{"id":"https://openalex.org/W7224096439","doi":"https://doi.org/10.5281/zenodo.23605849","title":"Copy and relatedness leaks in genomic language model benchmarks are common and can be found and largely removed automatically","display_name":"Copy and relatedness leaks in genomic language model benchmarks are common and can be found and largely removed automatically","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224096439","doi":"https://doi.org/10.5281/zenodo.23605849"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23605849","doi":"https://doi.org/10.5281/zenodo.23605849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23605849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23605849","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073858793","display_name":"Tejasvi Singh Tomar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tomar, Tejasvi Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4668-3639","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5073858793"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3215000033378601,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3215000033378601,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.29809999465942383,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.08309999853372574,"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/genomic-language-models","display_name":"genomic language models","score":0.8059999942779541},{"id":"https://openalex.org/keywords/nucleotide-transformer","display_name":"Nucleotide Transformer","score":0.8389999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381999850273132},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4392000138759613},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23605849","doi":"https://doi.org/10.5281/zenodo.23605849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23605849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23605850","doi":"https://doi.org/10.5281/zenodo.23605850","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23605850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23605849","doi":"https://doi.org/10.5281/zenodo.23605849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23605849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7224083133","https://openalex.org/W4414090232","https://openalex.org/W4411805238","https://openalex.org/W7152411707","https://openalex.org/W7171508104","https://openalex.org/W7170056316","https://openalex.org/W4417199851","https://openalex.org/W7214622400","https://openalex.org/W7204209660","https://openalex.org/W7221748185"],"abstract_inverted_index":{"Genomic":[0,260],"language":[1],"model":[2],"benchmarks":[3,73],"rank":[4],"models,":[5],"but":[6],"on":[7,83,112,124,138,162,173,182,194,229,259],"some":[8],"tasks":[9,85,114,236],"a":[10,15,147,243,289],"no-model":[11,244],"rule,":[12],"such":[13],"as":[14],"nearest-training":[16],"lookup":[17],"that":[18,41,57,79,110,291],"copies":[19,43],"the":[20,23,31,52,59,68,92,150,191,202,226,232,269,278,284],"label":[21],"of":[22,46,67,98,109,158,167,190,225,263,273,276,283],"most":[24,84,262,282],"similar":[25],"training":[26,47,132],"item,":[27],"matches":[28],"or":[29,44],"beats":[30],"best":[32],"published":[33,74,93,249],"score.":[34],"Such":[35],"rules":[36,97,152],"exploit":[37],"leaks:":[38],"test":[39,134,200,212],"items":[40],"are":[42,142,204],"relatives":[45,63,130],"items,":[48],"negatives":[49,141,165],"constructed":[50,164],"from":[51,75,149,256],"positives,":[53],"and":[54,62,71,106,153,179,186,206,231,287],"genomic":[55,175,294],"positions":[56],"reveal":[58],"label.":[60],"Copies":[61],"occur":[64],"in":[65,131],"8":[66],"11":[69],"DNA":[70],"RNA":[72],"2024":[76],"to":[77,91,117],"2026":[78],"we":[80],"audited,":[81],"although":[82],"no":[86],"leak":[87,245,257],"rule":[88],"comes":[89],"close":[90],"scores.":[94],"The":[95],"frozen":[96,151],"our":[99],"linter,":[100,270],"seqleak,":[101],"recover":[102],"all":[103],"24":[104],"copy":[105],"relatedness":[107],"flags":[108],"audit":[111],"41":[113],"not":[115,217,241],"used":[116],"set":[118],"them.":[119],"In":[120],"pre-registered":[121],"fine-tuning":[122],"experiments":[123],"GUE's":[125,163],"yeast":[126],"histone-mark":[127],"tasks,":[128,275],"however,":[129],"raise":[133],"scores":[135,171,250],"only":[136,146],"slightly":[137],"average.":[139],"Constructed":[140],"rarer,":[143],"mostly":[144],"draw":[145],"warning":[148],"survive":[154],"re-splitting.":[155],"Yet":[156],"each":[157],"six":[159],"models":[160],"fine-tuned":[161],"instead":[166],"matched":[168,174],"genome":[169],"windows":[170],"lower":[172],"negatives,":[176,188],"by":[177],"0.15":[178],"0.41":[180],"AUROC":[181],"average":[183],"for":[184,293],"shuffled":[185],"segment-substituted":[187],"net":[189],"same":[192],"comparison":[193],"control":[195],"tasks.":[196],"On":[197],"independent":[198,211],"G+C-matched":[199],"sets":[201],"losses":[203],"0.14":[205],"0.31,":[207],"whereas":[208],"an":[209],"earlier":[210],"without":[213],"G+C":[214],"matching":[215],"did":[216],"meet":[218],"its":[219],"registered":[220],"criterion.":[221],"About":[222],"two":[223],"thirds":[224],"improvement":[227],"reported":[228],"GUE":[230],"original":[233],"Nucleotide":[234],"Transformer":[235],"since":[237],"their":[238],"release":[239,268],"does":[240],"exceed":[242],"rule's":[246],"score,":[247],"so":[248],"alone":[251],"cannot":[252],"tell":[253],"it":[254,264],"apart":[255],"exploitation;":[258],"Benchmarks,":[261],"lies":[265],"above.":[266],"We":[267],"leak-reduced":[271],"versions":[272],"60":[274],"which":[277],"re-split":[279],"ones":[280],"remove":[281],"lookup's":[285],"signal,":[286],"PairCtrl,":[288],"leaderboard":[290],"controls":[292],"position.":[295]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-29T00:00:00"}