{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:35:29Z","timestamp":1774949729552,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["2030859"],"award-info":[{"award-number":["2030859"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1763423, IIS-1943971,IIS-1916505, OAC-1934464"],"award-info":[{"award-number":["CCF-1763423, IIS-1943971,IIS-1916505, OAC-1934464"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517864","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"217-231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["DataPrism: Exposing Disconnect between Data and Systems"],"prefix":"10.1145","author":[{"given":"Sainyam","family":"Galhotra","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Fariha","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raoni","family":"Louren\u00e7o","sequence":"additional","affiliation":[{"name":"New York University, NYC, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juliana","family":"Freire","sequence":"additional","affiliation":[{"name":"New York University, NYC, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandra","family":"Meliou","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Divesh","family":"Srivastava","sequence":"additional","affiliation":[{"name":"AT&T Chief Data Office, Bedminster, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0389-y"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01865-7"},{"key":"e_1_3_2_2_3_1","unstructured":"AdaBoost Classifier. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.AdaBoostClassifier.html"},{"key":"e_1_3_2_2_4_1","volume-title":"Contextual String Embeddings for Sequence Labeling. In COLING 2018, 27th International Conference on Computational Linguistics. 1638--1649","author":"Akbik Alan","year":"2018","unstructured":"Alan Akbik, Duncan Blythe, and Roland Vollgraf. 2018. Contextual String Embeddings for Sequence Labeling. In COLING 2018, 27th International Conference on Computational Linguistics. 1638--1649."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of USENIX OSDI","author":"Attariyan Mona","year":"2012","unstructured":"Mona Attariyan, Michael Chow, and Jason Flinn. 2012. X-Ray: Automating Root-Cause Diagnosis of Performance Anomalies in Production Software. In Proceedings of USENIX OSDI (Hollywood, CA, USA) (OSDI'12). USENIX Association, USA, 307--320."},{"key":"e_1_3_2_2_6_1","volume-title":"Automating Configuration Troubleshooting with ConfAid. ;login: 36, 1","author":"Attariyan Mona","year":"2011","unstructured":"Mona Attariyan and Jason Flinn. 2011. Automating Configuration Troubleshooting with ConfAid. ;login: 36, 1 (2011), 1--14."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035928"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276518"},{"key":"e_1_3_2_2_9_1","volume-title":"Berger","author":"Barowy Daniel W.","year":"2014","unstructured":"Daniel W. Barowy, Dimitar Gochev, and Emery D. Berger. 2014. CheckCell: data debugging for spreadsheets. In OOPSLA. 507--523."},{"key":"e_1_3_2_2_10_1","volume-title":"et al","author":"Bellamy Rachel KE","year":"2018","unstructured":"Rachel KE Bellamy, Kuntal Dey, Michael Hind, Samuel C Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, et al . 2018. AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv preprint arXiv:1810.01943 (2018)."},{"key":"e_1_3_2_2_11_1","unstructured":"Bias in Amazon Hiring. https:\/\/becominghuman.ai\/amazons-sexist-ai-recruiting-tool-how-did-it-go-so-wrong-e3d14816d98e"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320246"},{"key":"e_1_3_2_2_13_1","volume-title":"Conference on Systems and Machine Learning (SysML). https:\/\/www. sysml. cc\/doc\/2019\/167","author":"Breck Eric","year":"2019","unstructured":"Eric Breck, Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang, and Martin Zinkevich. 2019. Data validation for machine learning. In Conference on Systems and Machine Learning (SysML). https:\/\/www. sysml. cc\/doc\/2019\/167. pdf."},{"key":"e_1_3_2_2_14_1","volume-title":"ICML Workshop on Reliable Machine Learning in the Wild.","author":"Cadamuro Gabriel","year":"2016","unstructured":"Gabriel Cadamuro, Ran Gilad-Bachrach, and Xiaojin Zhu. 2016. Debugging machine learning models. In ICML Workshop on Reliable Machine Learning in the Wild."},{"key":"e_1_3_2_2_15_1","unstructured":"Cardiovascular Disease dataset. https:\/\/www.kaggle.com\/sulianova\/cardiovascular-disease-dataset"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2938503.2938519"},{"key":"e_1_3_2_2_17_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 655--670","author":"Casalicchio Giuseppe","year":"2018","unstructured":"Giuseppe Casalicchio, Christoph Molnar, and Bernd Bischl. 2018. Visualizing the feature importance for black box models. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 655--670."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2002.1029005"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915245"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732962"},{"key":"e_1_3_2_2_22_1","volume-title":"Combinatorial group testing and its applications","author":"Du Dingzhu","unstructured":"Dingzhu Du, Frank K Hwang, and Frank Hwang. 