{"id":"https://openalex.org/W7225828754","doi":"https://doi.org/10.5281/zenodo.24136569","title":"GeoDetect Revisited: A Leakage-Aware Analysis of Predictive-Entropy Text Classification","display_name":"GeoDetect Revisited: A Leakage-Aware Analysis of Predictive-Entropy Text Classification","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225828754","doi":"https://doi.org/10.5281/zenodo.24136569"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24136569","doi":"https://doi.org/10.5281/zenodo.24136569","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24136569","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","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24136569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160238736","display_name":"Mitra Varun Gogulapati","orcid":"https://orcid.org/0009-0005-5510-9921","observed_orcids":["https://orcid.org/0009-0005-5510-9921"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gogulapati, Mitra Varun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160238736"],"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9976000189781189,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9976000189781189,"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/T11644","display_name":"Spam and Phishing Detection","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7368000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619700014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.375},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28119999170303345},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24136569","doi":"https://doi.org/10.5281/zenodo.24136569","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24136569","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.24136570","doi":"https://doi.org/10.5281/zenodo.24136570","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24136570","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.24136569","doi":"https://doi.org/10.5281/zenodo.24136569","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24136569","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":[],"abstract_inverted_index":{"Distinguishing":[0],"human-authored":[1],"from":[2,42,60,68],"synthetic":[3,152],"text":[4,156],"is":[5,40,123,169],"difficult":[6],"when":[7],"dataset":[8,172],"construction":[9],"introduces":[10],"shortcuts.":[11],"We":[12,53],"revisit":[13],"GeoDetect":[14],"as":[15],"a":[16,61,113,170,174,189],"supervised,":[17],"entropy-only":[18],"pipeline":[19],"and":[20,34,46,93,112,131,154,177,184],"checks":[21],"4,758":[22],"recorded":[23],"passages.":[24,38],"Normalized":[25],"deduplication":[26],"removes":[27],"1,002":[28],"repeated":[29],"rows,":[30],"leaving":[31],"2,404":[32],"human-labeled":[33,44],"1,352":[35],"AI-labeled":[36],"unique":[37],"Punctuation":[39],"absent":[41],"every":[43,49],"passage":[45],"present":[47],"in":[48],"AI-":[50],"labeled":[51],"passage.":[52],"therefore":[54],"distinguish":[55],"an":[56,82,178],"input":[57],"artifact":[58],"condition":[59,63],"primary":[62,102],"with":[64],"punctuation":[65],"removed":[66],"consistently":[67],"both":[69],"classes.":[70],"A":[71],"frozen":[72],"DistilGPT2":[73],"scorer":[74],"produces":[75],"14":[76],"predictive-":[77],"entropy":[78,140],"statistics,":[79],"followed":[80],"by":[81],"XGBoost":[83],"classifier.":[84],"TF-IDF":[85],"similarity":[86],"components":[87],"are":[88],"kept":[89],"intact":[90],"across":[91],"development":[92,121],"holdout":[94,99,136],"partitions.":[95],"On":[96],"888":[97],"group-isolated":[98],"passages,":[100],"the":[101,139],"model":[103],"achieves":[104],"88.06%":[105],"accuracy,":[106,109],"87.09%":[107],"balanced":[108],"0.9877":[110],"AUROC,":[111],"1.86%":[114],"human":[115,155],"false-positive":[116],"rate.":[117],"Pooled":[118],"five-fold":[119],"grouped":[120],"AUROC":[122],"0.9739;":[124],"exact":[125],"word-count":[126],"matching":[127],"yields":[128],"0.9629.":[129],"Length":[130],"surface-style":[132],"controls":[133],"attain":[134],"higher":[135],"accuracy":[137],"than":[138,188],"model.":[141],"These":[142],"results":[143],"characterize":[144],"separation":[145],"within":[146],"differently":[147],"constructed":[148],"corpora,":[149],"including":[150],"templated":[151],"material":[153],"of":[157,181],"unverified":[158],"provenance;":[159],"they":[160],"do":[161],"not":[162],"establish":[163],"general":[164],"AI-authorship":[165],"detection.":[166],"The":[167],"contribution":[168],"reproducible":[171],"analysis,":[173],"dependence-aware":[175],"evaluation,":[176],"explicit":[179],"analysis":[180],"preprocessing,":[182],"threshold,":[183],"source-confounding":[185],"failures,":[186],"rather":[187],"new":[190],"geometric":[191],"detector.":[192]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}