{"id":"https://openalex.org/W2946595616","doi":null,"title":"Data Validation for Machine Learning","display_name":"Data Validation for Machine Learning","publication_year":2019,"publication_date":"2019-04-15","ids":{"openalex":"https://openalex.org/W2946595616","mag":"2946595616"},"language":"en","primary_location":{"id":"mag:2946595616","doi":null,"is_oa":false,"landing_page_url":"https://proceedings.mlsys.org/paper/2019/file/5878a7ab84fb43402106c575658472fa-Paper.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090556758","display_name":"Eric J. Breck","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Breck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044323471","display_name":"Marty Zinkevich","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marty Zinkevich","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010950113","display_name":"Neoklis Polyzotis","orcid":"https://orcid.org/0000-0002-2694-8591","observed_orcids":["https://orcid.org/0000-0002-2694-8591"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neoklis Polyzotis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2694-8591","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X","observed_orcids":["https://orcid.org/0000-0001-6419-931X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Euijong Whang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065950643","display_name":"Sudip Roy","orcid":"https://orcid.org/0000-0002-0535-0531","observed_orcids":["https://orcid.org/0000-0002-0535-0531"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sudip Roy","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0535-0531","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.9666,"has_fulltext":false,"cited_by_count":182,"citation_normalized_percentile":{"value":0.98753974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"1","issue":null,"first_page":"334","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5698000192642212,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5698000192642212,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.39649999141693115,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.699999988079071},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.9179999828338623},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5291695594787598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47099751234054565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40574580430984497}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2946595616","doi":null,"is_oa":false,"landing_page_url":"https://proceedings.mlsys.org/paper/2019/file/5878a7ab84fb43402106c575658472fa-Paper.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W404240460","https://openalex.org/W1570448133","https://openalex.org/W1976732638","https://openalex.org/W1997952460","https://openalex.org/W2000809552","https://openalex.org/W2002934700","https://openalex.org/W2044535354","https://openalex.org/W2078639378","https://openalex.org/W2098759488","https://openalex.org/W2131400476","https://openalex.org/W2166775458","https://openalex.org/W2189162242","https://openalex.org/W2288244345","https://openalex.org/W2432911982","https://openalex.org/W2434390175","https://openalex.org/W2547386789","https://openalex.org/W2591700809","https://openalex.org/W2616028256","https://openalex.org/W2753069234","https://openalex.org/W2767280887","https://openalex.org/W2782864149","https://openalex.org/W2963207607","https://openalex.org/W3110197861"],"related_works":["https://openalex.org/W6922839789","https://openalex.org/W6922957437","https://openalex.org/W3144571334","https://openalex.org/W2906364242","https://openalex.org/W7095829966","https://openalex.org/W1914700511","https://openalex.org/W7096840558","https://openalex.org/W572185906","https://openalex.org/W7018083119","https://openalex.org/W6959938604"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-05-29T00:00:00"}
