{"id":"https://openalex.org/W4410859924","doi":"https://doi.org/10.1186/s40537-025-01193-8","title":"Overview of leakage scenarios in supervised machine learning","display_name":"Overview of leakage scenarios in supervised machine learning","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4410859924","doi":"https://doi.org/10.1186/s40537-025-01193-8"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01193-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01193-8","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01193-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01193-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043815564","display_name":"Leonard Sasse","orcid":"https://orcid.org/0000-0002-2400-3404"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]},{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I4210130445","display_name":"Max Planck Institute for Human Cognitive and Brain Sciences","ror":"https://ror.org/0387jng26","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210130445"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"L. Sasse","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","Max Planck School of Cognition, Stephanstrasse 1a, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]},{"raw_affiliation_string":"Max Planck School of Cognition, Stephanstrasse 1a, Leipzig, Germany","institution_ids":["https://openalex.org/I4210130445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001220330","display_name":"Eliana Nicolaisen\u2010Sobesky","orcid":"https://orcid.org/0000-0002-4806-2863"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"E. Nicolaisen-Sobesky","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059906003","display_name":"Juergen Dukart","orcid":"https://orcid.org/0000-0003-0492-5644"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Dukart","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007313280","display_name":"Simon B. Eickhoff","orcid":"https://orcid.org/0000-0001-6363-2759"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. B. Eickhoff","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010048557","display_name":"Michael G\u00f6tz","orcid":"https://orcid.org/0000-0003-0984-224X"},"institutions":[{"id":"https://openalex.org/I4210155144","display_name":"University Hospital Ulm","ror":"https://ror.org/05emabm63","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210155144"]},{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. G\u00f6tz","raw_affiliation_strings":["Division of Experimental Radiology, Department for Diagnostic and Interventional Radiology, Ulm University Medical Center, Ulm, Germany","Experimental Radiology, University Ulm, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Division of Experimental Radiology, Department for Diagnostic and Interventional Radiology, Ulm University Medical Center, Ulm, Germany","institution_ids":["https://openalex.org/I4210155144","https://openalex.org/I196349391"]},{"raw_affiliation_string":"Experimental Radiology, University Ulm, Ulm, Germany","institution_ids":["https://openalex.org/I196349391","https://openalex.org/I4210155144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042943582","display_name":"Sami Hamdan","orcid":"https://orcid.org/0000-0002-4398-2441"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]},{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Hamdan","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092820208","display_name":"Vera Komeyer","orcid":"https://orcid.org/0000-0001-9486-0922"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]},{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"V. Komeyer","raw_affiliation_strings":["Department of Biology, Faculty of Mathematics and Natural Sciences, Heinrich Heine University Duesseldorf, Duesseldorf, Germany","Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Biology, Faculty of Mathematics and Natural Sciences, Heinrich Heine University Duesseldorf, Duesseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]},{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110113414","display_name":"Abhijit Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139993","display_name":"Global Services (Slovakia)","ror":"https://ror.org/047kbmp67","country_code":"SK","type":"company","lineage":["https://openalex.org/I4210139993"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"A. Kulkarni","raw_affiliation_strings":["Principal Global Services, Pune, India"],"affiliations":[{"raw_affiliation_string":"Principal Global Services, Pune, India","institution_ids":["https://openalex.org/I4210139993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036568583","display_name":"Juha M. Lahnakoski","orcid":"https://orcid.org/0000-0002-5223-7822"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]},{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. M. Lahnakoski","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069362336","display_name":"Bradley C. Love","orcid":"https://orcid.org/0000-0002-7883-7076"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. C. Love","raw_affiliation_strings":["Computer, Computational, and Statistical Sciences, Los Alamos National Laboratory, Los Alamos, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer, Computational, and Statistical Sciences, Los Alamos National Laboratory, Los Alamos, United States of America","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053862168","display_name":"Federico Raimondo","orcid":"https://orcid.org/0000-0003-4087-8259"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F. Raimondo","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083494075","display_name":"Kaustubh R. Patil","orcid":"https://orcid.org/0000-0002-0289-5480"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]},{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE","IN"],"is_corresponding":false,"raw_author_name":"Kaustubh R. Patil","raw_affiliation_strings":["Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","Koita Centre for Digital Health, IIT Bombay, Mumbai, 400076, India"],"affiliations":[{"raw_affiliation_string":"Institute of Neuroscience and Medicine, Brain and Behaviour (INM-7), Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Institute of Systems Neuroscience, Medical Faculty, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]},{"raw_affiliation_string":"Koita Centre for Digital Health, IIT Bombay, Mumbai, 