{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2020-08-27T15:01:24.853445+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "BigDataStack_D2.3_v1.0.pdf": { "checksum": "md5:724943b3582e881d106e3bb8907c4ade", "ext": "pdf", "id": "515a23a0-65a7-4fc5-8ca6-40ae940bb5be", "key": "BigDataStack_D2.3_v1.0.pdf", "metadata": null, "mimetype": "application/pdf", "size": 2988329 } }, "order": [], "total_bytes": 2988329 }, "id": "4004170", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/4004170/access", "access_links": "https://zenodo.org/api/records/4004170/access/links", "access_request": "https://zenodo.org/api/records/4004170/access/request", "access_users": "https://zenodo.org/api/records/4004170/access/users", "archive": "https://zenodo.org/api/records/4004170/files-archive", "archive_media": "https://zenodo.org/api/records/4004170/media-files-archive", "communities": "https://zenodo.org/api/records/4004170/communities", "communities-suggestions": "https://zenodo.org/api/records/4004170/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.4004170", "draft": "https://zenodo.org/api/records/4004170/draft", "files": "https://zenodo.org/api/records/4004170/files", "latest": "https://zenodo.org/api/records/4004170/versions/latest", "latest_html": "https://zenodo.org/records/4004170/latest", "media_files": "https://zenodo.org/api/records/4004170/media-files", "parent": "https://zenodo.org/api/records/4004169", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.4004169", "parent_html": "https://zenodo.org/records/4004169", "requests": "https://zenodo.org/api/records/4004170/requests", "reserve_doi": "https://zenodo.org/api/records/4004170/draft/pids/doi", "self": "https://zenodo.org/api/records/4004170", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.4004170", "self_html": "https://zenodo.org/records/4004170", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:4004170/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:4004170/sequence/default", "versions": "https://zenodo.org/api/records/4004170/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "ATOS" } ], "person_or_org": { "family_name": "Orlando Avila-Garc\u00eda", "identifiers": [ { "identifier": "0000-0003-1549-2960", "scheme": "orcid" } ], "name": "Orlando Avila-Garc\u00eda", "type": "personal" } }, { "affiliations": [ { "name": "IBM" } ], "person_or_org": { "family_name": "Paula Ta-Shma", "name": "Paula Ta-Shma", "type": "personal" } }, { "affiliations": [ { "name": "IBM" } ], "person_or_org": { "family_name": "Yosef Moatti", "name": "Yosef Moatti", "type": "personal" } }, { "affiliations": [ { "name": "NEC" } ], "person_or_org": { "family_name": "Mauricio Fadel", "name": "Mauricio Fadel", "type": "personal" } }, { "affiliations": [ { "name": "NEC" } ], "person_or_org": { "family_name": "Bin Chen", "identifiers": [ { "identifier": "0000-0002-3849-9375", "scheme": "orcid" } ], "name": "Bin Chen", "type": "personal" } }, { "affiliations": [ { "name": "ATOS" } ], "person_or_org": { "family_name": "Ismael Cuadrado", "identifiers": [ { "identifier": "0000-0001-7134-3375", "scheme": "orcid" } ], "name": "Ismael Cuadrado", "type": "personal" } }, { "affiliations": [ { "name": "ATOS" } ], "person_or_org": { "family_name": "Ana Bel\u00e9n Gonz\u00e1lez", "identifiers": [ { "identifier": "0000-0002-8299-6301", "scheme": "orcid" } ], "name": "Ana Bel\u00e9n Gonz\u00e1lez", "type": "personal" } }, { "affiliations": [ { "name": "ATOS" } ], "person_or_org": { "family_name": "Bernat Quesada", "name": "Bernat Quesada", "type": "personal" } }, { "affiliations": [ { "name": "ATOS" } ], "person_or_org": { "family_name": "Alberto Soler", "name": "Alberto Soler", "type": "personal" } }, { "affiliations": [ { "name": "DAN" } ], "person_or_org": { "family_name": "Stathis Plitsos", "identifiers": [ { "identifier": "0000-0002-9439-4703", "scheme": "orcid" } ], "name": "Stathis Plitsos", "type": "personal" } }, { "affiliations": [ { "name": "ATC" } ], "person_or_org": { "family_name": "Anestis Sidiropoulos", "name": "Anestis Sidiropoulos", "type": "personal" } }, { "affiliations": [ { "name": "ATC" } ], "person_or_org": { "family_name": "Amaryllis Raouzaiou", "name": "Amaryllis Raouzaiou", "type": "personal" } }, { "affiliations": [ { "name": "LXS" } ], "person_or_org": { "family_name": "Jose Mar\u00eda Zaragoza", "identifiers": [ { "identifier": "0000-0002-0838-8367", "scheme": "orcid" } ], "name": "Jose Mar\u00eda Zaragoza", "type": "personal" } }, { "affiliations": [ { "name": "LXS" } ], "person_or_org": { "family_name": "Jesus Gallego", "name": "Jesus Gallego", "type": "personal" } }, { "affiliations": [ { "name": "UBI" } ], "person_or_org": { "family_name": "Sophia Karagiorgou", "identifiers": [ { "identifier": "0000-0002-1099-8463", "scheme": "orcid" } ], "name": "Sophia Karagiorgou", "type": "personal" } }, { "affiliations": [ { "name": "UBI" } ], "person_or_org": { "family_name": "Panagiotis Gouvas", "name": "Panagiotis Gouvas", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Dimitris Poulopoulos", "name": "Dimitris Poulopoulos", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Stavroula Meimetea", "name": "Stavroula Meimetea", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Maria Kanakari", "name": "Maria Kanakari", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Christos Doulkeridis", "identifiers": [ { "identifier": "0000-0002-3219-0510", "scheme": "orcid" } ], "name": "Christos Doulkeridis", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Giannis Poulakis", "name": "Giannis Poulakis", "type": "personal" } }, { "affiliations": [ { "name": "UPRC" } ], "person_or_org": { "family_name": "Dimosthenis Kyriazis", "identifiers": [ { "identifier": "0000-0001-7019-7214", "scheme": "orcid" } ], "name": "Dimosthenis Kyriazis", "type": "personal" } }, { "affiliations": [ { "name": "UPM" } ], "person_or_org": { "family_name": "Marta Patino", "identifiers": [ { "identifier": "0000-0002-3404-8155", "scheme": "orcid" } ], "name": "Marta Patino", "type": "personal" } }, { "affiliations": [ { "name": "GLA" } ], "person_or_org": { "family_name": "Richard McCreadie", "identifiers": [ { "identifier": "0000-0002-2751-2087", "scheme": "orcid" } ], "name": "Richard McCreadie", "type": "personal" } }, { "affiliations": [ { "name": "RHT" } ], "person_or_org": { "family_name": "Miki Kenneth", "name": "Miki Kenneth", "type": "personal" } }, { "affiliations": [ { "name": "RHT" } ], "person_or_org": { "family_name": "Luis Tomas", "identifiers": [ { "identifier": "0000-0002-9217-2277", "scheme": "orcid" } ], "name": "Luis Tomas", "type": "personal" } }, { "affiliations": [ { "name": "SILO" } ], "person_or_org": { "family_name": "Nikos Drosos", "identifiers": [ { "identifier": "0000-0002-9583-0482", "scheme": "orcid" } ], "name": "Nikos Drosos", "type": "personal" } }, { "affiliations": [ { "name": "GFT" } ], "person_or_org": { "family_name": "Maurizio Megliola", "name": "Maurizio Megliola", "type": "personal" } } ], "description": "
In the requirements analysis presented in this document, a top-down approach is taken with respect to the user requirements, which have been collected through the BigDataStack use case providers. This is complemented with a bottom-up approach aiming to identify, collect, and analyse the rest of the stakeholder requirements as well as technical requirements from the BigDataStack technology.
