{"id":"https://openalex.org/W7215103402","doi":"https://doi.org/10.1371/journal.pone.0353137","title":"A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking","display_name":"A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215103402","doi":"https://doi.org/10.1371/journal.pone.0353137","pmid":"https://pubmed.ncbi.nlm.nih.gov/42821622","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13630321"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pone.0353137","doi":"https://doi.org/10.1371/journal.pone.0353137","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0353137","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0353137&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0353137&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100634392","display_name":"Xiaojing Fan","orcid":"https://orcid.org/0009-0008-2620-2117","observed_orcids":["https://orcid.org/0009-0008-2620-2117","https://orcid.org/0000-0001-6299-0570"]},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojing Fan","raw_affiliation_strings":["University of Shanghai for Science and Technology"],"raw_orcid":"https://orcid.org/0009-0008-2620-2117","affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology","institution_ids":["https://openalex.org/I148128674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100634392"],"corresponding_institution_ids":["https://openalex.org/I148128674"],"apc_list":{"value":2382,"currency":"USD","value_usd":2382},"apc_paid":{"value":2382,"currency":"USD","value_usd":2382},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68571535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"10","first_page":"e0353137","last_page":"e0353137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11257","display_name":"Taxation and Compliance Studies","score":0.5062999725341797,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11257","display_name":"Taxation and Compliance Studies","score":0.5062999725341797,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11508","display_name":"Corporate Taxation and Avoidance","score":0.33500000834465027,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.026000000536441803,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/accounting-identities","display_name":"accounting identities","score":0.5709999799728394},{"id":"https://openalex.org/keywords/tax-evasion","display_name":"tax evasion","score":0.5130000114440918},{"id":"https://openalex.org/keywords/ctgan","display_name":"CTGAN","score":0.675000011920929},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.7260000109672546},{"id":"https://openalex.org/keywords/transfer-pricing","display_name":"transfer pricing","score":0.8759999871253967},{"id":"https://openalex.org/keywords/tax-burden","display_name":"tax burden","score":0.5920000076293945},{"id":"https://openalex.org/keywords/profit-margin","display_name":"profit margin","score":0.6629999876022339},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5910000205039978},{"id":"https://openalex.org/keywords/constraint-validation","display_name":"constraint validation","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8228999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570000052452087},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C203223496","wikidata":"https://www.wikidata.org/wiki/Q4681344","display_name":"Additive model","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2777780509","wikidata":"https://www.wikidata.org/wiki/Q1377422","display_name":"Profit maximization","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.2583000063896179}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013660","descriptor_name":"Taxes","qualifier_ui":"Q000191","qualifier_name":"economics","is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pone.0353137","doi":"https://doi.org/10.1371/journal.pone.0353137","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0353137","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0353137&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13630321","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13630321/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13630321/pdf/pone.0353137.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS One","raw_type":"Text"},{"id":"pmid:42821622","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42821622","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":"PloS one","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:7c2f5e3aff2b400d90b90e423481ded7","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/7c2f5e3aff2b400d90b90e423481ded7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS ONE, Vol 21, Iss 10, p e0353137 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pone.0353137","doi":"https://doi.org/10.1371/journal.pone.0353137","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0353137","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0353137&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215103402.pdf","grobid_xml":"https://content.openalex.org/works/W7215103402.