{"id":"https://openalex.org/W7222415650","doi":"https://doi.org/10.26434/chemrxiv.15010923/v1","title":"What topology hold-out removes\u2014and what it does not","display_name":"What topology hold-out removes\u2014and what it does not","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7222415650","doi":"https://doi.org/10.26434/chemrxiv.15010923/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15010923/v1","doi":"https://doi.org/10.26434/chemrxiv.15010923/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010923/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010923/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010923/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158897071","display_name":"wang359826","orcid":"https://orcid.org/0009-0005-2334-4636","observed_orcids":["https://orcid.org/0009-0005-2334-4636"]},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Wang","raw_affiliation_strings":["College of Chemical Engineering","Nanjing Tech University"],"raw_orcid":"https://orcid.org/0009-0005-2334-4636","affiliations":[{"raw_affiliation_string":"College of Chemical Engineering","institution_ids":[]},{"raw_affiliation_string":"Nanjing Tech University","institution_ids":["https://openalex.org/I134687103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5158897071"],"corresponding_institution_ids":["https://openalex.org/I134687103"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10096","display_name":"Metal-Organic Frameworks: Synthesis and Applications","score":0.5127000212669373,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10096","display_name":"Metal-Organic Frameworks: Synthesis and Applications","score":0.5127000212669373,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.4821999967098236,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10967","display_name":"Carbon Dioxide Capture Technologies","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1506","display_name":"Filtration and Separation"},"field":{"id":"https://openalex.org/fields/15","display_name":"Chemical Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metal-organic-frameworks","display_name":"metal-organic frameworks","score":0.9359999895095825},{"id":"https://openalex.org/keywords/co2-capture","display_name":"CO2 capture","score":0.9559999704360962},{"id":"https://openalex.org/keywords/validation-protocol","display_name":"validation protocol","score":0.32600000500679016},{"id":"https://openalex.org/keywords/chemical-composition-distribution","display_name":"chemical composition distribution","score":0.46700000762939453},{"id":"https://openalex.org/keywords/loss-of-support","display_name":"loss of support","score":0.44600000977516174},{"id":"https://openalex.org/keywords/mof-screening","display_name":"MOF screening","score":0.4790000021457672},{"id":"https://openalex.org/keywords/hmof","display_name":"hMOF","score":0.5600000023841858},{"id":"https://openalex.org/keywords/hit-rate","display_name":"hit rate","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5281000137329102},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C59659247","wikidata":"https://www.wikidata.org/wiki/Q11990","display_name":"Reproduction","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2802000045776367},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22750000655651093},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2272000014781952}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.26434/chemrxiv.15010923/v1","doi":"https://doi.org/10.26434/chemrxiv.15010923/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010923/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010923/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.23415179","doi":"https://doi.org/10.5281/zenodo.23415179","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23415179","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.23415181","doi":"https://doi.org/10.5281/zenodo.23415181","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23415181","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":"Software"},{"id":"doi:10.5281/zenodo.23433981","doi":"https://doi.org/10.5281/zenodo.23433981","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23433981","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":"Software"},{"id":"doi:10.5281/zenodo.23434268","doi":"https://doi.org/10.5281/zenodo.23434268","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23434268","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.23618746","doi":"https://doi.org/10.5281/zenodo.23618746","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23618746","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.23622637","doi":"https://doi.org/10.5281/zenodo.23622637","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23622637","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15010923/v1","doi":"https://doi.org/10.26434/chemrxiv.15010923/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010923/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010923/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222415650.pdf","grobid_xml":"https://content.openalex.org/works/W7222415650.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4393880712"],"related_works":["https://openalex.org/W7223057179","https://openalex.org/W7164932395","https://openalex.org/W7168279704","https://openalex.org/W4412637822","https://openalex.org/W7169546597","https://openalex.org/W7162098927","https://openalex.org/W7162487522","https://openalex.org/W2888453876","https://openalex.org/W4400870189","https://openalex.org/W7162031371"],"abstract_inverted_index":{"Machine-learning":[0],"screens":[1],"of":[2,49,64,76,80,140],"metal\u2013organic":[3],"frameworks":[4],"(MOFs)":[5],"for":[6,74],"CO2":[7],"capture":[8],"increasingly":[9],"report":[10],"the":[11,23,47,50,53,57,93,101,118,141,147,167],"validation":[12],"protocol":[13],"that":[14,52,217],"produced":[15],"a":[16,37,70,87,110,212],"score,":[17],"and":[18,40,78,115,190,226],"topology":[19,34,103,142,209],"hold-out":[20,35,136,210],"has":[21],"become":[22],"standard":[24],"stricter":[25],"alternative":[26],"to":[27,174],"random":[28],"splitting.":[29],"Prior":[30],"work":[31,45],"already":[32],"reads":[33],"as":[36,203,211],"combined":[38],"structural":[39],"chemical":[41,66,88,222],"distribution":[42],"shift;":[43],"this":[44],"measures":[46],"size":[48],"chemistry":[51],"split":[54],"withholds.":[55],"On":[56,92],"hypothetical-MOF":[58],"library":[59],"hMOF":[60,189],"(324,426":[61],"structures),":[62],"74.7%":[63],"coarse-grained":[65],"compositions":[67],"occur":[68],"in":[69,90,182],"single":[71],"topology,":[72],"accounting":[73],"61.3%":[75],"structures,":[77],"seven":[79],"eleven":[81],"topologies":[82],"leave":[83],"every":[84],"structure":[85],"without":[86],"counterpart":[89],"training.":[91],"one":[94],"usable":[95],"chemistry-matched":[96],"pair":[97],"(pcu":[98],"\u2194nbo),":[99],"removing":[100,116],"partner":[102,120,126],"raised":[104],"nbo-side":[105],"MAE":[106],"by":[107],"70.0%":[108],"while":[109,215],"size-matched":[111],"control":[112],"did":[113],"not,":[114],"only":[117,138],"shared-composition":[119],"rows":[121],"improved":[122],"pcu-side":[123],"MAE,":[124],"so":[125,146],"coverage":[127],"is":[128,150,185],"direction-dependent":[129],"rather":[130,201],"than":[131,202],"uniformly":[132],"beneficial.":[133],"A":[134,179],"chemistry-key":[135],"produces":[137],"21.1%":[139],"hold-out's":[143],"R2":[144],"decrease,":[145],"support":[148,165,180],"loss":[149],"real":[151],"but":[152],"does":[153],"not":[154],"translate":[155],"proportionally":[156],"into":[157],"performance":[158],"loss.":[159],"Across":[160],"five":[161],"independently":[162],"redrawn":[163],"25,000-sample":[164],"sets,":[166],"top-1%":[168],"hit":[169],"rate":[170],"fell":[171],"from":[172],"50.4%":[173],"19.3%":[175],"under":[176,198],"topology-grouped":[177],"validation.":[178],"audit":[181],"ARC-MOF,":[183],"which":[184],"partly":[186],"dependent":[187],"on":[188],"uses":[191],"different":[192],"composition":[193],"keys,":[194],"confirms":[195],"strong":[196],"coupling":[197],"bounded":[199],"sensitivity":[200],"an":[204],"independent":[205],"replication.":[206],"We":[207],"retain":[208],"stress":[213],"test":[214],"recommending":[216],"groupedsplit":[218],"reports":[219],"disclose":[220],"their":[221],"support,":[223],"deployment-relevant":[224],"aggregation":[225],"ranking":[227],"performance.":[228]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-17T00:00:00"}
