{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:40:07Z","timestamp":1751928007436,"version":"3.41.2"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030809591"},{"type":"electronic","value":"9783030809607"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-80960-7_11","type":"book-chapter","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T06:02:37Z","timestamp":1625724157000},"page":"183-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Model and System for Querying Provenance from Data Cleaning Workflows"],"prefix":"10.1007","author":[{"given":"Nikolaus Nova","family":"Parulian","sequence":"first","affiliation":[]},{"given":"Timothy M.","family":"McPhillips","sequence":"additional","affiliation":[]},{"given":"Bertram","family":"Lud\u00e4scher","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,9]]},"reference":[{"key":"11_CR1","unstructured":"Belhajjame, K., et al.: PROV-DM: the PROV data model. www.w3.org\/TR\/prov-dm (2012)"},{"key":"11_CR2","unstructured":"Clingo: A grounder and solver for logic programs. https:\/\/github.com\/potassco\/clingo"},{"key":"11_CR3","unstructured":"Cuevas-Vicentt\u00edn, V., et al.: ProvONE: a PROV extension data model for scientific workflow provenance (2016). http:\/\/jenkins-1.dataone.org\/jenkins\/view\/DocumentationProjects\/job\/ProvONE-Documentation-trunk\/ws\/provenance\/ProvONE\/v1\/provone.html"},{"key":"11_CR4","unstructured":"Dey, S.C., K\u00f6hler, S., Bowers, S., Lud\u00e4scher, B.: Datalog as a Lingua Franca for Provenance Querying and Reasoning. In: Workshop on Theory and Practice of Provenance (TaPP) (2012)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Gebser, M., Kaminski, R., Kaufmann, B., Schaub, T.: Multi-shot ASP solving with clingo. CoRR arXiv:1705.09811 (2017)","DOI":"10.1017\/S1471068418000054"},{"key":"11_CR6","unstructured":"Hipp, R.: SQLite (2021). www.sqlite.org"},{"key":"11_CR7","unstructured":"Li, L., Parulian, N., Lud\u00e4scher, B.: or2yw: generating YesWorkflow models from OpenRefine histories (2021). https:\/\/github.com\/idaks\/OR2YWTool"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"McPhillips, T., Bowers, S., Belhajjame, K., Lud\u00e4scher, B.: Retrospective provenance without a runtime provenance recorder. In: Theory and Practice of Provenance (TaPP) (2015). https:\/\/doi.org\/10.5555\/2814579.2814580","DOI":"10.5555\/2814579.2814580"},{"key":"11_CR9","unstructured":"McPhillips, T., Li, L., Parulian, N., Lud\u00e4scher, B.: Modeling provenance and understanding reproducibility for OpenRefine data cleaning workflows. In: Workshop on Theory and Practice of Provenance (TaPP) (2019)"},{"key":"11_CR10","unstructured":"Missier, P., Dey, S., Belhajjame, K., Cuevas-Vicentt\u00edn, V., Lud\u00e4scher, B.: D-PROV: extending the PROV provenance model with workflow structure. In: Workshop on the Theory and Practice of Provenance (TaPP) (2013)"},{"issue":"6","key":"11_CR11","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.future.2010.07.005","volume":"27","author":"L Moreau","year":"2011","unstructured":"Moreau, L., et al.: The open provenance model core specification. Future Gener. Comput. Syst. 27(6), 743\u2013756 (2011)","journal-title":"Future Gener. Comput. Syst."},{"key":"11_CR12","unstructured":"New York Public Library: What\u2019s on the menu? (2020). http:\/\/menus.nypl.org"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Olveira, W., Missier, P., de Olveira, D., Braganholo, V.: Comparing provenance data models for scientific workflows: an analysis of PROV-Wf and ProvONE. In: Anais do Brazilian e-Science Workshop (BreSci), pp. 9\u201316, January 2020","DOI":"10.5753\/bresci.2016.9119"},{"key":"11_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-3-662-46641-4_3","volume-title":"The Semantic Web: ESWC 2012 Satellite Events","author":"T Omitola","year":"2015","unstructured":"Omitola, T., Freitas, A., Curry, E., O\u2019Riain, S., Gibbins, N., Shadbolt, N.: Capturing interactive data transformation operations using provenance workflows. In: Simperl, E., et al. (eds.) ESWC 2012. LNCS, vol. 7540, pp. 29\u201342. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-46641-4_3"},{"key":"11_CR15","unstructured":"OpenRefine: A free, open source, power tool for working with messy data (2021). https:\/\/github.com\/OpenRefine"},{"key":"11_CR16","unstructured":"Pandas: powerful Python data analysis toolkit (2019). https:\/\/github.com\/pandas-dev\/pandas"},{"key":"11_CR17","unstructured":"Parulian, N.: OpenRefine Provenance Explorer (ORPE) Data Cleaning Model (DCM) (2021). https:\/\/github.com\/idaks\/IPAW2021-ORPE"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Pimentel, J.F., et al.: Yin & Yang: demonstrating complementary provenance from noWorkflow & YesWorkflow. In: IPAW. LNCS, vol. 9672. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-40593-3_13","DOI":"10.1007\/978-3-319-40593-3_13"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Sadiq, S.: Handbook of Data Quality. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-36257-6","DOI":"10.1007\/978-3-642-36257-6"},{"issue":"2","key":"11_CR20","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/3377330.3377338","volume":"48","author":"M Winslett","year":"2019","unstructured":"Winslett, M., Braganholo, V.: Richard Hipp speaks out on SQLite. ACM SIGMOD Record 48(2), 39\u201346 (2019)","journal-title":"ACM SIGMOD Record"}],"container-title":["Lecture Notes in Computer Science","Provenance and Annotation of Data and Processes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-80960-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:02:16Z","timestamp":1751925736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-80960-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030809591","9783030809607"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-80960-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"9 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IPAW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Provenance and Annotation Workshop","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ipaw2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iitdbgroup.github.io\/ProvenanceWeek2021\/ipaw.html","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":"15","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":"7","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":"47% - 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":"2","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":"No","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, 6 posters and system demonstrations were accepted for publication","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)"}}]}}