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W265896103","https://openalex.org/W2085766370","https://openalex.org/W2088663850","https://openalex.org/W2107274838","https://openalex.org/W2122646361","https://openalex.org/W2134246329","https://openalex.org/W2296719434","https://openalex.org/W2913997948","https://openalex.org/W3172701880","https://openalex.org/W3200676775","https://openalex.org/W3202428668","https://openalex.org/W4206823904","https://openalex.org/W4323263363","https://openalex.org/W4401035214","https://openalex.org/W4402741890","https://openalex.org/W7117232754","https://openalex.org/W7133186244"],"related_works":["https://openalex.org/W4289948362","https://openalex.org/W4295837861","https://openalex.org/W2955428767","https://openalex.org/W4377007281","https://openalex.org/W3091367221","https://openalex.org/W4401035214","https://openalex.org/W7018905789","https://openalex.org/W4416572724","https://openalex.org/W4414793355","https://openalex.org/W4366398774"],"abstract_inverted_index":{"Synthetic":[0],"benchmarks":[1],"can":[2,15,260],"support":[3],"tax-risk":[4],"method":[5],"development":[6],"when":[7],"administrative":[8,60],"records":[9],"are":[10,226,232,253,265],"inaccessible,":[11],"but":[12,155,217],"a":[13,33,44,78,138,164,233,236,269],"simulator":[14,35],"also":[16],"predetermine":[17],"the":[18,27,69,128,134,160,186,199,229,247],"patterns":[19],"later":[20],"reported":[21],"as":[22],"detection":[23],"findings.":[24],"We":[25],"present":[26],"Tax":[28],"Data":[29],"Generation":[30],"Model":[31],"(TDGM),":[32],"mechanism-guided":[34,241],"that":[36],"enforces":[37],"specified":[38],"income-statement":[39],"and":[40,50,75,99,131,176,182,243],"balance-sheet":[41],"identities,":[42,148],"generates":[43],"three-year":[45],"panel":[46],"for":[47,111,119,123,127,133,240],"10,000":[48],"firms,":[49],"injects":[51],"four":[52],"prespecified":[53],"risk":[54],"strategies.":[55],"This":[56],"study":[57],"uses":[58],"no":[59,93],"audit":[61,238,281],"data;":[62],"its":[63,72],"purpose":[64],"is":[65],"to":[66,76,195,201,208,220],"test":[67,100],"whether":[68],"implementation":[70],"reproduces":[71],"design":[73],"assumptions":[74],"provide":[77],"reproducible":[79],"benchmark.":[80],"All":[81],"predictive":[82],"evaluations":[83],"used":[84],"five":[85],"repeated":[86],"70/30":[87],"group":[88],"splits":[89],"by":[90],"firm,":[91],"so":[92],"firm":[94],"appeared":[95],"in":[96],"both":[97,145],"training":[98],"data.":[101],"Observed":[102],"marginal":[103],"effects":[104],"were":[105],"heterogeneous":[106],"rather":[107],"than":[108],"uniformly":[109],"small:":[110],"all":[112],"risky":[113],"observations,":[114],"Cohen's":[115],"d":[116],"was":[117],"-1.29":[118],"profit":[120],"margin,":[121],"-1.20":[122],"tax":[124],"burden,":[125],"1.05":[126],"transfer-pricing":[129],"indicator,":[130],"0.15":[132],"income-gap":[135,187],"ratio.":[136],"In":[137],"controlled":[139],"cross-sectional":[140],"comparison,":[141],"raw":[142,202],"CTGAN":[143],"failed":[144],"row-level":[146],"accounting":[147],"whereas":[149],"deterministic":[150],"projection":[151],"restored":[152],"100%":[153],"validity":[154],"worsened":[156],"dependence":[157],"fidelity.":[158],"Under":[159],"revised":[161],"classifier":[162],"specification,":[163],"one-hidden-layer":[165],"neural":[166],"network":[167],"with":[168],"conventional":[169],"L2":[170],"regularization":[171],"achieved":[172,180],"mean":[173],"ROC-AUC":[174,191,214],"0.9942":[175],"PR-AUC":[177,218],"0.9710;":[178],"XGBoost":[179,190,213],"0.9714":[181,194],"0.8975,":[183],"respectively.":[184],"Removing":[185],"ratio":[188],"changed":[189,254],"only":[192],"from":[193],"0.9702,":[196],"while":[197],"restricting":[198],"model":[200],"Level":[203],"1":[204],"variables":[205],"reduced":[206],"it":[207],"0.8941.":[209],"At":[210],"1%":[211],"prevalence,":[212],"remained":[215],"0.9720":[216],"fell":[219],"0.6703,":[221],"showing":[222],"why":[223],"prevalence-sensitive":[224],"metrics":[225],"required.":[227],"Together,":[228],"three":[230],"contributions":[231],"constraint-by-construction":[234],"simulator,":[235],"reusable":[237],"protocol":[239],"generators,":[242],"explicit":[244],"measurement":[245],"of":[246,268,275],"accounting-repair/statistical-fidelity":[248],"trade-off.":[249],"Because":[250],"selected":[251],"flows":[252],"after":[255],"stock":[256],"generation,":[257],"derived":[258],"ratios":[259],"carry":[261],"design-induced":[262],"information.":[263],"These":[264],"internal":[266],"properties":[267],"synthetic":[270],"data-generating":[271],"process,":[272],"not":[273],"estimates":[274],"real":[276],"tax-evasion":[277],"behavior":[278],"or":[279],"deployable":[280],"performance.":[282]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-02T00:00:00"}