", "funding": [ { "award": { "acronym": "BigDataStack", "id": "00k4n6c32::779747", "identifiers": [ { "identifier": "https://cordis.europa.eu/projects/779747", "scheme": "url" } ], "number": "779747", "program": "H2020", "title": { "en": "High-performance data-centric stack for big data applications and operations" } }, "funder": { "id": "00k4n6c32", "name": "European Commission" } } ], "publication_date": "2020-08-27", "publisher": "Zenodo", "references": [ { "reference": "G. Beskales, I. F. Ilyas, and L. Golab, \"Sampling the repairs of functional dependency violations under hard constraints,\" Proc. VLDB Endow., vol. 3, no. 1\u20132, pp. 197\u2013207, 2010." }, { "reference": "W. Fan, J. Li, S. Ma, N. Tang, and W. Yu, \"Towards certain fixes with editing rules and master data,\" Proc. VLDB Endow., vol. 3, no. 1\u20132, pp. 173\u2013184, 2010." }, { "reference": "J. Wang and N. Tang, \"Towards dependable data repairing with fixing rules,\" in Proceedings of the 2014 ACM SIGMOD international conference on Management of data, 2014, pp. 457\u2013468" }, { "reference": "X. Chu, I. F. Ilyas, and P. Papotti, \"Holistic data cleaning: Putting violations into context,\" in Data Engineering (ICDE), 2013 IEEE 29th International Conference on, 2013, pp. 458\u2013469." }, { "reference": "M. Heinsman, \"Trifacta,\" Trifacta. [Online]. Available at https://www.trifacta.com/. [Accessed: 23- May-2018]." }, { "reference": "M. Dallachiesa et al., \"NADEEF: a commodity data cleaning system,\" in Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, 2013, pp. 541\u2013552." }, { "reference": "J. Wang, S. Krishnan, M. J. Franklin, K. Goldberg, T. Kraska, and T. Milo, \"A sample-and-clean framework for fast and accurate query processing on dirty data,\" in Proceedings of the 2014 ACM SIGMOD international conference on Management of data, 2014, pp. 469\u2013480." }, { "reference": "Z. Khayyat et al., \"Bigdansing: A system for big data cleansing,\" in Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, 2015, pp. 1215\u20131230." }, { "reference": "Y. Altowim, D. V. Kalashnikov, and S. Mehrotra, \"Progressive approach to relational entity resolution,\" Proc. VLDB Endow., vol. 7, no. 11, pp. 999\u20131010, 2014." }, { "reference": "Z. Li, S. Shang, Q. Xie, and X. Zhang, \"Cost reduction for web-based data imputation,\" in International Conference on Database Systems for Advanced Applications, 2014, pp. 438\u2013452." }, { "reference": "D. Haas, J. Wang, E. Wu, and M. J. Franklin, \"Clamshell: Speeding up crowds for low-latency data labeling,\" Proc. VLDB Endow., vol. 9, no. 4, pp. 372\u2013383, 2015." }, { "reference": "C. Gokhale et al., \"Corleone: hands-off crowdsourcing for entity matching,\" in Proceedings of the 2014 ACM SIGMOD international conference on Management of data, 2014, pp. 601\u2013612." }, { "reference": "B. Mozafari, P. Sarkar, M. Franklin, M. Jordan, and S. Madden, \"Scaling up crowd-sourcing to very large datasets: a case for active learning,\" Proc. VLDB Endow., vol. 8, no. 2, pp. 125\u2013136, 2014." }, { "reference": "X. Chu, I. F. Ilyas, S. Krishnan, and J. Wang, \"Data Cleaning: Overview and Emerging Challenges,\" 2016, pp. 2201\u20132206." }, { "reference": "P. Bohannon, W. Fan, M. Flaster, and R. Rastogi, \"A cost-based model and effective heuristic for repairing constraints by value modification,\" in Proceedings of the 2005 ACM SIGMOD international conference on Management of data, 2005, pp. 143\u2013154." }, { "reference": "] J. Wang, T. Kraska, M. J. Franklin, and J. Feng, \"Crowder: Crowdsourcing entity resolution,\" Proc. VLDB Endow., vol. 5, no. 11, pp. 1483\u20131494, 2012." }, { "reference": "A. Chalamalla, I. F. Ilyas, M. Ouzzani, and P. Papotti, \"Descriptive and prescriptive data cleaning,\" in Proceedings of the 2014 ACM SIGMOD Int. Conf. on Management of data, 2014, pp. 