{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:23:53Z","timestamp":1785543833456,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,5,27]],"date-time":"2016-05-27T00:00:00Z","timestamp":1464307200000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CCF-1139158"],"award-info":[{"award-number":["CCF-1139158"]}]},{"name":"LBNL","award":["7076018"],"award-info":[{"award-number":["7076018"]}]},{"name":"DARPA","award":["FA8750-12-2-0331"],"award-info":[{"award-number":["FA8750-12-2-0331"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,5,27]]},"DOI":"10.1145\/2723372.2742797","type":"proceedings-article","created":{"date-parts":[[2015,6,2]],"date-time":"2015-06-02T01:35:02Z","timestamp":1433208902000},"page":"1383-1394","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":974,"title":["Spark SQL"],"prefix":"10.1145","author":[{"given":"Michael","family":"Armbrust","sequence":"first","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reynold S.","family":"Xin","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Huai","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davies","family":"Liu","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph K.","family":"Bradley","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangrui","family":"Meng","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomer","family":"Kaftan","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael J.","family":"Franklin","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Ghodsi","sequence":"additional","affiliation":[{"name":"Databricks, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,5,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452377"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-014-0357-y"},{"key":"e_1_3_2_1_3_1","unstructured":"AMPLab big data benchmark. https:\/\/amplab.cs.berkeley.edu\/benchmark."},{"key":"e_1_3_2_1_4_1","unstructured":"Apache Avro project. http:\/\/avro.apache.org."},{"key":"e_1_3_2_1_5_1","unstructured":"Apache Parquet project. http:\/\/parquet.incubator.apache.org."},{"key":"e_1_3_2_1_6_1","unstructured":"Apache Spark project. http:\/\/spark.apache.org."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807149"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10619-011-7082-y"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1325851.1325964"},{"key":"e_1_3_2_1_10_1","unstructured":"BigDF project. https:\/\/github.com\/AyasdiOpenSource\/bigdf."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806638"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687576"},{"key":"e_1_3_2_1_13_1","unstructured":"DDF project. http:\/\/ddf.io."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2394758.2394779"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685096"},{"key":"e_1_3_2_1_16_1","volume-title":"The Cascades framework for query optimization","author":"Graefe G.","year":"1995","unstructured":"G. Graefe. The Cascades framework for query optimization. IEEE Data Engineering Bulletin, 18(3), 1995."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/38713.38734"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.166"},{"key":"e_1_3_2_1_19_1","unstructured":"Hive data definition language. https:\/\/cwiki.apache.org\/confluence\/display\/Hive\/LanguageManual"},{"key":"e_1_3_2_1_20_1","unstructured":"DDL."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559962"},{"key":"e_1_3_2_1_22_1","unstructured":"Jackson JSON processor. http:\/\/jackson.codehaus.org."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732959"},{"key":"e_1_3_2_1_24_1","volume-title":"CIDR","author":"Kornacker M.","year":"2015","unstructured":"M. Kornacker et al. Impala: A modern, open-source SQL engine for Hadoop. In CIDR, 2015."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920886"},{"key":"e_1_3_2_1_27_1","unstructured":"X. Meng J. Bradley E. Sparks and S. Venkataraman. ML pipelines: a new high-level API for MLlib. https:\/\/databricks.com\/blog\/2015\/01\/07\/ml-pipelines-a-new-high-level-api-for-mllib.html."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276331"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742787"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_31_1","unstructured":"\\textttpandas Python data analysis library. http:\/\/pandas.pydata.org."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"key":"e_1_3_2_1_33_1","unstructured":"R project for statistical computing. http:\/\/www.r-project.org."},{"key":"e_1_3_2_1_34_1","unstructured":"scikit-learn: machine learning in Python. http:\/\/scikit-learn.org."},{"key":"e_1_3_2_1_35_1","unstructured":"D. Shabalin E. Burmako and M. Odersky. Quasiquotes for Scala a technical report. Technical Report 185242 \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne 2013."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2612183"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/647698.734146"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465288"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2228298.2228301"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2735381"}],"event":{"name":"SIGMOD\/PODS'15: International Conference on Management of Data","location":"Melbourne Victoria Australia","acronym":"SIGMOD\/PODS'15","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2723372.2742797","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2723372.2742797","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2723372.2742797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:43:10Z","timestamp":1763458990000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2723372.2742797"}},"subtitle":["Relational Data Processing in Spark"],"short-title":[],"issued":{"date-parts":[[2015,5,27]]},"references-count":41,"alternative-id":["10.1145\/2723372.2742797","10.1145\/2723372"],"URL":"https:\/\/doi.org\/10.1145\/2723372.2742797","relation":{},"subject":[],"published":{"date-parts":[[2015,5,27]]},"assertion":[{"value":"2015-05-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}