{"id":"https://openalex.org/W4408793166","doi":"https://doi.org/10.1109/mc.2025.3527374","title":"Measuring and Visualizing Dataset Coverage for Machine Learning","display_name":"Measuring and Visualizing Dataset Coverage for Machine Learning","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4408793166","doi":"https://doi.org/10.1109/mc.2025.3527374"},"language":"en","primary_location":{"id":"doi:10.1109/mc.2025.3527374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mc.2025.3527374","pdf_url":null,"source":{"id":"https://openalex.org/S178916657","display_name":"Computer","issn_l":"0018-9162","issn":["0018-9162","1558-0814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5011985891","display_name":"D. Richard Kuhn","orcid":"https://orcid.org/0000-0003-0050-1596"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Richard Kuhn","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, MD, USA","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041317074","display_name":"M S Raunak","orcid":"https://orcid.org/0000-0003-4934-7331"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M S Raunak","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, MD, USA","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061215075","display_name":"Raghu N. Kacker","orcid":"https://orcid.org/0000-0002-7666-3391"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghu N. Kacker","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, MD, USA","institution_ids":["https://openalex.org/I1321296531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011985891"],"corresponding_institution_ids":["https://openalex.org/I1321296531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05668327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"4","first_page":"18","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.6291000247001648,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.6291000247001648,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.632994532585144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47139981389045715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4502800703048706},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4331994354724884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.632994532585144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47139981389045715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4502800703048706},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4331994354724884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mc.2025.3527374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mc.2025.3527374","pdf_url":null,"source":{"id":"https://openalex.org/S178916657","display_name":"Computer","issn_l":"0018-9162","issn":["0018-9162","1558-0814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1987220198","https://openalex.org/W2128204165","https://openalex.org/W2994987245","https://openalex.org/W3089213640","https://openalex.org/W3170449064","https://openalex.org/W3174573899","https://openalex.org/W4200596789","https://openalex.org/W4226216828","https://openalex.org/W4281664578","https://openalex.org/W4282541642","https://openalex.org/W4396909846","https://openalex.org/W4400074414"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Measuring":[0],"and":[1,33],"visualizing":[2],"the":[3],"relative":[4],"strength":[5],"of":[6,20],"datasets":[7],"in":[8,27],"machine":[9],"learning":[10],"can":[11],"be":[12],"highly":[13],"useful.":[14],"Combinatorial":[15],"methods":[16],"effectively":[17],"measure":[18],"coverage":[19],"interactions":[21],"between":[22],"features,":[23],"an":[24],"essential":[25],"consideration":[26],"judging":[28],"data":[29],"adequacy":[30],"for":[31],"training":[32],"testing.":[34]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}