{"id":"https://openalex.org/W7213268588","doi":"https://doi.org/10.64898/2026.09.09.750484","title":"Cell-level random splits leak group-owned answers in single-cell benchmarks","display_name":"Cell-level random splits leak group-owned answers in single-cell benchmarks","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213268588","doi":"https://doi.org/10.64898/2026.09.09.750484","pmid":"https://pubmed.ncbi.nlm.nih.gov/42780116","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13596545"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.09.750484","doi":"https://doi.org/10.64898/2026.09.09.750484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/15/2026.09.09.750484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/15/2026.09.09.750484.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044142335","display_name":"Hu Cang","orcid":"https://orcid.org/0000-0002-7096-2905","observed_orcids":["https://orcid.org/0000-0002-7096-2905"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hu Cang","raw_affiliation_strings":["Department of Developmental and Cell Biology, University of California, Irvine, Irvine, CA 92697, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Developmental and Cell Biology, University of California, Irvine, Irvine, CA 92697, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086505023","display_name":"Sha Sun","orcid":"https://orcid.org/0000-0002-0044-6403","observed_orcids":["https://orcid.org/0000-0002-0044-6403"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sha Sun","raw_affiliation_strings":["Department of Developmental and Cell Biology, University of California, Irvine, Irvine, CA 92697, USA"],"raw_orcid":"https://orcid.org/0000-0002-0044-6403","affiliations":[{"raw_affiliation_string":"Department of Developmental and Cell Biology, University of California, Irvine, Irvine, CA 92697, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044142335"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.6510000228881836},{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.7409999966621399},{"id":"https://openalex.org/keywords/clonal-architecture","display_name":"clonal architecture","score":0.33799999952316284},{"id":"https://openalex.org/keywords/exposure","display_name":"exposure","score":0.46799999475479126},{"id":"https://openalex.org/keywords/retrievability","display_name":"retrievability","score":0.968999981880188},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"nearest neighbor search","score":0.9319999814033508},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.3569999933242798},{"id":"https://openalex.org/keywords/patient-cohort","display_name":"patient cohort","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.516700029373169},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.296099990606308},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C34602496","wikidata":"https://www.wikidata.org/wiki/Q2271882","display_name":"Sequential probability ratio test","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.09.750484","doi":"https://doi.org/10.64898/2026.09.09.750484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/15/2026.09.09.750484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:42780116","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42780116","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13596545","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42780116/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.64898/2026.09.09.750484","doi":"https://doi.org/10.64898/2026.09.09.750484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/15/2026.09.09.750484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000909676","display_name":"Smart Laser Capturing Microscope for Genome Wide Single Cell Spatial Transcriptomics","funder_award_id":"1r01hg014004-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213268588.pdf","grobid_xml":"https://content.openalex.org/works/W7213268588.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4395660103","https://openalex.org/W4401159754"],"related_works":["https://openalex.org/W7202377924","https://openalex.org/W7202111985","https://openalex.org/W7202081072","https://openalex.org/W7170897467","https://openalex.org/W4409257324","https://openalex.org/W7222941461","https://openalex.org/W4407893446","https://openalex.org/W4413756015","https://openalex.org/W7154319394","https://openalex.org/W2174534287"],"abstract_inverted_index":{"Machine":[0],"learning":[1,74],"models":[2],"in":[3,58,119,180,184,203],"single-cell":[4],"biology":[5,24],"increasingly":[6],"forecast":[7],"differentiation,":[8],"reprogramming":[9],"and":[10,62,121,139,152,183],"therapeutic":[11],"response":[12],"from":[13,34,105,171],"early":[14],"transcriptomic":[15],"profiles.":[16],"Testing":[17],"whether":[18,144],"a":[19,63,70,75,125,130,145,149,185,192],"model":[20,64,208],"has":[21,169],"learned":[22],"real":[23],"requires":[25],"held-out":[26],"cells.":[27],"Single-cell":[28],"data,":[29,141],"however,":[30],"are":[31],"grouped:":[32],"cells":[33,116],"the":[35,42,59,109,112,160,206],"same":[36,43],"clone,":[37],"patient":[38,140,186],"or":[39],"batch":[40],"share":[41],"label.":[44],"A":[45],"random":[46,146],"split":[47,147],"therefore":[48],"places":[49],"relatives":[50,118],"of":[51,73,108,114],"each":[52,90],"test":[53,115],"cell,":[54],"carrying":[55],"its":[56],"label,":[57],"training":[60,102],"set,":[61],"can":[65,158],"score":[66],"well":[67],"by":[68],"memorizing":[69],"relative":[71,131],"instead":[72],"transferable":[76],"rule.":[77],"Grouped":[78],"validation":[79],"removes":[80],"this":[81,99],"leakage":[82,100,150],"but":[83],"leaves":[84],"far":[85],"fewer":[86],"independent":[87],"units":[88],"behind":[89],"error":[91],"bar.":[92],"Here":[93],"we":[94],"show":[95],"how":[96,123,155],"to":[97,190],"estimate":[98],"before":[101,205],"any":[103],"model,":[104],"two":[106],"properties":[107,202],"data:":[110],"exposure,":[111],"fraction":[113],"with":[117],"training,":[120],"retrievability,":[122],"often":[124],"nearest-neighbor":[126],"search":[127],"returns":[128],"such":[129],"rather":[132],"than":[133],"an":[134],"unrelated":[135],"cell.":[136],"Across":[137],"lineage-barcoded":[138],"exposure":[142],"determines":[143,154],"opens":[148],"channel,":[151],"retrievability":[153],"much":[156,173],"it":[157],"inflate":[159],"score.":[161],"The":[162],"inflation":[163],"is":[164,209],"negligible":[165],"where":[166,175],"cell":[167],"state":[168],"decoupled":[170],"ancestry,":[172],"larger":[174],"clonal":[176],"sisters":[177],"remain":[178],"close":[179],"expression":[181],"space,":[182],"cohort":[187],"large":[188],"enough":[189],"overturn":[191],"clinical":[193],"conclusion.":[194],"We":[195],"also":[196],"provide":[197],"leakcheck,":[198],"which":[199],"computes":[200],"both":[201],"seconds,":[204],"outcome":[207],"fitted.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-16T00:00:00"}