{"id":"https://openalex.org/W7225348463","doi":"https://doi.org/10.20944/preprints202611.0528.v1","title":"Auditable Evaluation Protocol for Spam Detection Under Bounded Paraphrase Attacks","display_name":"Auditable Evaluation Protocol for Spam Detection Under Bounded Paraphrase Attacks","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225348463","doi":"https://doi.org/10.20944/preprints202611.0528.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0528.v1","doi":"https://doi.org/10.20944/preprints202611.0528.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0528.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0528.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160871376","display_name":"Xin Ge","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xin Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160874668","display_name":"Minnan Yue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minnan Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159470036","display_name":"Sizheng Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sizheng Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160915747","display_name":"Shanshan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160771226","display_name":"Dan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054131406","display_name":"Ye Xu","orcid":"https://orcid.org/0000-0002-8714-8715","observed_orcids":["https://orcid.org/0000-0002-8714-8715"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160871376"],"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/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":9.999999747378752e-05,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0,"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/spam-detection","display_name":"spam detection","score":0.9649999737739563},{"id":"https://openalex.org/keywords/tf-idf-features","display_name":"TF-IDF features","score":0.7269999980926514},{"id":"https://openalex.org/keywords/structural-cues","display_name":"structural cues","score":0.7710000276565552},{"id":"https://openalex.org/keywords/human-adjudication","display_name":"human adjudication","score":0.6679999828338623},{"id":"https://openalex.org/keywords/false-negative-rate","display_name":"false negative rate","score":0.7440000176429749},{"id":"https://openalex.org/keywords/enron-corpus","display_name":"Enron corpus","score":0.8180000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741100013256073},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6597999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227000117301941},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.46619999408721924},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0528.v1","doi":"https://doi.org/10.20944/preprints202611.0528.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0528.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0528.v1","doi":"https://doi.org/10.20944/preprints202611.0528.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0528.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213773525","https://openalex.org/W2058737869","https://openalex.org/W2035488614","https://openalex.org/W2149604555","https://openalex.org/W7099064987","https://openalex.org/W7154726837","https://openalex.org/W3157938077","https://openalex.org/W3003926702","https://openalex.org/W1604555660","https://openalex.org/W203990329"],"abstract_inverted_index":{"Spam-filter":[0],"scores":[1],"are":[2,14,164],"difficult":[3],"to":[4,103,166],"interpret":[5],"when":[6],"split":[7],"construction,":[8],"attack":[9],"denominators,":[10],"and":[11,25,33,45,56,80,134,139,147,150,158],"candidate":[12],"validity":[13],"not":[15],"retained.":[16],"We":[17],"evaluate":[18],"an":[19,34,129],"auditable":[20],"RMF-PC":[21,72],"protocol":[22,39],"using":[23],"word":[24],"character":[26],"TF-IDF":[27],"views,":[28],"structural":[29],"cues,":[30],"calibrated":[31],"fusion,":[32],"optional":[35],"paraphrase-consistency":[36],"gate.":[37],"The":[38],"freezes":[40],"data,":[41],"fitting,":[42],"attacks,":[43],"predictions,":[44],"review":[46],"decisions;":[47],"separates":[48],"deterministic":[49],"L1":[50,77,81],"rewrites":[51],"from":[52,62,89],"human-adjudicated":[53],"L2/L3":[54],"candidates;":[55,142],"keeps":[57],"exact-deduplicated":[58],"Track":[59,64,67,110],"A":[60,68],"distinct":[61],"group-near-deduplicated":[63],"B.":[65],"On":[66,109],"(seed":[69],"42),":[70],"gated":[71],"achieved":[73],"clean":[74],"F1":[75,78],"97.937%,":[76],"98.117%,":[79],"spam":[82],"FNR":[83,87],"1.971%":[84],"(11/558).":[85],"Its":[86],"difference":[88],"linear":[90],"SVM":[91],"was":[92],"-0.538":[93],"percentage":[94],"points":[95],"(exact":[96],"McNemar":[97],"p=0.5078;":[98],"paired-bootstrap":[99],"95%":[100],"interval":[101],"-1.613":[102],"+0.538),":[104],"so":[105],"superiority":[106],"is":[107],"unresolved.":[108],"B,":[111],"the":[112,167],"same":[113],"comparison":[114],"had":[115],"a":[116,120],"raw":[117],"p=0.0215":[118],"but":[119],"Holm-adjusted":[121],"p=0.0859,":[122],"showing":[123],"that":[124],"cohort":[125],"policy":[126],"can":[127],"affect":[128],"inferential":[130],"conclusion.":[131],"Two":[132],"reviewers":[133],"adjudication":[135],"retained":[136,168],"38":[137],"L2":[138],"55":[140],"L3":[141],"observed":[143],"misses":[144],"were":[145],"1/38":[146],"0/55.":[148],"Enron":[149],"third-party":[151],"Zenodo-curated":[152],"TREC":[153],"tracks":[154],"show":[155],"corpus":[156],"sensitivity":[157],"fixed":[159],"5%/10%":[160],"adaptation":[161],"results.":[162],"Findings":[163],"limited":[165],"local":[169],"protocols.":[170]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}