400076, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5043815564"],"corresponding_institution_ids":["https://openalex.org/I171892758","https://openalex.org/I4210130445","https://openalex.org/I44260953"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":61.3158,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.99880006,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.8186594843864441},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.6965625286102295},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.5943772196769714},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5241292119026184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016047954559326},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33484768867492676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186594843864441},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.6965625286102295},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5943772196769714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5241292119026184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016047954559326},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33484768867492676},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-025-01193-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01193-8","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01193-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4eff38ec60c42c6ae034b5c6bf96965","is_oa":true,"landing_page_url":"https://doaj.org/article/c4eff38ec60c42c6ae034b5c6bf96965","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 12, Iss 1, Pp 1-23 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01193-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01193-8","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01193-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2773239854","display_name":null,"funder_award_id":"Projekt DEAL","funder_id":"https://openalex.org/F4320322434","funder_display_name":"Max-Planck-Gesellschaft"},{"id":"https://openalex.org/G3514550006","display_name":null,"funder_award_id":"Centre","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5168466499","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G6743243744","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7154890119","display_name":null,"funder_award_id":"431549029","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7537950183","display_name":null,"funder_award_id":"CRC1451","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G762232396","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8330397625","display_name":null,"funder_award_id":"Funding","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8767435255","display_name":null,"funder_award_id":"945539","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8928656450","display_name":null,"funder_award_id":"Projekt DEAL","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410859924.pdf","grobid_xml":"https://content.openalex.org/works/W4410859924.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1552009804","https://openalex.org/W1555759181","https://openalex.org/W1981251392","https://openalex.org/W2024729467","https://openalex.org/W2029445248","https://openalex.org/W2072876893","https://openalex.org/W2077641783","https://openalex.org/W2098740506","https://openalex.org/W2111902267","https://openalex.org/W2117829824","https://openalex.org/W2141007997","https://openalex.org/W2144981148","https://openalex.org/W2154290668","https://openalex.org/W2157755551","https://openalex.org/W2293040502","https://openalex.org/W2406349003","https://openalex.org/W2421101021","https://openalex.org/W2487770199","https://openalex.org/W2562251009","https://openalex.org/W2736287575","https://openalex.org/W2766099988","https://openalex.org/W2787894218","https://openalex.org/W2788572835","https://openalex.org/W2896236534","https://openalex.org/W2897042519","https://openalex.org/W2942047515","https://openalex.org/W2947014533","https://openalex.org/W2949222200","https://openalex.org/W2963521553","https://openalex.org/W2966848807","https://openalex.org/W2979650665","https://openalex.org/W2981679558","https://openalex.org/W2990091959","https://openalex.org/W2990963920","https://openalex.org/W2998649189","https://openalex.org/W2998701638","https://openalex.org/W3025161810","https://openalex.org/W3028493752","https://openalex.org/W3045004532","https://openalex.org/W3083804794","https://openalex.org/W3086029573","https://openalex.org/W3093451924","https://openalex.org/W3099848476","https://openalex.org/W3100279624","https://openalex.org/W3104128335","https://openalex.org/W3113493652","https://openalex.org/W3130390764","https://openalex.org/W3130801515","https://openalex.org/W3134939446","https://openalex.org/W3143569708","https://openalex.org/W3146796711","https://openalex.org/W3164340364","https://openalex.org/W3165292502","https://openalex.org/W3170657538","https://openalex.org/W3186118520","https://openalex.org/W3193448347","https://openalex.org/W3208504364","https://openalex.org/W3212368439","https://openalex.org/W3214734349","https://openalex.org/W3217037671","https://openalex.org/W3217314753","https://openalex.org/W4210818739","https://openalex.org/W4212863985","https://openalex.org/W4212876805","https://openalex.org/W4220751562","https://openalex.org/W4223430324","https://openalex.org/W4292121845","https://openalex.org/W4292791807","https://openalex.org/W4321073670","https://openalex.org/W4327923045","https://openalex.org/W4362673421","https://openalex.org/W4366494274","https://openalex.org/W4385576721","https://openalex.org/W4387210595","https://openalex.org/W4392232009","https://openalex.org/W4401455507","https://openalex.org/W6675354045"],"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":{"Abstract":[0],"Machine":[1],"learning":[2],"(ML)":[3],"provides":[4],"powerful":[5],"tools":[6],"for":[7],"predictive":[8],"modeling.":[9],"ML\u2019s":[10],"popularity":[11],"stems":[12],"from":[13,26],"the":[14],"promise":[15],"of":[16,24,96,99],"sample-level":[17],"prediction":[18],"with":[19,73],"applications":[20],"across":[21],"a":[22,91],"variety":[23],"fields":[25],"physics":[27],"and":[28,37,50,63,81,94],"marketing":[29],"to":[30,52,54,69,76],"healthcare.":[31],"However,":[32],"if":[33],"not":[34],"properly":[35],"implemented":[36],"evaluated,":[38],"ML":[39,83,105],"pipelines":[40],"may":[41,102],"contain":[42],"leakage":[43,77,100],"typically":[44],"resulting":[45],"in":[46,104],"overoptimistic":[47],"performance":[48],"estimates":[49],"failure":[51],"generalize":[53],"new":[55],"data.":[56],"This":[57],"can":[58],"have":[59],"severe":[60],"negative":[61],"financial":[62],"societal":[64],"implications.":[65],"Our":[66],"aim":[67],"is":[68],"expand":[70],"understanding":[71],"associated":[72],"causes":[74],"leading":[75],"when":[78],"designing,":[79],"implementing,":[80],"evaluating":[82],"pipelines.":[84,106],"Illustrated":[85],"by":[86],"concrete":[87],"examples,":[88],"we":[89],"provide":[90],"comprehensive":[92],"overview":[93],"discussion":[95],"various":[97],"types":[98],"that":[101],"arise":[103]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":11}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-05-30T00:00:00"}
