{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T04:05:53Z","timestamp":1748837153530,"version":"3.41.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030494346"},{"type":"electronic","value":"9783030494353"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-49435-3_30","type":"book-chapter","created":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T20:11:27Z","timestamp":1591128687000},"page":"482-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mutation Operators for Large Scale Data Processing Programs in Spark"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-2525","authenticated-orcid":false,"given":"Jo\u00e3o Batista","family":"de Souza Neto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7707-8469","authenticated-orcid":false,"given":"Anamaria","family":"Martins Moreira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9545-1821","authenticated-orcid":false,"given":"Genoveva","family":"Vargas-Solar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5589-3895","authenticated-orcid":false,"given":"Martin Alejandro","family":"Musicante","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,3]]},"reference":[{"key":"30_CR1","volume-title":"Introduction to Software Testing","author":"P Ammann","year":"2017","unstructured":"Ammann, P., Offutt, J.: Introduction to Software Testing, 2nd edn. Cambridge University Press, New York (2017)","edition":"2"},{"key":"30_CR2","unstructured":"AMPLab: Big Data Benchmark (2019). https:\/\/amplab.cs.berkeley.edu\/benchmark\/"},{"key":"30_CR3","unstructured":"Apache Foundation: Apache Beam: An advanced unified programming model (2016). https:\/\/beam.apache.org\/"},{"key":"30_CR4","unstructured":"Apache Foundation: Apache Hadoop Documentation (2019). https:\/\/hadoop.apache.org\/docs\/r2.7.3\/"},{"key":"30_CR5","unstructured":"Camargo, L.C., Vergilio, S.R.: MapReduce program testing: a systematic mapping study. In: Chilean Computer Science Society (SCCC), 32nd International Conference of the Computation (2013)"},{"key":"30_CR6","unstructured":"Carbone, P., Ewen, S., Haridi, S., Katsifodimos, A., Markl, V., Tzoumas, K.: Apache Flink: stream and batch processing in a single engine. IEEE Data Eng. Bull. 38(4), 28\u201338 (2015)"},{"key":"30_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-319-59647-1_31","volume-title":"Networked Systems","author":"Y-F Chen","year":"2017","unstructured":"Chen, Y.-F., Hong, C.-D., Leng\u00e1l, O., Mu, S.-C., Sinha, N., Wang, B.-Y.: An executable sequential specification for spark aggregation. In: El Abbadi, A., Garbinato, B. (eds.) NETYS 2017. LNCS, vol. 10299, pp. 421\u2013438. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-59647-1_31"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Csallner, C., Fegaras, L., Li, C.: New ideas track: testing mapreduce-style programs. In: Proceedings of the 19th ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering, pp. 504\u2013507. ACM (2011)","DOI":"10.1145\/2025113.2025204"},{"key":"30_CR9","unstructured":"De Souza Neto, J.B.: An approach to mutation testing of big data processing programs. Thesis Proposal, Federal University of Rio Grande do Norte (2019). (in Portuguese). https:\/\/archive.org\/details\/prop-doc-joao-ufrn"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Ferrari, F.C., Maldonado, J.C., Rashid, A.: Mutation testing for aspect-oriented programs. In: 2008 1st International Conference on Software Testing, Verification, and Validation, pp. 52\u201361, April 2008","DOI":"10.1109\/ICST.2008.37"},{"issue":"3","key":"30_CR11","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/S0164-1212(96)00154-9","volume":"38","author":"PG Frankl","year":"1997","unstructured":"Frankl, P.G., Weiss, S.N., Hu, C.: All-uses vs mutation testing: an experimental comparison of effectiveness. J. Syst. Softw. 38(3), 235\u2013253 (1997)","journal-title":"J. Syst. Softw."},{"key":"30_CR12","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1016\/j.procs.2016.05.285","volume":"85","author":"N Garg","year":"2016","unstructured":"Garg, N., Singla, S., Jangra, S.: Challenges and techniques for testing of big data. Procedia Comput. Sci. 85, 940\u2013948 (2016). International Conference on Computational Modelling and Security (CMS 2016)","journal-title":"Procedia Comput. Sci."