{"id":"https://openalex.org/W4297678136","doi":"https://doi.org/10.48550/arxiv.2209.03345","title":"Data Leakage in Notebooks: Static Detection and Better Processes","display_name":"Data Leakage in Notebooks: Static Detection and Better Processes","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4297678136","doi":"https://doi.org/10.48550/arxiv.2209.03345"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.03345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.03345","pdf_url":"https://arxiv.org/pdf/2209.03345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.03345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082950698","display_name":"Chenyang Yang","orcid":"https://orcid.org/0000-0003-0058-0765"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Chenyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112865849","display_name":"Rachel A Brower-Sinning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brower-Sinning, Rachel A","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015259511","display_name":"Grace A. Lewis","orcid":"https://orcid.org/0000-0001-9128-9863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lewis, Grace A.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067467896","display_name":"Christian K\u00e4stner","orcid":"https://orcid.org/0000-0002-4450-4572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K\u00e4stner, Christian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082950698"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.988099992275238,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.988099992275238,"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/T10260","display_name":"Software Engineering Research","score":0.9879000186920166,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9837999939918518,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.7819057703018188},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.7767208814620972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6387696862220764},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.44719386100769043},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.4199380874633789},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.39599424600601196},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3955051004886627},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.32654130458831787},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.209509938955307},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09366282820701599}],"concepts":[{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.7819057703018188},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.7767208814620972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387696862220764},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.44719386100769043},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4199380874633789},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.39599424600601196},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3955051004886627},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.32654130458831787},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.209509938955307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09366282820701599},{"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},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.03345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.03345","pdf_url":"https://arxiv.org/pdf/2209.03345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.03345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.03345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.03345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.03345","pdf_url":"https://arxiv.org/pdf/2209.03345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1590719878","https://openalex.org/W4244271513","https://openalex.org/W4376622330","https://openalex.org/W2365974527","https://openalex.org/W4306382224","https://openalex.org/W4226517682","https://openalex.org/W3108263396","https://openalex.org/W2895872277","https://openalex.org/W4284675145","https://openalex.org/W2372021191"],"abstract_inverted_index":{"Data":[0],"science":[1,80],"pipelines":[2],"to":[3,27,37,62,71],"train":[4],"and":[5,22,60,92,115,117],"evaluate":[6],"models":[7,41],"with":[8],"machine":[9],"learning":[10],"may":[11,57],"contain":[12],"bugs":[13],"just":[14],"like":[15],"any":[16],"other":[17],"code.":[18,81],"Leakage":[19],"between":[20],"training":[21],"test":[23],"data":[24,76,79,90],"can":[25,46,111,121],"lead":[26],"overestimating":[28],"the":[29,125],"model's":[30],"accuracy":[31],"during":[32],"offline":[33],"evaluations,":[34],"possibly":[35],"leading":[36],"deployment":[38],"of":[39,75],"low-quality":[40],"in":[42,78],"production.":[43],"Such":[44],"leakage":[45,77,91,95,119],"happen":[47],"easily":[48],"by":[49,52],"mistake":[50],"or":[51],"following":[53],"poor":[54],"practices,":[55],"but":[56],"be":[58,122],"tedious":[59],"challenging":[61],"detect":[63,72],"manually.":[64],"We":[65,104],"develop":[66],"a":[67],"static":[68,108],"analysis":[69,87,109],"approach":[70,110],"common":[73],"forms":[74],"Our":[82],"evaluation":[83],"shows":[84],"that":[85,93],"our":[86,107],"accurately":[88],"detects":[89],"such":[94],"is":[96],"pervasive":[97],"among":[98],"over":[99],"100,000":[100],"analyzed":[101],"public":[102],"notebooks.":[103],"discuss":[105],"how":[106,118],"help":[112],"both":[113],"practitioners":[114],"educators,":[116],"prevention":[120],"designed":[123],"into":[124],"development":[126],"process.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}