{"id":"https://openalex.org/W7224747709","doi":"https://doi.org/10.5281/zenodo.23824500","title":"A Held-Out Site Is a Sample of One: What Random, Spatial and Site-Disjoint Splits Each Estimate, Why Leakage That Differs Between Configurations Reorders a Comparison, and How Many Sites a General Claim Needs","display_name":"A Held-Out Site Is a Sample of One: What Random, Spatial and Site-Disjoint Splits Each Estimate, Why Leakage That Differs Between Configurations Reorders a Comparison, and How Many Sites a General Claim Needs","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7224747709","doi":"https://doi.org/10.5281/zenodo.23824500"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23824500","doi":"https://doi.org/10.5281/zenodo.23824500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23824500","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.23824500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147720734","display_name":"Pranay M. Mahendrakar","orcid":"https://orcid.org/0009-0003-7224-029X","observed_orcids":["https://orcid.org/0009-0003-7224-029X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mahendrakar, Pranay","raw_affiliation_strings":["SONYTECH"],"raw_orcid":"https://orcid.org/0009-0003-7224-029X","affiliations":[{"raw_affiliation_string":"SONYTECH","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147720734"],"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/T12535","display_name":"Machine Learning and Data Classification","score":0.4569999873638153,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.4569999873638153,"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/T10616","display_name":"Smart Agriculture and AI","score":0.13590000569820404,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.03909999877214432,"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/spatial-cross-validation","display_name":"spatial cross-validation","score":0.9259999990463257},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.6470000147819519},{"id":"https://openalex.org/keywords/optimism-bias","display_name":"optimism bias","score":0.35199999809265137},{"id":"https://openalex.org/keywords/pessimistic-bias","display_name":"pessimistic bias","score":0.8069999814033508},{"id":"https://openalex.org/keywords/small-sample-inference","display_name":"small sample inference","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4424999952316284},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C131676636","wikidata":"https://www.wikidata.org/wiki/Q5282696","display_name":"Dispute resolution","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2912999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C141239990","wikidata":"https://www.wikidata.org/wiki/Q957423","display_name":"Superresolution","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26570001244544983},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.257099986076355},{"id":"https://openalex.org/C2777016058","wikidata":"https://www.wikidata.org/wiki/Q7574061","display_name":"Spatial distribution","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23824500","doi":"https://doi.org/10.5281/zenodo.23824500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23824500","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.23824501","doi":"https://doi.org/10.5281/zenodo.23824501","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23824501","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.23824500","doi":"https://doi.org/10.5281/zenodo.23824500","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23824500","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6960185478","https://openalex.org/W7214586204","https://openalex.org/W7221700834","https://openalex.org/W7224503221","https://openalex.org/W7167249743","https://openalex.org/W4313071984","https://openalex.org/W7223563915","https://openalex.org/W7154452949","https://openalex.org/W4411921886","https://openalex.org/W7162781652"],"abstract_inverted_index":{"(c)":[0],"2026":[1,14],