445\u2013456." }, { "reference": "L. Golab, H. Karloff, F. Korn, D. Srivastava, and B. Yu, \"On generating near-optimal tableaux for conditional functional dependencies,\" Proc. VLDB Endow., vol. 1, no. 1, pp. 376\u2013390, 2008." }, { "reference": "G. Beskales, I. F. Ilyas, L. Golab, and A. Galiullin, \"On the relative trust between inconsistent data and inaccurate constraints,\" in Data Engineering (ICDE), 2013 IEEE 29th International Conference on, 2013, pp. 541\u2013552." }, { "reference": "M. Yakout, A. K. Elmagarmid, J. Neville, M. Ouzzani, and I. F. Ilyas, \"Guided data repair,\" Proc. VLDB Endow., vol. 4, no. 5, pp. 279\u2013289, 2011." }, { "reference": "S. Krishnan, J. Wang, E. Wu, M. J. Franklin, and K. Goldberg, \"Activeclean: Interactive data cleaning while learning convex loss models,\" ArXiv Prepr. ArXiv160103797, 2016." }, { "reference": "Carbonell, J. (1990). Machine learning: paradigms and methods. Elsevier North-Holland, Inc." }, { "reference": "Yu, H., Han, J. & Chang, K. C.-C., \"PEBL: Positive example -based learning for Web page classification using SVM.\" In 'Proceedings of ACM SIGKDD 2002 International Conference on Knowledge Discovery and Data Mining'." }, { "reference": "Agichtein, E., Brill, E. & Dumais, S. T.,\"Improving Web search ranking by incorporating user behavior information.\" In 'Proceedings of the 29th International ACM SIGIR Conference on Research and Development in Information Retrieval'." }, { "reference": "Liu, T.-Y., \"Learning to rank for information retrieval.\" Foundations Trends Information Retrieval. 3, 225\u2013331." }, { "reference": "Page, L., Brin, S., Motwani, R. & Winograd, T.,\"The PageRank Citation Ranking: Bringing Order to the Web.\" Technical report. Stanford InfoLab. 1999" }, { "reference": "Macdonald, C., Santos, R. & Ounis, \"The whens and hows of learning to rank.\" Information Retrieval. 2012" }, { "reference": "J. N. Gray, \"Notes on data base operating systems,\" Lecture Notes in Computer Science, vol. 60, pp. 393-481, 1978." }, { "reference": "H. Sturgis and B. Lampson, \"Crash recovery in a distributed data storage system,\" Computer Science Laboratory, Xerox, Palo Alto, 1976" }, { "reference": "D. Peng and F. Dabek, \"Large-scale incremental processing using distributed transactions and notifications,\" in Proceedings of the 9th USENIX Symposium on Operating Systems Design and Implementation (OSDI'10), 2010." }, { "reference": "J. C. Corbett, J. Dean, M. Epstein, A. Fikes, C. Frost, J. J. Furman, S. Ghemawat, A. Gubarev, C. Heiser, P. Hochschild, W. Hsieh, S. Kanthak, E. Kogan, H. Li, A. Lloyd and S. Melnik, \"Spanner: Google's globally-distributed database,\" in Proceedings of the 10th USENIX Conference on Operating Systems Design and Implementation (OSDI '12), 2012." }, { "reference": "D. G. Ferro, F. Junqueira, I. Kelly, B. Reed and M. Yabandeh, \"Omid: Lock-free transactional support for distributed data stores,\" in IEEE 30th International Conference on Data Engineering (ICDE), Chicago, 2014." }, { "reference": "Apache, \"Apache Tephra,\" [Online]. Available at http://tephra.incubator.apache.org. [Accessed May 2018]." }, { "reference": "Amr Osman, Mohamed El-Refaey, Ayman Elnaggar, Towards Real-Time Analytics in the Cloud, In Proceedings of IEEE SERVICES, 2013" }, { "reference": "Mike Barlow, Real-Time Big Data Analytics: Emerging Architecture, O'Reilly Media, Inc.,2013" }, { "reference": "T. \u00d6zsu, P. Valduriez. Principles of Distributed Database Systems. Springer, 2011" }, { "reference": "Alfons Kemper and Thomas Neumann. HyPer: A hybrid OLTP&OLAP main memory database system based on virtual memory snapshots. In Proceedings of ICDE, 2011" }, { "reference": "Franz F\u00e4rber, Sang Kyun Cha, J\u00fcrgen Primsch, Christof Bornh\u00f6vd, Stefan Sigg, and Wolfgang Lehner. SAP HANA database: data management for modern business applications. In Proceedings of SIGMOD, 