2000. Combinatorial group testing and its applications. Vol. 12. World Scientific."},{"key":"e_1_3_2_2_23_1","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_3_2_2_24_1","first-page":"1","article-title":"Interpretable and Informative Explanations of Outcomes","volume":"8","author":"Gebaly Kareem El","year":"2014","unstructured":"Kareem El Gebaly, Parag Agrawal, Lukasz Golab, Flip Korn, and Divesh Srivastava. 2014. Interpretable and Informative Explanations of Outcomes. PVLDB 8, 1 (Sept. 2014), 61--72.","journal-title":"PVLDB"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.208"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Anna Fariha Suman Nath and Alexandra Meliou. 2020. Causality-Guided Adaptive Interventional Debugging. In SIGMOD. 431--446.","DOI":"10.1145\/3318464.3389694"},{"key":"e_1_3_2_2_27_1","volume-title":"Conformance Constraint Discovery: Measuring Trust in Data- Driven Systems. In SIGMOD '21: International Conference on Management of Data","author":"Fariha Anna","year":"2021","unstructured":"Anna Fariha, Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani, and Alexandra Meliou. 2021. Conformance Constraint Discovery: Measuring Trust in Data- Driven Systems. In SIGMOD '21: International Conference on Management of Data, Virtual Event, China, June 20--25, 2021. ACM, 499--512."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2012.14"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2019.00161"},{"key":"e_1_3_2_2_32_1","volume-title":"Hanna M. Wallach, Hal Daum\u00e9 III, and Kate Crawford.","author":"Gebru Timnit","year":"2018","unstructured":"Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna M. Wallach, Hal Daum\u00e9 III, and Kate Crawford. 2018. Datasheets for Datasets. CoRR abs\/1803.09010 (2018). arXiv:1803.09010"},{"key":"e_1_3_2_2_33_1","volume-title":"Molnar","author":"Godefroid Patrice","year":"2008","unstructured":"Patrice Godefroid, Michael Y. Levin, and David A. Molnar. 2008. Automated whitebox fuzz testing. In Proceedings of NDSS. 151--166."},{"key":"e_1_3_2_2_34_1","unstructured":"Google Vision Racism. https:\/\/algorithmwatch.org\/en\/story\/google-vision-racism\/"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264586"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.411.0004"},{"key":"e_1_3_2_2_37_1","unstructured":"Joseph M Hellerstein. 2008. Quantitative Data Cleaning for Large Databases. (2008)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44829-2_17"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of USENIX Security Symposium. 445--458","author":"Holler Christian","year":"2012","unstructured":"Christian Holler, Kim Herzig, and Andreas Zeller. 2012. Fuzzing with code fragments. In Proceedings of USENIX Security Symposium. 445--458."},{"key":"e_1_3_2_2_40_1","unstructured":"IBM AIF 360. https:\/\/aif360.mybluemix.net\/"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007641"},{"key":"e_1_3_2_2_42_1","unstructured":"IMDb Dataset. https:\/\/www.kaggle.com\/lakshmi25npathi\/imdb-dataset-of-50k-movie-reviews"},{"key":"e_1_3_2_2_43_1","unstructured":"Md Shahriar Iqbal Rahul Krishna Mohammad Ali Javidian Baishakhi Ray and Pooyan Jamshidi. [n.d.]. CADET: A Systematic Method For Debugging Miscon- figurations using Counterfactual Reasoning. ([n. d.])."},{"key":"e_1_3_2_2_44_1","unstructured":"Is Amazon same-day delivery service racist? 2016. The Christian Science Monitor. https:\/\/www.csmonitor.com\/Business\/2016\/0423\/Is-Amazon-same-day-delivery-service-racist"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380377"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.219"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2678025.2701399"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT.2013.6726852"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0412-3"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1064978.1065014"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321438"},{"key":"e_1_3_2_2_52_1","volume-title":"Shasha","author":"Louren\u00e7o Raoni","year":"2020","unstructured":"Raoni Louren\u00e7o, Juliana Freire, and Dennis E. Shasha. 2020. BugDoc: Algorithms to Debug Computational Processes. In SIGMOD. 463--478."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.28"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_2_55_1","volume-title":"Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering. 631--634","author":"Brun Yuriy","year":"2013","unstructured":"K?van\u00e7 Mu?lu, Yuriy Brun, and Alexandra Meliou. 2013. Data debugging with continuous testing. In Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering. 631--634."},{"key":"e_1_3_2_2_56_1","first-page":"1082","article-title":"Functional dependency discovery: An experimental evaluation of seven algorithms","volume":"8","author":"Papenbrock Thorsten","year":"2015","unstructured":"Thorsten Papenbrock, Jens Ehrlich, Jannik Marten, Tommy Neubert, Jan-Peer Rudolph, Martin Sch\u00f6nberg, Jakob Zwiener, and Felix Naumann. 