{"id":"https://openalex.org/W7207553178","doi":"https://doi.org/10.48550/arxiv.2609.02883","title":"Repairing PBE-Spurious Metallicity for HSE06-Level Screening of 2D Photocatalysts for Green Hydrogen Production","display_name":"Repairing PBE-Spurious Metallicity for HSE06-Level Screening of 2D Photocatalysts for Green Hydrogen Production","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207553178","doi":"https://doi.org/10.48550/arxiv.2609.02883"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02883","pdf_url":"https://arxiv.org/pdf/2609.02883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.02883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023564573","display_name":"Ritam Chakraborty","orcid":"https://orcid.org/0009-0002-4824-1471","observed_orcids":["https://orcid.org/0009-0002-4824-1471"]},"institutions":[{"id":"https://openalex.org/I147481903","display_name":"Jawaharlal Nehru Centre for Advanced Scientific Research","ror":"https://ror.org/0538gdx71","country_code":"IN","type":"facility","lineage":["https://openalex.org/I147481903","https://openalex.org/I2799351866","https://openalex.org/I4210098748","https://openalex.org/I4210134808"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chakraborty, Ritam","raw_affiliation_strings":["\u2020Theoretical Sciences Unit , Jawaharlal Nehru Centre for Advanced Scientific Research (JNCASR) , Bangalore 560064 , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Theoretical Sciences Unit , Jawaharlal Nehru Centre for Advanced Scientific Research (JNCASR) , Bangalore 560064 , India","institution_ids":["https://openalex.org/I147481903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5149764718","display_name":"Arpan Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405268729","display_name":"Audisankara (Deemed to be University)","ror":"https://ror.org/01w9a6a91","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405268729"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Das, Arpan","raw_affiliation_strings":["\u2021Department of Science and Humanities , Audisankara (Deemed to be University) , Gudur 524101 , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Department of Science and Humanities , Audisankara (Deemed to be University) , Gudur 524101 , India","institution_ids":["https://openalex.org/I4405268729"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T11948","display_name":"Machine Learning in Materials Science","score":0.975600004196167,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.975600004196167,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10078","display_name":"Advanced Photocatalysis Techniques","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/green-hydrogen-production","display_name":"green hydrogen production","score":0.9800000190734863},{"id":"https://openalex.org/keywords/narrow-gap-semiconductors","display_name":"narrow-gap semiconductors","score":0.8450000286102295},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.6039999723434448},{"id":"https://openalex.org/keywords/materials-screening","display_name":"materials screening","score":0.4650000035762787},{"id":"https://openalex.org/keywords/computational-materials-database","display_name":"computational materials database","score":0.4269999861717224},{"id":"https://openalex.org/keywords/band-gap-prediction","display_name":"band gap prediction","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C99465377","wikidata":"https://www.wikidata.org/wiki/Q217030","display_name":"Metallicity","level":3,"score":0.44909998774528503},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.42640000581741333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42309999465942383},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C22693506","wikidata":"https://www.wikidata.org/wiki/Q3075290","display_name":"Hybrid functional","level":3,"score":0.4050999879837036},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.375},{"id":"https://openalex.org/C108225325","wikidata":"https://www.wikidata.org/wiki/Q11456","display_name":"Semiconductor","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C100253034","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Systematic error","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C512968161","wikidata":"https://www.wikidata.org/wiki/Q556","display_name":"Hydrogen","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C202189072","wikidata":"https://www.wikidata.org/wiki/Q1929999","display_name":"Hydrogen production","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C206139338","wikidata":"https://www.wikidata.org/wiki/Q192355","display_name":"Raw material","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C65165184","wikidata":"https://www.wikidata.org/wiki/Q218831","display_name":"Photocatalysis","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C86025842","wikidata":"https://www.wikidata.org/wiki/Q5358432","display_name":"Electronic structure","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.27239999175071716}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02883","pdf_url":"https://arxiv.org/pdf/2609.02883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.02883","doi":"https://doi.org/10.48550/arxiv.2609.02883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02883","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.02883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02883","pdf_url":"https://arxiv.org/pdf/2609.02883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207553178.pdf","grobid_xml":"https://content.openalex.org/works/W7207553178.