{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T19:48:57Z","timestamp":1766951337817,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,26]],"date-time":"2017-06-26T00:00:00Z","timestamp":1498435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["SN10040, DE-SC0012463"],"award-info":[{"award-number":["SN10040, DE-SC0012463"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-12-2-0331"],"award-info":[{"award-number":["FA8750-12-2-0331"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1139158"],"award-info":[{"award-number":["CCF-1139158"]}],"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":[[2017,6,26]]},"DOI":"10.1145\/3078597.3078603","type":"proceedings-article","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T12:46:51Z","timestamp":1498222011000},"page":"143-153","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Diagnosing Machine Learning Pipelines with Fine-grained Lineage"],"prefix":"10.1145","author":[{"given":"Zhao","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Texas at Austin, Austin, TX, USA"}]},{"given":"Evan R.","family":"Sparks","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}]},{"given":"Michael J.","family":"Franklin","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2017,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17819-1_6"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/11890850_14"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/2095686.2095693"},{"key":"e_1_3_2_1_4_1","unstructured":"Apache. Apache Hadoop. http:\/\/hadoop.apache.org\/.  Apache. Apache Hadoop. http:\/\/hadoop.apache.org\/."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/93597.98741"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1057977.1057978"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807271"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142534"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/846219.847324"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-002-0083-8"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685090"},{"key":"e_1_3_2_1_12_1","unstructured":"M. Everingham L. Van Gool C. K. I. Williams J. Winn and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html.  M. Everingham L. Van Gool C. K. I. Williams J. Winn and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSDM.2002.1029704"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2008.79"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/882498.884550"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767930"},{"key":"e_1_3_2_1_17_1","unstructured":"Google. Tensorflow. http:\/\/tensorflow.org\/.  Google. Tensorflow. http:\/\/tensorflow.org\/."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/602259.602266"},{"key":"e_1_3_2_1_19_1","volume-title":"CIDR","author":"Ikeda R.","year":"2011","unstructured":"R. Ikeda , H. Park , and J. Widom . Provenance for generalized map and reduce workflows . In CIDR 2011 . Stanford InfoLab. R. Ikeda, H. Park, and J. Widom. Provenance for generalized map and reduce workflows. In CIDR 2011. Stanford InfoLab."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850595"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670985"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523619"},{"key":"e_1_3_2_1_23_1","first-page":"1150","volume-title":"The proceedings of the seventh IEEE international conference on","volume":"2","author":"Lowe D. G.","year":"1999","unstructured":"D. G. Lowe . Object recognition from local scale-invariant features. In Computer vision, 1999 . The proceedings of the seventh IEEE international conference on , volume 2 , pages 1150 -- 1157 . Ieee , 1999 . D. G. Lowe. Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, volume 2, pages 1150--1157. Ieee, 1999."},{"key":"e_1_3_2_1_24_1","first-page":"281","volume-title":"Proceedings of the fifth Berkeley symposium on mathematical statistics and probability","volume":"1","author":"MacQueen J.","year":"1967","unstructured":"J. MacQueen Some methods for classification and analysis of multivariate observations . In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability , volume 1 , pages 281 -- 297 . Oakland, CA, USA. , 1967 . J. MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, pages 281--297. Oakland, CA, USA., 1967."},{"key":"e_1_3_2_1_25_1","volume-title":"et al. Mllib: Machine learning in apache spark. arXiv preprint arXiv:1505.06807","author":"Meng X.","year":"2015","unstructured":"X. Meng , J. Bradley , B. Yavuz , E. Sparks , S. Venkataraman , D. Liu , J. Freeman , D. Tsai , M. Amde , S. Owen , et al. Mllib: Machine learning in apache spark. arXiv preprint arXiv:1505.06807 , 2015 . X. Meng, J. Bradley, B. Yavuz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D. Tsai, M. Amde, S. Owen, et al. Mllib: Machine learning in apache spark. arXiv preprint arXiv:1505.06807, 2015."