},{"issue":"5","key":"30_CR13","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/TSE.2010.62","volume":"37","author":"Y Jia","year":"2011","unstructured":"Jia, Y., Harman, M.: An analysis and survey of the development of mutation testing. IEEE Trans. Softw. Eng. 37(5), 649\u2013678 (2011)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"30_CR14","unstructured":"Karau, H.: Spark testing base (2019). https:\/\/github.com\/holdenk\/spark-testing-base"},{"key":"30_CR15","unstructured":"Lee, S.C., Offutt, J.: Generating test cases for XML-based Web component interactions using mutation analysis. In: Proceedings 12th International Symposium on Software Reliability Engineering, pp. 200\u2013209, November 2001"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Li, K., Reichenbach, C., Smaragdakis, Y., Diao, Y., Csallner, C.: SEDGE: symbolic example data generation for dataflow programs. In: 2013 28th IEEE\/ACM International Conference on Automated Software Engineering, pp. 235\u2013245 (2013)","DOI":"10.1109\/ASE.2013.6693083"},{"issue":"2","key":"30_CR17","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1002\/stvr.308","volume":"15","author":"YS Ma","year":"2005","unstructured":"Ma, Y.S., Offutt, J., Kwon, Y.R.: MuJava: an automated class mutation system. Softw. Test. Verif. Reliab. 15(2), 97\u2013133 (2005)","journal-title":"Softw. Test. Verif. Reliab."},{"key":"30_CR18","volume-title":"Big Data: Using SMART Big Data, Analytics and Metrics to Make Better Decisions and Improve Performance","author":"B Marr","year":"2015","unstructured":"Marr, B.: Big Data: Using SMART Big Data, Analytics and Metrics to Make Better Decisions and Improve Performance. Wiley, Hoboken (2015)"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Mor\u00e1n, J., de la Riva, C., Tuya, J.: Testing data transformations in MapReduce programs. In: Proceedings of the 6th International Workshop on Automating Test Case Design, Selection and Evaluation, pp. 20\u201325. ACM (2015)","DOI":"10.1145\/2804322.2804326"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Mor\u00e1n, J., de la Riva, C., Tuya, J.: Testing MapReduce programs: a systematic mapping study. J. Softw. Evol. Process 31(3), e2120 (2019)","DOI":"10.1002\/smr.2120"},{"issue":"2","key":"30_CR21","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1002\/(SICI)1097-024X(199602)26:2<165::AID-SPE5>3.0.CO;2-K","volume":"26","author":"AJ Offutt","year":"1996","unstructured":"Offutt, A.J., Pan, J., Tewary, K., Zhang, T.: An experimental evaluation of data flow and mutation testing. Softw. Pract. Exper. 26(2), 165\u2013176 (1996)","journal-title":"Softw. Pract. Exper."},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig Latin: a not-so-foreign language for data processing. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1099\u20131110. ACM (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"30_CR23","unstructured":"Richard, H.A., et al.: Design of mutant operators for the C programming language. Technical report (1989)"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web, pp. 285\u2013295. ACM, New York (2001)","DOI":"10.1145\/371920.372071"},{"key":"30_CR25","unstructured":"Walsh, P.J.: A measure of test case completeness (software, engineering). Ph.D. thesis, State University of New York at Binghamton, Binghamton, NY, USA (1985)"},{"key":"30_CR26","unstructured":"Yu, Y., et al.: DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language. In: Proceedings of the 8th USENIX Conference on Operating Systems Design and Implementation, pp. 1\u201314. USENIX Association (2008)"},{"key":"30_CR27","unstructured":"Zaharia, M., et al.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, p. 2. USENIX Association (2012)"},{"key":"30_CR28","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, HotCloud 2010, p. 10. USENIX Association (2010)"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-49435-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T22:03:03Z","timestamp":1748815383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-49435-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030494346","9783030494353"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-49435-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAiSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caise2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/caise20.imag.fr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"185","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In addition, 11 papers were published from the CAiSE 2020 workshops. The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}