2012." }, { "reference": "V. Gulisano, R. Jim\u00e9nez-Peris, M. Pati\u00f1o-Mart\u00ednez, C. Soriente, P. Valduriez (2012) StreamCloud: An Elastic and Scalable Data Streaming System. IEEE Trans. Parallel Distrib. Syst. 23(12): 2351-2365." }, { "reference": "B. F. van Dongen, A. K. A. de Medeiros, H. M. W. Verbeek, A. J. M. M. Weijters, and W. M. P. van der Aalst, \"The ProM Framework: A New Era in Process Mining Tool Support,\" in Applications and Theory of Petri Nets 2005, vol. 3536, G. Ciardo and P. Darondeau, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 444\u2013454." }, { "reference": "International Organization for Standardization, \"ISO/IEC/IEEE 29148:2011 \u2013 Systems and software engineering \u2014 Life cycle processes \u2014 Requirements engineering,\" ISO/IEC/IEEE, Nov. 2011." }, { "reference": "Open Grid Forum, \"Web Services Agreement Specification (WS-Agreement),\" Oct. 10, 2011. http://ogf.org/documents/GFD.192.pdf" }, { "reference": "Open Grid Forum, \"WS-Agreement Negotiation Version 1.0,\" Jan. 31, 2011. https://www.ogf.org/Public_Comment_Docs/Documents/2011-03/WS-AgreementNegotiation+v1.0.pdf" }, { "reference": "P. Pietzuch, J. Ledlie, J. Shneidman, M. Roussopoulos, M. Welsh, and M. Seltzer, \"Network-Aware Operator Placement for Stream-Processing Systems\", 22nd International Conference on Data Engineering (ICDE '06), pp. 49\u201353, IEEE Computer Society, 2006." }, { "reference": "V. Cardellini, V. Grassi, F. Lo Presti, and M. Nardelli, \"Distributed QoS-aware Scheduling in Storm\", 9th ACM International Conference on Distributed Event-Based Systems, pp. 344-347, ACM, 2015." }, { "reference": "Y. Xing, S. Zdonik, and J.-H. Hwang, \"Dynamic Load Distribution in the Borealis Stream Processor\", 21st Int. Conf. on Data Engineering (ICDE '05), pp. 791\u2013802, IEEE Computer Society, 2005." }, { "reference": "M. Hirzel, R. Soule, S. Schneider, B. Gedik, and R. Grimm, \"A Catalog of Stream Processing Optimizations\", ACM Computing Surveys, vol. 46, Mar. 2014, pp 1\u201334." }, { "reference": "MongoDB MongoDB and MySQL Compare. [Accessed: 27/05/2018] https://www.mongodb.com/compare/mongodb-mysql" }, { "reference": "L. Sun, M. J. Franklin, S. Krishnan, and R. S. Xin, \"Fine-grained partitioning for aggressive data skipping,\" SIGMOD, 2014." }, { "reference": "L. Sun, S. Krishnan, R. S. Xin, and M. J. Franklin, \"A partitioning framework for aggressive data skipping,\" VLDB, 2014." }, { "reference": "A. Shanbhag, A. Jindal, S. Madden, J. Quiane, and A. J. Elmore, \"A robust partitioning scheme for ad-hoc query workloads,\" SoCC, 2017." }, { "reference": "Y. Lu, A. Shanbhag, A. Jindal, and S. Madden, \"Adaptdb: Adaptive partitioning for distributed joins,\" VLDB, 2017." }, { "reference": "D. McPherson, \"Managing Compute Resources with OpenShift/Kubernetes,\" August 2016. Red Hat. https://blog.openshift.com/managing-compute-resources-openshiftkubernetes/ [Accessed June 2018]." }, { "reference": "Mao, H., Netravali, R., & Alizadeh, M. (2017, August). Neural adaptive video streaming with pensieve. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication (pp. 197-210). ACM." }, { "reference": "Jiang, J., Ananthanarayanan, G., Bodik, P., Sen, S., & Stoica, I. (2018, August). Chameleon: scalable adaptation of video analytics. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication (pp. 253-266). ACM." }, { "reference": "Rao, J., Bu, X., Xu, C. Z., Wang, L., & Yin, G. (2009, June). VCONF: a reinforcement learning approach to virtual machines auto-configuration. In Proceedings of the 6th international conference on Autonomic computing (pp. 137-146). ACM." }, { "reference": "Tamraparni Dasu and Ji Meng Loh. 2012. Statistical distortion: Consequences of data cleaning. Proceedings of the VLDB Endowment5, 11(2012), 1674\u20131683." }, { "reference": "Tamraparni Dasu, Theodore Johnson, Shanmugauelayut Muthukrishnan, and Vladislav Shkapenyuk. 