"Pranay":[2],"Mahendrakar.":[3],"Licensed":[4],"under":[5,35,335],"CC":[6],"BY":[7],"4.0.":[8],"Life":[9],"of":[10,16,86,174,189],"Research":[11],"A":[12],"September":[13],"study":[15],"farm-machinery":[17],"traversability":[18],"reports":[19],"that":[20,41,51,66,92,128,134,150,198,223,250,344,356],"a":[21,28,32,60,90,110,165,169,191,201,234,248,255,297,309,330,342],"forward-facing":[22],"near-infrared":[23,53],"camera":[24,30,71],"appears":[25],"to":[26,148],"beat":[27],"colour":[29,63],"on":[31,218,222,284],"paddy-boundary":[33],"class":[34],"its":[36],"corpus's":[37],"own":[38],"sequence-level":[39],"split,":[40],"the":[42,52,69,80,117,141,187,209,215,237,333,348],"advantage":[43,184],"disappears":[44],"once":[45,208],"recording":[46],"sites":[47,190,252],"are":[48],"held":[49,72],"apart,":[50],"configuration":[54],"gained":[55],"more":[56,225],"from":[57],"having":[58],"seen":[59],"site":[61,76,82,319],"than":[62,226],"did,":[64],"and":[65,97,123,133,144,181,197,214,257,291,296,352],"two":[67,175],"leads":[68],"second":[70],"at":[73,168],"one":[74,317,321],"held-out":[75,81,318],"changed":[77],"sign":[78],"when":[79,243],"was":[83],"rotated.":[84],"Each":[85],"those":[87],"findings":[88],"touches":[89],"literature":[91],"disagrees":[93],"with":[94],"itself:":[95],"ecologists":[96],"remote-sensing":[98],"researchers":[99],"dispute":[100,119,206,239],"whether":[101,182],"spatial":[102],"cross-validation":[103],"corrects":[104],"an":[105,157,183,339],"optimistic":[106],"bias":[107],"or":[108,268],"introduces":[109],"pessimistic":[111],"one,":[112],"clinical":[113],"machine":[114],"learning":[115],"had":[116],"same":[118],"over":[120],"subject-wise":[121],"splitting,":[122],"machine-learning":[124],"benchmarks":[125],"report":[126],"both":[127,219],"rankings":[129],"survive":[130],"distribution":[131],"shift":[132],"they":[135],"do":[136],"not.":[137],"In":[138],"this":[139],"analysis":[140],"author":[142],"reviews":[143],"synthesises":[145],"published":[146,216,259,327],"results":[147,260,328],"show":[149,264],"these":[151],"disputes":[152],"concern":[153],"three":[154],"different":[155,202],"questions":[156],"evaluation":[158,347],"can":[159,253],"be":[160],"asked":[161],"-":[162,196],"how":[163],"accurate":[164],"model":[166],"is":[167,177,212,308,320],"stated":[170],"target":[171,211],"(level),":[172],"which":[173,336],"configurations":[176,246],"better":[178],"there":[179],"(order),":[180],"holds":[185],"across":[186],"population":[188],"deployment":[192],"will":[193],"meet":[194],"(generality)":[195],"each":[199,346],"needs":[200],"design.":[203],"The":[204,230,305,323],"level":[205,238],"resolves":[207],"prediction":[210],"specified,":[213],"positions":[217],"sides":[220],"agree":[221],"resolution":[224],"their":[227],"titles":[228],"suggest.":[229],"order":[231],"question":[232,307],"has":[233],"failure":[235],"mode":[236],"does":[240],"not":[241,314],"cover:":[242],"leakage":[244,337],"inflates":[245],"unequally,":[247],"split":[249],"shares":[251],"reverse":[254],"comparison,":[256],"six":[258],"in":[261,272,300,312,315,329],"four":[262],"fields":[263],"it":[265,350],"doing":[266],"so":[267],"coming":[269],"close:":[270],"reversals":[271],"Kang":[273],"(2026),":[274],"Zech":[275],"et":[276,280,288,293,302],"al.":[277,281,289,294,303],"(2018),":[278,295],"Liang":[279],"(2017)":[282],"and,":[283],"small":[285],"margins,":[286],"Meyer":[287],"(2019)":[290],"Schratz":[292],"several-fold":[298],"shrinkage":[299],"Milioto":[301],"(2018).":[304],"generality":[306],"small-sample":[310],"problem":[311],"sites,":[313],"images:":[316],"observation.":[322],"paper":[324],"consolidates":[325],"24":[326],"table,":[331],"derives":[332],"condition":[334],"preserves":[338],"ordering,":[340],"states":[341],"procedure":[343],"assigns":[345],"claim":[349],"licenses,":[351],"specifies":[353],"five":[354],"studies":[355],"would":[357],"settle":[358],"what":[359],"remains":[360],"open.":[361]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-31T00:00:00"}