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1739041.1739079"},{"key":"e_1_3_2_1_27_1","volume-title":"Powers of 10: Time scales in user experience","author":"Nielsen J.","year":"2009","unstructured":"J. Nielsen . Powers of 10: Time scales in user experience , 2009 . http:\/\/www.nngroup.com\/articles\/powers-of-10-time-scales-in-ux\/. J. Nielsen. Powers of 10: Time scales in user experience, 2009. http:\/\/www.nngroup.com\/articles\/powers-of-10-time-scales-in-ux\/."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.v18:10"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_30_1","unstructured":"E. Osheim. Archery. https:\/\/github.com\/meetup\/archery.  E. Osheim. Archery. https:\/\/github.com\/meetup\/archery."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402755.3402768"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_33_1","unstructured":"T. Sellis N. Roussopoulos and C. Faloutsos. The R  T. Sellis N. Roussopoulos and C. Faloutsos. The R"},{"key":"e_1_3_2_1_34_1","volume-title":"A dynamic index for multi-dimensional objects","author":"Sellis T.","year":"1987","unstructured":"T. Sellis , N. Roussopoulos , and C. Faloutsos : A dynamic index for multi-dimensional objects . 1987 . -tree: A dynamic index for multi-dimensional objects. 1987."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1084805.1084812"},{"key":"e_1_3_2_1_37_1","volume-title":"Karma2: Provenance management for data-driven workflows. Web Services Research for Emerging Applications: Discoveries and Trends: Discoveries and Trends, page 317","author":"Simmhan Y. L.","year":"2010","unstructured":"Y. L. Simmhan , B. Plale , and D. Gannon . Karma2: Provenance management for data-driven workflows. Web Services Research for Emerging Applications: Discoveries and Trends: Discoveries and Trends, page 317 , 2010 . Y. L. Simmhan, B. Plale, and D. Gannon. Karma2: Provenance management for data-driven workflows. Web Services Research for Emerging Applications: Discoveries and Trends: Discoveries and Trends, page 317, 2010."},{"key":"e_1_3_2_1_38_1","unstructured":"E. Sparks S. Venkataraman T. Kaftan M. Franklin and B. Recht. Keystoneml. https:\/\/github.com\/amplab\/keystone.  E. Sparks S. Venkataraman T. Kaftan M. Franklin and B. Recht. Keystoneml. https:\/\/github.com\/amplab\/keystone."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2009.11.009"},{"key":"e_1_3_2_1_40_1","first-page":"25","volume-title":"VLDB","volume":"93","author":"Stonebraker M.","year":"1993","unstructured":"M. Stonebraker , J. Chen , N. Nathan , C. Paxson , and J. Wu . Tioga: Providing data management support for scientific visualization applications . In VLDB , volume 93 , pages 25 -- 38 . Citeseer , 1993 . M. Stonebraker, J. Chen, N. Nathan, C. Paxson, and J. Wu. Tioga: Providing data management support for scientific visualization applications. In VLDB, volume 93, pages 25--38. Citeseer, 1993."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/645482.653450"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544881"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1086\/301513"},{"key":"e_1_3_2_1_45_1","first-page":"2","volume-title":"Proceedings of the USENIX Conference on Networked Systems Design and Implementation (NSDI '12)","author":"Zaharia M.","year":"2012","unstructured":"M. Zaharia , M. Chowdhury , T. Das , A. Dave , J. Ma , M. McCauley , M. Franklin , S. Shenker , and I. Stoica . Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing . In Proceedings of the USENIX Conference on Networked Systems Design and Implementation (NSDI '12) , pages 2 -- 2 . USENIX Association , 2012 . M. Zaharia, M. Chowdhury, T. Das, A. Dave, J. Ma, M. McCauley, M. Franklin, S. Shenker, and I. Stoica. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of the USENIX Conference on Networked Systems Design and Implementation (NSDI '12), pages 2--2. USENIX Association, 2012."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/1325851.1325977"}],"event":{"name":"HPDC '17: The 26th International Symposium on High-Performance Parallel and Distributed Computing","sponsor":["University of Arizona University of Arizona","SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Washington DC USA","acronym":"HPDC '17"},"container-title":["Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3078597.3078603","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3078597.3078603","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3078597.3078603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:15Z","timestamp":1750215795000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3078597.3078603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,26]]},"references-count":45,"alternative-id":["10.1145\/3078597.3078603","10.1145\/3078597"],"URL":"https:\/\/doi.org\/10.1145\/3078597.3078603","relation":{},"subject":[],"published":{"date-parts":[[2017,6,26]]},"assertion":[{"value":"2017-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}