2002. Mining database structure; or, how to build a data quality browser. In Proceedings of the 2002 ACM SIGMOD international conference on Management of data. ACM,240\u2013251" }, { "reference": "Ziawasch Abedjan, Cuneyt G Akcora, Mourad Ouzzani, Paolo Papotti, and Michael Stonebraker. 2015. Temporal rules discovery for web data cleaning. Proceedings of the VLDB Endowment9, 4 (2015), 336\u2013347." }, { "reference": "Ziawasch Abedjan, Xu Chu, Dong Deng, Raul Castro Fernandez, Ihab FIlyas, Mourad Ouzzani, Paolo Papotti, Michael Stonebraker, and NanTang. 2016. Detecting data errors: Where are we and what needs to be done? Proceedings of the VLDB Endowment 9, 12 (2016), 993\u20131004" }, { "reference": "Alireza Heidari, Joshua McGrath, Ihab F Ilyas, and Theodoros Rekatsinas. 2019. HoloDetect: FewShot Learning for Error Detection. Proceedings of the 2019 International Conference on Management of Data (2019), 829\u2013846." }, { "reference": "Zhuoran Yu and Xu Chu. 2019. PIClean: A Probabilistic and Inter-active Data Cleaning System. In Proceedings of the 2019 International Conference on Management of Data. ACM, 2021\u20132024" } ], "resource_type": { "id": "publication-deliverable", "title": { "de": "Projektergebnis", "en": "Project deliverable" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "BigDataStack - D2.3 Requirements & State of the Art Analysis \u2013 III" }, "parent": { "access": { "owned_by": { "user": 125416 } }, "communities": { "entries": [ { "access": { "member_policy": "open", "members_visibility": "restricted", "record_policy": "open", "review_policy": "closed", "visibility": "public" }, "children": { "allow": true }, "created": "2022-11-23T15:53:29.436323+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c", "links": {}, "metadata": { "curation_policy": "The EU Open Research Repository serves as a repository for research outputs (data, software, posters, presentations, publications, etc) which have been funded under an EU research funding programme such as Horizon Europe, Euratom or earlier Framework Programmes.
\nThe community is managed by CERN on behalf of the European Commission.
\nZenodo’s general policies and Terms of Use apply to all content.
\nThe EU Open Research Repository accepts all digital research objects which is a research output stemming from one of EU’s research and innovation funding programmes. The funding programmes currently include:
\nHorizon Europe (including ERC, MSCA), earlier Framework Programmes (eg Horizon 2020) as well as Euratom.
\nIn line with the principle as open as possible, as closed as necessary both public and restricted content is accepted. See note on how Zenodo handles restricted content.
\nEU programme beneficiaries are eligible to submit content to the community. The community supports three types of content submissions:
\nSubmission via an EU Project Community (through user interface or programmatic APIs).
\nSubmission directly to the EU Open Research Repository.
\nAutomated harvesting from existing Zenodo content.
\nA representative of an EU project may request an EU Project Community and invite other project participants as members of the community. The project community is linked to one or more European Commission grants. All records in the project community are automatically integrated into the EU Open Research Repository immediately upon acceptance into the project community.
\nAny user may submit a record directly to the EU Open Research Repository. The submission will be moderated by Zenodo staff for compliance with the minimal required metadata requirements and its correctness.
\nRecords found among Zenodo’s existing content will on a regular basis automatically be integrated if they are found to comply with the requirements. The submissions through this method are integrated into the EU Open Research Repository with delay in a fully automated way.
