{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:00:44Z","timestamp":1772906444878,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3702634.3702955","type":"proceedings-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T16:14:07Z","timestamp":1732724047000},"page":"31-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Bauplan: Zero-copy, Scale-up FaaS for Data Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8634-6122","authenticated-orcid":false,"given":"Jacopo","family":"Tagliabue","sequence":"first","affiliation":[{"name":"Bauplan, NYU, New York, US"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6125-4386","authenticated-orcid":false,"given":"Tyler","family":"Caraza-Harter","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, US"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0359-4130","authenticated-orcid":false,"given":"Ciro","family":"Greco","sequence":"additional","affiliation":[{"name":"Bauplan, New York, US"}]}],"member":"320","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Apache. 2024. Airflow. https:\/\/github.com\/apache\/airflow."},{"key":"e_1_3_2_1_2_1","unstructured":"Apache. 2024. Arrow. https:\/\/github.com\/apache\/arrow."},{"key":"e_1_3_2_1_3_1","unstructured":"Apache. 2024. OpenServerless. https:\/\/incubator.apache.org\/projects\/openserverless.html."},{"key":"e_1_3_2_1_4_1","unstructured":"Apache. 2024. OpenWhisk. https:\/\/github.com\/apache\/openwhisk."},{"key":"e_1_3_2_1_5_1","unstructured":"AWS. 2024. AWS Developer Guide. https:\/\/docs.aws.amazon.com\/lambda\/latest\/api\/API_Invoke.html."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362711"},{"key":"e_1_3_2_1_7_1","unstructured":"dbt-labs. 2024. dbt-core. https:\/\/github.com\/dbt-labs\/dbt-core."},{"key":"e_1_3_2_1_8_1","unstructured":"Dimensional Research. 2022. What Data Scientists Tell Us About AI Model Training Today. https:\/\/content.alegion.com\/dimensional-researchs-survey"},{"key":"e_1_3_2_1_9_1","unstructured":"Dremio. 2024. dremio-oss. https:\/\/github.com\/dremio\/dremio-oss."},{"key":"e_1_3_2_1_10_1","unstructured":"Dremio. 2024. Nessie. https:\/\/github.com\/projectnessie\/nessie."},{"key":"e_1_3_2_1_11_1","volume-title":"Serverless Computation with OpenLambda. In 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16)","author":"Hendrickson Scott","unstructured":"Scott Hendrickson, Stephen Sturdevant, Tyler Harter, Venkateshwaran Venkataramani, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. 2016. Serverless Computation with OpenLambda. In 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16). USENIX Association, Denver, CO. https:\/\/www.usenix.org\/conference\/hotcloud16\/workshop-program\/presentation\/hendrickson"},{"key":"e_1_3_2_1_12_1","unstructured":"Influx Data. 2024. influxdb. https:\/\/github.com\/influxdata\/influxdb."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360575"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446701"},{"key":"e_1_3_2_1_15_1","unstructured":"Lithops. 2024. Lithops. https:\/\/github.com\/lithops-cloud\/lithops."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3401025.3401731"},{"key":"e_1_3_2_1_17_1","volume-title":"SONIC: Application-aware Data Passing for Chained Serverless Applications. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Mahgoub Ashraf","year":"2021","unstructured":"Ashraf Mahgoub, Karthick Shankar, Subrata Mitra, Ana Klimovic, Somali Chaterji, and Saurabh Bagchi. 2021. SONIC: Application-aware Data Passing for Chained Serverless Applications. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 285--301. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/mahgoub"},{"key":"e_1_3_2_1_18_1","unstructured":"Microsoft. 2024. Azure Functions. https:\/\/azure.microsoft.com\/en-us\/products\/functions\/."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407807"},{"key":"e_1_3_2_1_20_1","unstructured":"PrefectHQ. 2024. Prefect. https:\/\/github.com\/PrefectHQ\/prefect."},{"key":"e_1_3_2_1_21_1","unstructured":"Research and Markets. 