{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:31:44Z","timestamp":1779337904660,"version":"3.51.4"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"CSCW2","license":[{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"content-version":"vor","delay-in-days":5,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2040942"],"award-info":[{"award-number":["IIS-2040942"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2021,10,13]]},"abstract":"<jats:p>AI systems can fail to learn important behaviors, leading to real-world issues like safety concerns and biases. Discovering these systematic failures often requires significant developer attention, from hypothesizing potential edge cases to collecting evidence and validating patterns. To scale and streamline this process, we introduce crowdsourced failure reports, end-user descriptions of how or why a model failed, and show how developers can use them to detect AI errors. We also design and implement Deblinder, a visual analytics system for synthesizing failure reports that developers can use to discover and validate systematic failures. In semi-structured interviews and think-aloud studies with 10 AI practitioners, we explore the affordances of the Deblinder system and the applicability of failure reports in real-world settings. Lastly, we show how collecting additional data from the groups identified by developers can improve model performance.<\/jats:p>","DOI":"10.1145\/3479569","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T02:46:19Z","timestamp":1634611579000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":54,"title":["Discovering and Validating AI Errors With Crowdsourced Failure Reports"],"prefix":"10.1145","volume":"5","author":[{"given":"\u00c1ngel Alexander","family":"Cabrera","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abraham J.","family":"Druck","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason I.","family":"Hong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Perer","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934262"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531653"},{"key":"e_1_2_2_4_1","volume-title":"Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence.","author":"Attenberg Josh M","year":"2011","unstructured":"Josh M Attenberg, Pagagiotis G Ipeirotis, and Foster Provost. 2011. Beat the machine: Challenging workers to find the unknown unknowns. In Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence."},{"key":"e_1_2_2_5_1","volume-title":"32nd AAAI Conference on Artificial Intelligence, AAAI 2018","author":"Bansal Gagan","year":"2018","unstructured":"Gagan Bansal and Daniel S. Weld. 2018. A coverage-based utility model for identifying unknown unknowns. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (2018), 1463--1470."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2477899"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/b978--155860915-0\/50016-0"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1453101.1453146"},{"key":"e_1_2_2_9_1","volume-title":"2008 IEEE International Conference on Software Maintenance. IEEE, 337--345","author":"Bettenburg Nicolas","unstructured":"Nicolas Bettenburg, Rahul Premraj, Thomas Zimmermann, and Sunghun Kim. [n.d.]. Duplicate bug reports considered harmful? really?. In 2008 IEEE International Conference on Software Maintenance. IEEE, 337--345."},{"key":"e_1_2_2_10_1","volume-title":"Conference on fairness, accountability and transparency. 77--91","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency. 77--91."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST47406.2019.8986948"},{"key":"e_1_2_2_12_1","unstructured":"\u00c1ngel Alexander Cabrera Fred Hohman Jason Lin and Duen Horng Chau. 2018. Interactive Classification for Deep Learning Interpretation. (2018) 1--5. http:\/\/arxiv.org\/abs\/1806.05660"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858411"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1978967"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172950"},{"key":"e_1_2_2_16_1","volume-title":"Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices. NeurIPS","author":"Chen Vincent S.","year":"2019","unstructured":"Vincent S. Chen, Sen Wu, Zhenzhen Weng, Alexander Ratner, and Christopher R\u00e9. 2019. Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices. NeurIPS (2019). http:\/\/arxiv.org\/abs\/1909.06349"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675214"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00139"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2746018"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2207711"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134680"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.324"},{"key":"e_1_2_2_23_1","unstructured":"Nitesh Goyal. 2015. Designing for Collaborative Sensemaking: Using Expert & Non-Expert Crowd. (2015). http:\/\/arxiv.org\/abs\/1511.06053"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421429"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"e_1_2_2_26_1","unstructured":"Panos Ipeirotis. [n.d.]. Demographics of mechanical Turk CeDER-10-01.pdf. ( [n. d.]). http:\/\/archive.nyu.edu\/fda\/bitstream\/2451\/29585\/2\/CeDER-10-01.pdf"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2018.2873427"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2985222"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939503"},{"key":"e_1_2_2_30_1","volume-title":"35th International Conference on Machine Learning, ICML 2018","volume":"6","author":"Kim Been","year":"2018","unstructured":"Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, and Rory Sayres. 2018a. Interpretability beyond feature attribution: Quantitative Testing with Concept Activation Vectors (TCAV). 35th International Conference on Machine Learning, ICML 2018, Vol. 6 (2018), 4186--4195."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2754374"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531644"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481415"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACIFICVIS.2015.7156366"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10821"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380306"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415168"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.06.019"},{"key":"e_1_2_2_42_1","volume-title":"Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure. HCOMP","author":"Nushi Besmira","year":"2018","unstructured":"Besmira Nushi, Ece Kamar, and Eric Horvitz. 2018. Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure. HCOMP (2018). http:\/\/arxiv.org\/abs\/1809.07424"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033--295X.106.4.643"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173--7.2"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965--7"},{"key":"e_1_2_2_47_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings","author":"Radford Alec","year":"2016","unstructured":"Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings (2016), 1--16."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019--1138-y"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016137"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.2297712"},{"key":"e_1_2_2_51_1","volume-title":"Quickly. In Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Ratner Alexander","year":"2016","unstructured":"Alexander Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, and Christopher R\u00e9. 2016. Data Programming: Creating Large Training Sets, Quickly. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS'16). Curran Associates Inc., Red Hook, NY, USA, 3574--3582."},{"key":"e_1_2_2_52_1","volume-title":"36th International Conference on Machine Learning, ICML 2019","volume":"9424","author":"Recht Benjamin","year":"2019","unstructured":"Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. 2019. Do ImageNet classifiers generalize to ImageNet? 36th International Conference on Machine Learning, ICML 2019, Vol. 2019-June (2019), 9413--9424."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2598828"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470689646.ch1"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2010.5463280"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287598"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357247"},{"key":"e_1_2_2_58_1","volume-title":"Wired","volume":"13","author":"Simonite Tom","year":"2018","unstructured":"Tom Simonite. 2018. When it comes to gorillas, google photos remains blind. Wired, January, Vol. 13 (2018)."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2011.6100061"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806811"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289"},{"key":"e_1_2_2_62_1","first-page":"19","article-title":"Self-driving Uber car kills pedestrian in Arizona, where robots roam","volume":"3","author":"Wakabayashi Daisuke","year":"2018","unstructured":"Daisuke Wakabayashi. 2018. Self-driving Uber car kills pedestrian in Arizona, where robots roam. The New York Times, Vol. 3 (2018), 19.","journal-title":"The New York Times"},{"key":"e_1_2_2_63_1","volume-title":"Sensemaking in Organizations (Foundations for Organizational Science). Star","author":"Weick Karl E","year":"1995","unstructured":"Karl E Weick. 1995. Sensemaking in Organizations (Foundations for Organizational Science). Star (1995)."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1073"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.66"},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-014--5241--2"},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2010.63"}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3479569","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3479569","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3479569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T05:00:38Z","timestamp":1752469238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3479569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":67,"journal-issue":{"issue":"CSCW2","published-print":{"date-parts":[[2021,10,13]]}},"alternative-id":["10.1145\/3479569"],"URL":"https:\/\/doi.org\/10.1145\/3479569","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,13]]},"assertion":[{"value":"2021-10-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}