\nRecords in the EU Open Research Repository are required to comply with the following minimal metadata requirements:
\nVisibility: Both public and restricted (with or without embargo and/or access request)
\nResource types: All resource types.
\nLicenses: Public and embargoed records MUST specify a license.
\nFunding information: Records MUST specify at least one grant from the European Commission.
\nCreators: Creators SHOULD be identified with a persistent identifier (e.g. ORCID, GND, …), and affiliations SHOULD be identified with a persistent identifier (e.g. ROR, ISNI, …)
\nSubjects: Records SHOULD specify one or more fields of science from the European Science Vocabulary.
\nAll submissions will undergo automated curation checks for compliance with the policy. Submissions through project communities are reviewed by the project community. Submission directly to the EU Open Research Repository is reviewed by Zenodo staff.
\nCommunity curators may at any point edit metadata of the records in the community without notice through human or automated processing. The curators may at their sole discretion remove records from the community that are deemed not to comply with the content and curation policy or which are deemed of insufficient quality.
\nThe content and curation policy is subject to change by the community owner at any time and without notice, other than through updating this page.
", "description": "Open repository for EU-funded research outputs from Horizon Europe, Euratom and earlier Framework Programmes.", "organizations": [ { "id": "00k4n6c32" } ], "page": "The EU Open Research Repository is a Zenodo-community dedicated to fostering open science and enhancing the visibility and accessibility of research outputs funded by the European Union. The community is managed by CERN on behalf of the European Commission.
\nThe mission of the repository is to support the implementation of the EU's open science policy, providing a trusted and comprehensive space for researchers to share their research outputs such as data, software, reports, presentations, posters and more. The EU Open Research Repository simplifies the process of complying with open science requirements, ensuring that research outputs from Horizon Europe, Euratom, and earlier Framework Programmes are freely accessible, thereby accelerating scientific discovery and innovation.
\nThe EU Open Research Repository serves as a complementary platform to the Open Research Europe (ORE) publishing platform. Open Research Europe focuses on providing a publishing venue for peer-reviewed articles, ensuring that research meets rigorous academic standards. The EU Open Research Repository provides a space for all the other research outputs including data sets, software, posters, and presentations that are out of scope for ORE. This holistic approach enables researchers to not only publish their findings but also share the underlying data and materials that support their work, fostering transparency and reproducibility in the scientific process.
\nCurrently in its pilot phase and set to be fully operational during autumn 2024, the EU Open Research Repository is constantly evolving. Efforts are committed to integrating cutting-edge features, including automated curation checks and FAIR (Findable, Accessible, Interoperable, and Reusable) assistance, to further support the research community. The goal is to provide researchers with a simple goto solution for making their publicly funded research open and as FAIR as possible.
\nThe EU Open Research Repository is funded by the European Union under grant agreement no. 101122956(HORIZON-ZEN). For more information about the project see https://about.zenodo.org/projects/horizon-zen/.
", "title": "EU Open Research Repository (Pilot)", "type": { "id": "organization" }, "website": "https://research-and-innovation.ec.europa.eu" }, "revision_id": 16, "slug": "eu", "theme": { "brand": "horizon", "enabled": true, "style": { "font": { "family": "Arial, sans-serif", "size": "16px", "weight": 600 }, "mainHeaderBackgroundColor": "#FFFFFF", "primaryColor": "#004494", "primaryTextColor": "#FFFFFF", "secondaryColor": "#FFD617", "secondaryTextColor": "#000000", "tertiaryColor": "#e3eefd", "tertiaryTextColor": "#1c5694" } }, "updated": "2024-03-20T06:47:47.577483+00:00" } ], "ids": [ "f0a8b890-f97a-4eb2-9eac-8b8a712d3a6c" ] }, "id": "4004169", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.4004169", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.4004170", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:4004170", "provider": "oai" } }, "revision_id": 2, "stats": { "all_versions": { "data_volume": 409401073.0, "downloads": 137, "unique_downloads": 114, "unique_views": 70, "views": 79 }, "this_version": { "data_volume": 409401073.0, "downloads": 137, "unique_downloads": 114, "unique_views": 69, "views": 78 } }, "status": "published", "updated": "2020-08-28T00:59:23.696046+00:00", "versions": { "index": 1, "is_latest": true } }