2024. Global Data Pipeline Tools Market by Component. https:\/\/www.researchandmarkets.com\/report\/data-pipeline-tools"},{"key":"e_1_3_2_1_22_1","unstructured":"Michele Sciabarr\u00e0. 2019. Learning Apache OpenWhisk: Developing Open Source Serverless Solutions. https:\/\/www.oreilly.com\/library\/view\/learning-apache-openwhisk\/9781492046158\/"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2209.09125"},{"key":"e_1_3_2_1_24_1","unstructured":"Spotify. 2024. Luigi. https:\/\/github.com\/spotify\/luigi."},{"key":"e_1_3_2_1_25_1","volume-title":"Reasonable Scale Machine Learning with Open-Source Metaflow. ArXiv abs\/2303.11761","author":"Tagliabue Jacopo","year":"2023","unstructured":"Jacopo Tagliabue, Hugo Bowne-Anderson, Ville Tuulos, Savin Goyal, Romain Cledat, and David Berg. 2023. Reasonable Scale Machine Learning with Open-Source Metaflow. ArXiv abs\/2303.11761 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650203.3663335"},{"key":"e_1_3_2_1_27_1","volume-title":"Building a Serverless Data Lakehouse from Spare Parts. ArXiv abs\/2308.05368","author":"Tagliabue Jacopo","year":"2023","unstructured":"Jacopo Tagliabue, Ciro Greco, and Luca Bigon. 2023. Building a Serverless Data Lakehouse from Spare Parts. ArXiv abs\/2308.05368 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260775634"},{"key":"e_1_3_2_1_28_1","unstructured":"Rajesh Thallam and Martin Dominguez. 2024. Build end-to-end machine learning workflows with Amazon SageMaker and Apache Airflow. https:\/\/github.com\/aws-samples\/sagemaker-ml-workflow-with-apache-airflow\/blob\/master\/src\/dag_ml_pipeline_amazon_video_reviews.py"},{"key":"e_1_3_2_1_29_1","volume-title":"Wenjian Dong, Murali Narayanaswamy, Zhengchun Liu, Gaurav Saxena, Andreas Kipf, and Tim Kraska.","author":"van Renen Alexander","year":"2024","unstructured":"Alexander van Renen, Dominik Horn, Pascal Pfeil, Kapil Eknath Vaidya, Wenjian Dong, Murali Narayanaswamy, Zhengchun Liu, Gaurav Saxena, Andreas Kipf, and Tim Kraska. 2024. Why TPC is not enough: An analysis of the Amazon Redshift fleet. In VLDB 2024."},{"key":"e_1_3_2_1_30_1","volume-title":"Parameswaran","author":"Xin Doris","year":"2018","unstructured":"Doris Xin, Litian Ma, Shuchen Song, and Aditya G. Parameswaran. 2018. How Developers Iterate on Machine Learning Workflows - A Survey of the Applied Machine Learning Literature. ArXiv abs\/1803.10311 (2018). https:\/\/api.semanticscholar.org\/CorpusID:4378544"},{"key":"e_1_3_2_1_31_1","volume-title":"An Empirical Study of Developers' Challenges in Implementing Workflows as Code: A Case Study on Apache Airflow. ArXiv abs\/2406.00180","author":"Yasmin Jerin","year":"2024","unstructured":"Jerin Yasmin, Jiale Wang, Yuan Tian, and Bram Adams. 2024. An Empirical Study of Developers' Challenges in Implementing Workflows as Code: A Case Study on Apache Airflow. ArXiv abs\/2406.00180 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270213226"},{"key":"e_1_3_2_1_32_1","volume-title":"Conference on Innovative Data Systems Research.","author":"Zaharia Matei A.","year":"2021","unstructured":"Matei A. Zaharia, Ali Ghodsi, Reynold Xin, and Michael Armbrust. 2021. Lake-house: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics. In Conference on Innovative Data Systems Research."}],"event":{"name":"WoSC10 '24: 10th International Workshop on Serverless Computing","location":"Hong Kong Hong Kong","acronym":"WoSC10 '24","sponsor":["IFIP","Usenix"]},"container-title":["Proceedings of the 10th International Workshop on Serverless Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702634.3702955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:09Z","timestamp":1750295889000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702634.3702955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":32,"alternative-id":["10.1145\/3702634.3702955","10.1145\/3702634"],"URL":"https:\/\/doi.org\/10.1145\/3702634.3702955","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}