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00245"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11575-023-00507-3"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.2307\/3178066"},{"key":"e_1_3_2_1_62_1","first-page":"567","article-title":"After the Neutrality Ideal: Science, Politics, and \u201cStrong Objectivity","volume":"59","author":"Harding Sandra","year":"1992","unstructured":"Sandra Harding. 1992. After the Neutrality Ideal: Science, Politics, and \u201cStrong Objectivity\u201d. Social Research 59, 3 (1992), 567\u2013587. https:\/\/www.jstor.org\/stable\/40970706","journal-title":"Social Research"},{"key":"e_1_3_2_1_63_1","first-page":"437","article-title":"Rethinking Standpoint Epistemology: What Is \u201cStrong Objectivity?","volume":"36","author":"Harding Sandra","year":"1992","unstructured":"Sandra Harding. 1992. Rethinking Standpoint Epistemology: What Is \u201cStrong Objectivity?\u201d. The Centennial Review 36, 3 (1992), 437\u2013470. https:\/\/www.jstor.org\/stable\/23739232","journal-title":"The Centennial Review"},{"key":"e_1_3_2_1_64_1","unstructured":"Sheikh Md Shakeel 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_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555760"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","unstructured":"Anna Heinke LingLing Huang Kyongmi U. Simpkins Fritz Gerald P. Kalaw Apoorva Karsolia Kiratjit Singh Sanjay Soundarajan Camille Nebeker Sally L. Baxter Cecilia S. Lee Aaron Y. Lee Bhavesh Patel and the AI-READI Consortium. 2025. Dataset Documentation for Responsible AI: Analysis of Suitability and Usage for Health Datasets. doi:10.1101\/2025.11.18.689064","DOI":"10.1101\/2025.11.18.689064"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1080\/02691728.2013.793754"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781483384740.n27"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1177\/13548565221132243"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01203-8"},{"key":"e_1_3_2_1_71_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_1_72_1","volume-title":"Jaegul Choo, Moontae Lee, and Honglak Lee.","author":"Hormazabal Rodrigo","year":"2022","unstructured":"Rodrigo Hormazabal, Changyoung Park, Soonyoung Lee, Sehui Han, Yeonsik Jo, Jaewan Lee, Ahra Jo, Seung Hwan 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_1_73_1","volume-title":"Hughes","author":"Huang Zhe","year":"2021","unstructured":"Zhe Huang, Liang Wang, Giles Blaney, Christopher Slaughter, Devon McKeon, Ziyu Zhou, Robert Jacob, and Michael C. 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_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445918"},{"key":"e_1_3_2_1_75_1","unstructured":"Othering & Belonging Institute. 2025. Power Analysis. https:\/\/belonging.berkeley.edu\/transformative-research-toolkit\/power-analysis"},{"key":"e_1_3_2_1_76_1","volume-title":"Alexi Gladstone, Haley N. Green, and Tariq Iqbal.","author":"Islam Md Mofijul","year":"2022","unstructured":"Md Mofijul Islam, Reza Manuel Mirzaiee, Alexi Gladstone, Haley N. 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_1_77_1","doi-asserted-by":"publisher","DOI":"10.1177\/1609406919870075"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1111\/spc3.12735"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372829"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732013"},{"key":"e_1_3_2_1_81_1","unstructured":"Gaoussou Youssouf Kebe Padraig Higgins Patrick Jenkins Kasra Darvish Rishabh Sachdeva Ryan Barron John Winder Donald Engel Edward Raff Francis Ferraro and Cynthia Matuszek. 2021. A Spoken Language Dataset of Descriptions for Speech-Based Grounded Language Learning. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1080\/0142569042000236998"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1177\/1932296818796508"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","unstructured":"Mehtab Khan and Alex Hanna. 2022. The Subjects and Stages of AI Dataset Development: A Framework for Dataset Accountability. (2022). doi:10.2139\/ssrn.4217148","DOI":"10.2139\/ssrn.4217148"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780197571149.001.0001"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658981"},{"key":"e_1_3_2_1_87_1","volume-title":"Biao Zhang, Xavier Garcia, Derrick Xin, Aditya Kusupati, Romi Stella, Ankur Bapna, and Orhan Firat.","author":"Kudugunta Sneha","year":"2023","unstructured":"Sneha Kudugunta, Isaac Rayburn Caswell, Biao Zhang, Xavier Garcia, Derrick Xin, Aditya Kusupati, Romi Stella, Ankur Bapna, and Orhan Firat. 2023. MADLAD-400: A Multilingual And Document-Level Large Audited Dataset. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_88_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_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732179"},{"key":"e_1_3_2_1_90_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_1_91_1","volume-title":"Peng Xu, Feijun Jiang, Yuxiang Hu, Chen Shi, and Pascale Fung.","author":"Lin Zhaojiang","year":"2021","unstructured":"Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, Peng Xu, Feijun Jiang, Yuxiang Hu, Chen Shi, and Pascale Fung. 2021. BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1177\/1468794120946988"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1515\/jwl-2022-0004"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"crossref","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.","DOI":"10.52202\/068431-1993"},{"key":"e_1_3_2_1_95_1","unstructured":"Jiayuan Mao Xuelin Yang Xikun Zhang Noah Goodman and Jiajun Wu. 2022. CLEVRER-Humans: Describing Physical and Causal Events the Human Way. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1177\/1206331202238962"},{"key":"e_1_3_2_1_97_1","unstructured":"William Mattingly. 2021. Introduction to Topic Modeling and Text Classification. https:\/\/topic-modeling.pythonhumanities.com\/intro.html"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022967012774"},{"key":"e_1_3_2_1_99_1","volume-title":"SCAMPS: Synthetics for Camera Measurement of Physiological Signals. Advances in Neural Information Processing Systems.","author":"McDuff Daniel","year":"2022","unstructured":"Daniel McDuff, Miah Wander, Xin Liu, Brian L. Hill, Javier Hernandez, Jonathan Lester, and Tadas Baltrusaitis. 2022. SCAMPS: Synthetics for Camera Measurement of Physiological Signals. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1177\/0044118X13501343"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1145\/3594737"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445880"},{"key":"e_1_3_2_1_103_1","unstructured":"Nafise Sadat 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_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300356"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517644"},{"key":"e_1_3_2_1_106_1","volume-title":"Khapra","author":"Nc Gokul","year":"2022","unstructured":"Gokul Nc, Manideep Ladi, Sumit Negi, Prem Selvaraj, Pratyush Kumar, and Mitesh M. Khapra. 2022. Addressing Resource Scarcity across Sign Languages with Multilingual Pretraining and Unified-Vocabulary Datasets. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_107_1","volume-title":"Meta-Ethnography: Synthesizing Qualitative Studies","author":"Noblit George W.","unstructured":"George W. Noblit and R. Dwight Hare. 1988. Meta-Ethnography: Synthesizing Qualitative Studies. SAGE Publications."},{"key":"e_1_3_2_1_108_1","volume-title":"Eunsol Choi, and Greg Durrett.","author":"Onoe Yasumasa","year":"2021","unstructured":"Yasumasa Onoe, Michael JQ Zhang, Eunsol Choi, and Greg Durrett. 2021. CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1177\/1609406919899220"},{"key":"e_1_3_2_1_110_1","volume-title":"Chen Qian, Wayne Wu, Dahua Lin, and Kwan-Yee Lin.","author":"Pan Dongwei","year":"2023","unstructured":"Dongwei Pan, Long Zhuo, Jingtan Piao, Huiwen Luo, Wei Cheng, Yuxin Wang, Siming Fan, Shengqi Liu, Lei Yang, Bo Dai, Ziwei Liu, Chen Change Loy, Chen Qian, Wayne Wu, Dahua Lin, and Kwan-Yee Lin. 2023. RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594049"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287567"},{"key":"e_1_3_2_1_113_1","volume-title":"Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Edouard Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research (2011). https:\/\/inria.hal.science\/hal-00650905"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"crossref","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.","DOI":"10.52202\/075280-3464"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1080\/0951839032000060635"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533201"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732114"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533231"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372873"},{"key":"e_1_3_2_1_120_1","volume-title":"Stephanie Tan, Ashraful Islam, Ekin Gedik, and Hayley Hung.","author":"Raman Chirag","year":"2022","unstructured":"Chirag Raman, Jose Vargas Quiros, Stephanie Tan, Ashraful Islam, Ekin Gedik, and Hayley Hung. 2022. ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.3389\/fhumd.2023.1144668"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.4000\/configuracoes.15157"},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659030"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533239"},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"crossref","unstructured":"Kate Sanders Reno Kriz Anqi Liu and Benjamin Van Durme. 2022. Ambiguous Images With Human Judgments for Robust Visual Event Classification. Advances in Neural Information Processing Systems.","DOI":"10.52202\/068431-0191"},{"key":"e_1_3_2_1_127_1","volume-title":"MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Scepanovic Sanja","year":"2023","unstructured":"Sanja Scepanovic, Ivica Obadic, Sagar Joglekar, Laura Giustarini, Cristiano Nattero, Daniele Quercia, and Xiao Xiang Zhu. 2023. MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476058"},{"key":"e_1_3_2_1_129_1","first-page":"49","article-title":"Words alone: Dismantling topic models in the humanities","volume":"2","author":"Schmidt Benjamin M","year":"2012","unstructured":"Benjamin M Schmidt. 