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1906682345","https://openalex.org/W1970127494","https://openalex.org/W1971044734","https://openalex.org/W1979544533","https://openalex.org/W1981368803","https://openalex.org/W1994880295","https://openalex.org/W2003533963","https://openalex.org/W2007395042","https://openalex.org/W2015197254","https://openalex.org/W2083222334","https://openalex.org/W2085093563","https://openalex.org/W2295598076","https://openalex.org/W2334012917","https://openalex.org/W2464725281","https://openalex.org/W2601081289","https://openalex.org/W2804431384","https://openalex.org/W2806275814","https://openalex.org/W2967197658","https://openalex.org/W3094582681","https://openalex.org/W3129006275","https://openalex.org/W4286489048","https://openalex.org/W4288902439","https://openalex.org/W4385576721","https://openalex.org/W4387672521","https://openalex.org/W4390739817","https://openalex.org/W4396539521","https://openalex.org/W4400581110","https://openalex.org/W4411330529","https://openalex.org/W4415878236","https://openalex.org/W7149978657"],"related_works":["https://openalex.org/W7162037409","https://openalex.org/W7214555710","https://openalex.org/W7211901309","https://openalex.org/W4394856183","https://openalex.org/W4399804540","https://openalex.org/W7149978657","https://openalex.org/W7128488920","https://openalex.org/W3166368384","https://openalex.org/W7005786771","https://openalex.org/W4320032464"],"abstract_inverted_index":{"Semilocal":[0],"PBE":[1,40,54,148],"calculations":[2,153],"can":[3],"remove":[4],"viable":[5],"photocatalysts":[6],"before":[7],"screening":[8],"by":[9,27,195,200],"labeling":[10],"narrow-gap":[11],"semiconductors":[12],"as":[13],"metals.":[14],"We":[15],"address":[16],"this":[17],"failure":[18],"mode":[19],"in":[20],"the":[21,63,97,141,147,167,177],"Computational":[22],"2D":[23],"Materials":[24],"Database":[25],"(C2DB)":[26],"combining":[28],"leakage-aware":[29],"repair":[30],"of":[31,79,161],"PBE-spurious":[32],"metallicity":[33],"with":[34,74,83],"HSE06--PBE":[35],"$\u0394$-learning.":[36],"Stage~I":[37,89],"classifies":[38],"HSE06-unknown":[39],"metals":[41],"using":[42],"structural,":[43],"chemical,":[44],"magnetic,":[45],"and":[46,53,114,126,135,164,170],"stability":[47],"descriptors,":[48],"while":[49],"excluding":[50],"HSE06/GW":[51],"quantities":[52],"electronic":[55,121],"shortcuts.":[56],"Stage~II":[57],"learns":[58],"$E_g^{HSE}":[59],"-":[60],"E_g^{PBE}$":[61],"for":[62,85,94,154,166],"corrected":[64,119],"insulating":[65],"population.":[66],"The":[67,88,118,186],"curated":[68,171],"XGBoost":[69],"regressor":[70],"reconstructs":[71],"HSE06":[72,152],"gaps":[73],"a":[75],"mean":[76],"absolute":[77],"error":[78],"0.108~eV":[80],"($R^2=0.989$),":[81],"compared":[82],"1.036~eV":[84],"raw":[86],"PBE.":[87],"classifier":[90],"is":[91],"used":[92],"only":[93,199],"triage":[95],"because":[96],"labeled":[98],"true-metal":[99,112],"class":[100],"contains":[101],"29":[102,127],"materials;":[103],"its":[104],"best":[105],"holdout":[106],"performance":[107],"gives":[108],"87.5\\%":[109],"accuracy,":[110],"0.286":[111],"recall,":[113],"0.643":[115],"balanced":[116],"accuracy.":[117],"pH~0":[120],"screen":[122],"yields":[123],"10":[124],"strict":[125,134],"initial":[128],"relaxed":[129,137,184],"green-hydrogen":[130],"photocatalyst":[131],"candidates.":[132,185],"Four":[133],"18":[136],"candidates":[138],"would":[139],"fail":[140],"same":[142],"1.6--2.8~eV":[143],"gap":[144,179],"window":[145],"at":[146],"level.":[149],"Targeted":[150],"VASP":[151],"six":[155],"ML-predicted":[156],"compounds":[157],"give":[158],"material-level":[159],"MAEs":[160],"0.417,":[162],"0.182,":[163],"0.110~eV":[165],"C2DB-native,":[168],"Magpie+structural,":[169],"models,":[172],"respectively;":[173],"\\feat{1AgBr-1}":[174],"shifts":[175],"above":[176],"upper":[178],"cutoff,":[180],"leaving":[181],"28":[182],"retained":[183],"workflow":[187],"shows":[188],"that":[189],"high-fidelity":[190],"correction":[191],"must":[192],"be":[193],"evaluated":[194],"candidate":[196],"membership,":[197],"not":[198],"global":[201],"regression":[202],"error.":[203]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-04T00:00:00"}