2015. Functional dependency discovery: An experimental evaluation of seven algorithms. PLDB 8, 10 (2015), 1082--1093.","journal-title":"PLDB"},{"key":"e_1_3_2_2_57_1","first-page":"774","article-title":"Divide & conquer-based inclusion dependency discovery","volume":"8","author":"Papenbrock Thorsten","year":"2015","unstructured":"Thorsten Papenbrock, Sebastian Kruse, Jorge-Arnulfo Quian\u00e9-Ruiz, and Felix Naumann. 2015. Divide & conquer-based inclusion dependency discovery. PLDB 8, 7 (2015), 774--785.","journal-title":"PLDB"},{"key":"e_1_3_2_2_58_1","unstructured":"Python Rexpy package. https:\/\/tdda.readthedocs.io\/en\/v1.0.30\/rexpy.html"},{"key":"e_1_3_2_2_59_1","unstructured":"Random Forest Classifier. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.RandomForestClassifier.html"},{"key":"e_1_3_2_2_60_1","volume-title":"Can I Still Trust You?: Understanding the Impact of Distribution Shifts on Algorithmic Recourses. arXiv preprint arXiv:2012.11788","author":"Rawal Kaivalya","year":"2020","unstructured":"Kaivalya Rawal, Ece Kamar, and Himabindu Lakkaraju. 2020. Can I Still Trust You?: Understanding the Impact of Distribution Shifts on Algorithmic Recourses. arXiv preprint arXiv:2012.11788 (2020)."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415527"},{"key":"e_1_3_2_2_63_1","volume-title":"CIDR 2020, 10th Conference on Innovative Data Systems Research, Amsterdam, The Netherlands, January 12--15, 2020, Online Proceedings.","author":"Rezig El Kindi","year":"2020","unstructured":"El Kindi Rezig, Lei Cao, Giovanni Simonini, Maxime Schoemans, Samuel Madden, Nan Tang, Mourad Ouzzani, and Michael Stonebraker. 2020. Dagger: A Data (not code) Debugger. In CIDR 2020, 10th Conference on Innovative Data Systems Research, Amsterdam, The Netherlands, January 12--15, 2020, Online Proceedings."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476301"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_2_66_1","first-page":"1527","article-title":"Anchors: High- Precision Model-Agnostic Explanations","volume":"18","author":"Ribeiro Marco Tulio","year":"2018","unstructured":"Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High- Precision Model-Agnostic Explanations.. In AAAI, Vol. 18. 1527--1535.","journal-title":"AAAI"},{"key":"e_1_3_2_2_67_1","volume-title":"International Symposium on Software Testing and Analysis, ISSTA 2012","author":"R\u00f6\u00dfler Jeremias","year":"2012","unstructured":"Jeremias R\u00f6\u00dfler, Gordon Fraser, Andreas Zeller, and Alessandro Orso. 2012. Isolating failure causes through test case generation. In International Symposium on Software Testing and Analysis, ISSTA 2012, Minneapolis, MN, USA, July 15--20, 2012, Mats Per Erik Heimdahl and Zhendong Su (Eds.). ACM, 309--319."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389759"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319901"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"crossref","unstructured":"Sebastian Schelter Tammo Rukat and Felix Bie\u00dfmann. 2020. Learning to Validate the Predictions of Black Box Classifiers on Unseen Data. In SIGMOD. 1289--1299.","DOI":"10.1145\/3318464.3380604"},{"key":"e_1_3_2_2_71_1","unstructured":"Sentiment 140 dataset. https:\/\/www.kaggle.com\/kazanova\/sentiment140"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000824.2000826"},{"key":"e_1_3_2_2_73_1","first-page":"13","article-title":"Nutritional Labels for Data and Models","volume":"42","author":"Stoyanovich Julia","year":"2019","unstructured":"Julia Stoyanovich and Bill Howe. 2019. Nutritional Labels for Data and Models. IEEE Data Eng. Bull. 42, 3 (2019), 13--23.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077257.3077263"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2750549"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389696"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380568"},{"key":"e_1_3_2_2_78_1","volume-title":"7th European Software Engineering Conference, Held Jointly with the 7th ACM SIGSOFT Symposium on the Foundations of Software Engineering","author":"Zeller Andreas","year":"1999","unstructured":"Andreas Zeller. 1999. Yesterday, My Program Worked. Today, It Does Not. Why?. In Software Engineering - ESEC\/FSE'99, 7th European Software Engineering Conference, Held Jointly with the 7th ACM SIGSOFT Symposium on the Foundations of Software Engineering, Toulouse, France, September 1999, Proceedings. 253--267."},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143983"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517864","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517864","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:36Z","timestamp":1750188636000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":78,"alternative-id":["10.1145\/3514221.3517864","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517864","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}