{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:43:53Z","timestamp":1771890233753,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS21021A (ITEA project number 20219)"],"award-info":[{"award-number":["01IS21021A (ITEA project number 20219)"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["02L19C155"],"award-info":[{"award-number":["02L19C155"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1145\/3593078.3593930","type":"proceedings-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T18:07:10Z","timestamp":1687284430000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["AutoCure: Automated Tabular Data Curation Technique for ML Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4561-4761","authenticated-orcid":false,"given":"Mohamed","family":"Abdelaal","sequence":"first","affiliation":[{"name":"Software AG, Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8509-7247","authenticated-orcid":false,"given":"Rashmi","family":"Koparde","sequence":"additional","affiliation":[{"name":"Otto von Guericke University Magdebur, Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-8269","authenticated-orcid":false,"given":"Harald","family":"Schoening","sequence":"additional","affiliation":[{"name":"Software AG, Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Harald Schoening. REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines. In 26th International Conference on Extending Database Technology (EDBT)","author":"Abdelaal Mohamed","year":"2023","unstructured":"Mohamed Abdelaal , Christian Hammacher , and Harald Schoening. REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines. In 26th International Conference on Extending Database Technology (EDBT) , March 2023 . Mohamed Abdelaal, Christian Hammacher, and Harald Schoening. REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines. In 26th International Conference on Extending Database Technology (EDBT), March 2023."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850578.2850579"},{"key":"e_1_3_2_1_5_1","volume-title":"Smart factory: High storage system data for energy optimization","author":"Birgelen Oliver","year":"2018","unstructured":"Oliver Birgelen , Alexander; Niggemann. Smart factory: High storage system data for energy optimization , 2018 . accessed on January 2022. Oliver Birgelen, Alexander; Niggemann. Smart factory: High storage system data for energy optimization, 2018. accessed on January 2022."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations","author":"Cheung Tsz-Him","year":"2020","unstructured":"Tsz-Him Cheung and Dit-Yan Yeung . Modals : Modality-agnostic automated data augmentation in the latent space . In International Conference on Learning Representations , 2020 . Tsz-Him Cheung and Dit-Yan Yeung. Modals: Modality-agnostic automated data augmentation in the latent space. In International Conference on Learning Representations, 2020."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749431"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465327"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"e_1_3_2_1_10_1","volume-title":"UCI machine learning repository","author":"Dua Dheeru","year":"2017","unstructured":"Dheeru Dua and Casey Graff . UCI machine learning repository , 2017 . Dheeru Dua and Casey Graff. UCI machine learning repository, 2017."},{"key":"e_1_3_2_1_11_1","volume-title":"2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). IEEE","author":"Gaudio Daniel Del","year":"2023","unstructured":"Daniel Del Gaudio , Tim Schubert , and Mohamed Abdelaal . RTClean : Context-aware Tabular Data Cleaning using Real-time OFDs . In 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). IEEE , March 2023 . Daniel Del Gaudio, Tim Schubert, and Mohamed Abdelaal. RTClean: Context-aware Tabular Data Cleaning using Real-time OFDs. In 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). IEEE, March 2023."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3163\/1536-5050.101.3.020"},{"key":"e_1_3_2_1_14_1","volume-title":"Boston housing data","author":"Harrison D.","year":"1993","unstructured":"D. Harrison and D.L. Rubinfeld . Boston housing data , 1993 . Accessed on February 2021. D. Harrison and D.L. Rubinfeld. Boston housing data, 1993. Accessed on February 2021."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_3_2_1_16_1","volume-title":"Data errors: Symptoms, causes and origins. Data Engineering, page 4","author":"Ilyas Ihab F","year":"2022","unstructured":"Ihab F Ilyas and Felix Naumann . Data errors: Symptoms, causes and origins. Data Engineering, page 4 , 2022 . Ihab F Ilyas and Felix Naumann. Data errors: Symptoms, causes and origins. Data Engineering, page 4, 2022."},{"key":"e_1_3_2_1_17_1","volume-title":"Xu Chu, and Ce Zhang. Nearest neighbor classifiers over incomplete information: From certain answers to certain predictions. arXiv preprint arXiv:2005.05117","author":"Karla\u0161 Bojan","year":"2020","unstructured":"Bojan Karla\u0161 , Peng Li , Renzhi Wu , Nezihe Merve G\u00fcrel , Xu Chu, and Ce Zhang. Nearest neighbor classifiers over incomplete information: From certain answers to certain predictions. arXiv preprint arXiv:2005.05117 , 2020 . Bojan Karla\u0161, Peng Li, Renzhi Wu, Nezihe Merve G\u00fcrel, Xu Chu, and Ce Zhang. Nearest neighbor classifiers over incomplete information: From certain answers to certain predictions. arXiv preprint arXiv:2005.05117, 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling . Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 , 2013 . Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013."},{"key":"e_1_3_2_1_19_1","first-page":"202","volume-title":"Kdd","volume":"96","author":"Ron","year":"1996","unstructured":"Ron Kohavi et al. Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid . In Kdd , volume 96 , pages 202 -- 207 , 1996 . Ron Kohavi et al. Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. In Kdd, volume 96, pages 202--207, 1996."},{"key":"e_1_3_2_1_20_1","volume-title":"Boostclean: Automated error detection and repair for machine learning. arXiv preprint arXiv:1711.01299","author":"Krishnan Sanjay","year":"2017","unstructured":"Sanjay Krishnan , Michael J Franklin , Ken Goldberg , and Eugene Wu . Boostclean: Automated error detection and repair for machine learning. arXiv preprint arXiv:1711.01299 , 2017 . Sanjay Krishnan, Michael J Franklin, Ken Goldberg, and Eugene Wu. Boostclean: Automated error detection and repair for machine learning. arXiv preprint arXiv:1711.01299, 2017."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407801"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324956"},{"key":"e_1_3_2_1_24_1","volume-title":"Outlier detection in heterogeneous datasets using automatic tuple expansion","author":"Mariet Zelda","year":"2016","unstructured":"Zelda Mariet , Rachael Harding , Sam Madden , Outlier detection in heterogeneous datasets using automatic tuple expansion , 2016 . Zelda Mariet, Rachael Harding, Sam Madden, et al. Outlier detection in heterogeneous datasets using automatic tuple expansion, 2016."},{"issue":"1","key":"e_1_3_2_1_25_1","first-page":"24","article-title":"From cleaning before ml to cleaning for ml","volume":"44","author":"Neutatz Felix","year":"2021","unstructured":"Felix Neutatz , Binger Chen , Ziawasch Abedjan , and Eugene Wu . From cleaning before ml to cleaning for ml . IEEE Data Eng. Bull. , 44 ( 1 ): 24 -- 41 , 2021 . Felix Neutatz, Binger Chen, Ziawasch Abedjan, and Eugene Wu. From cleaning before ml to cleaning for ml. IEEE Data Eng. Bull., 44(1):24--41, 2021.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358129"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824086"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368293"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220109"},{"key":"e_1_3_2_1_30_1","volume-title":"Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820","author":"Rekatsinas Theodoros","year":"2017","unstructured":"Theodoros Rekatsinas , Xu Chu , Ihab F Ilyas , and Christopher R\u00e9 . Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820 , 2017 . Theodoros Rekatsinas, Xu Chu, Ihab F Ilyas, and Christopher R\u00e9. Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820, 2017."},{"key":"e_1_3_2_1_31_1","first-page":"6151","volume-title":"IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium","author":"Felix","year":"2018","unstructured":"Felix M. Riese and Sina Keller. Introducing a Framework of Self-Organizing Maps for Regression of Soil Moisture with Hyperspectral Data . In IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium , pages 6151 -- 6154 , Valencia, Spain , July 2018 . Felix M. Riese and Sina Keller. Introducing a Framework of Self-Organizing Maps for Regression of Soil Moisture with Hyperspectral Data. In IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, pages 6151--6154, Valencia, Spain, July 2018."},{"key":"e_1_3_2_1_32_1","volume-title":"A mathematical theory of communication. ACM SIGMOBILE mobile computing and communications review, 5(1):3--55","author":"Shannon Claude Elwood","year":"2001","unstructured":"Claude Elwood Shannon . A mathematical theory of communication. ACM SIGMOBILE mobile computing and communications review, 5(1):3--55 , 2001 . Claude Elwood Shannon. A mathematical theory of communication. ACM SIGMOBILE mobile computing and communications review, 5(1):3--55, 2001."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597"},{"key":"e_1_3_2_1_34_1","volume-title":"Nasa airfoil self-noise dataset","author":"Brooks D. Stuart Pope","year":"2014","unstructured":"D. Stuart Pope Thomas F. Brooks and Michael A. Marcolini . Nasa airfoil self-noise dataset , 2014 . accessed on January 2022. D. Stuart Pope Thomas F. Brooks and Michael A. Marcolini. Nasa airfoil self-noise dataset, 2014. accessed on January 2022."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21062140"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.4108\/trans.sis.2013.01-03.e2"}],"event":{"name":"aiDM '23: Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","location":"Seattle WA USA","acronym":"aiDM '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593078.3593930","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3593078.3593930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:19Z","timestamp":1750178239000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3593078.3593930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":36,"alternative-id":["10.1145\/3593078.3593930","10.1145\/3593078"],"URL":"https:\/\/doi.org\/10.1145\/3593078.3593930","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]},"assertion":[{"value":"2023-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}