2012. Words alone: Dismantling topic models in the humanities. Journal of Digital Humanities 2, 1 (2012), 49\u201365.","journal-title":"Journal of Digital Humanities"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533192"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732079"},{"key":"e_1_3_2_1_132_1","unstructured":"Tal Schuster Ashwin Kalyan Alex Polozov and Adam Tauman Kalai. 2021. Programming Puzzles. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_133_1","volume-title":"DigitalSTS: a field guide for science & technology studies, Janet Vertesi, David Ribes, Carl DiSalvo, Laura Forlano, Steven J","author":"Seaver Nick","unstructured":"Nick Seaver. 2019. Knowing Algorithms. In DigitalSTS: a field guide for science & technology studies, Janet Vertesi, David Ribes, Carl DiSalvo, Laura Forlano, Steven J. Jackson, Yanni Alexander Loukissas, Daniela K. Rosner, and Hanna Rose Shell (Eds.). Princeton University Press, Princeton, New Jersey."},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1002\/jee.20377"},{"key":"e_1_3_2_1_135_1","unstructured":"Raesetje Sefala Timnit Gebru Luzango Mfupe Nyalleng Moorosi and Richard Klein. 2021. Constructing a Visual Dataset to Study the Effects of Spatial Apartheid in South Africa. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_136_1","volume-title":"PROSPECT: Labeled Tandem Mass Spectrometry Dataset for Machine Learning in Proteomics. Advances in Neural Information Processing Systems.","author":"Shouman Omar","year":"2022","unstructured":"Omar Shouman, Wassim Gabriel, Victor-George Giurcoiu, Vitor Sternlicht, and Mathias Wilhelm. 2022. PROSPECT: Labeled Tandem Mass Spectrometry Dataset for Machine Learning in Proteomics. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_137_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658931"},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1080\/15265161"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1049096519002233"},{"key":"e_1_3_2_1_140_1","unstructured":"Moein Sorkhei Yue Liu Hossein Azizpour Edward Azavedo Karin Dembrower Dimitra Ntoula Athanasios Zouzos Fredrik Strand and Kevin Smith. 2021. CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_141_1","first-page":"7","article-title":"Located accountabilities in technology production","volume":"14","author":"Suchman Lucy","year":"2002","unstructured":"Lucy Suchman. 2002. Located accountabilities in technology production. Scandinavian Journal of Information Systems 14, 2 (2002), 7.","journal-title":"Scandinavian Journal of Information Systems"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465416.3483305"},{"key":"e_1_3_2_1_143_1","volume-title":"KeSpeech: An Open Source Speech Dataset of Mandarin and Its Eight Subdialects. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Tang Zhiyuan","year":"2021","unstructured":"Zhiyuan Tang, Dong Wang, Yanguang Xu, Jianwei Sun, Xiaoning Lei, Shuaijiang Zhao, Cheng Wen, Xingjun Tan, Chuandong Xie, Shuran Zhou, Rui Yan, Chenjia Lv, Yang Han, Wei Zou, and Xiangang Li. 2021. KeSpeech: An Open Source Speech Dataset of Mandarin and Its Eight Subdialects. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.eee0b0da"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555139"},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.1177\/01634437211060226"},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174014"},{"key":"e_1_3_2_1_148_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_1_149_1","volume-title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos. Advances in Neural Information Processing Systems.","author":"Wu Bo","year":"2021","unstructured":"Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B. Tenenbaum, and Chuang Gan. 2021. STAR: A Benchmark for Situated Reasoning in Real-World Videos. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_150_1","unstructured":"Tong Xia Dimitris Spathis Chlo{\\\u201ce} Brown J. Ch Andreas Grammenos Jing Han Apinan Hasthanasombat Erika Bondareva Ting Dang Andres Floto Pietro Cicuta and Cecilia Mascolo. 2021. COVID-19 Sounds: A Large-Scale Audio Dataset for Digital Respiratory Screening. Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acalib.2020.102217"},{"key":"e_1_3_2_1_152_1","unstructured":"Xinyu Yang Weixin Liang and James Zou. 2023. Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace. https:\/\/openreview.net\/forum?id=xC8xh2RSs2"},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.5040\/9798216187226.ch-005"},{"key":"e_1_3_2_1_154_1","volume-title":"Software Framework for Topic Modelling with Large Corpora","author":"\u0158eh\u016f\u0159ek Radim","unstructured":"Radim \u0158eh\u016f\u0159ek and Petr Sojka. 2010. Software Framework for Topic Modelling with Large Corpora. University of Malta. https:\/\/repozitar.cz\/publication\/15725\/cs\/Software-Framework-for-Topic-Modelling-with-Large-Corpora\/Rehurek-Sojka"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3812411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:24:21Z","timestamp":1782761061000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3812411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":154,"alternative-id":["10.1145\/3805689.3812411","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3812411","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}