{"id":"https://openalex.org/W7225566565","doi":"https://doi.org/10.5281/zenodo.24050873","title":"Query-Variation Robustness of Sparse, Latent-Semantic and Fused First-Stage Retrieval: A Reproducible Pilot Study on the Vaswani Collection","display_name":"Query-Variation Robustness of Sparse, Latent-Semantic and Fused First-Stage Retrieval: A Reproducible Pilot Study on the Vaswani Collection","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225566565","doi":"https://doi.org/10.5281/zenodo.24050873"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24050873","doi":"https://doi.org/10.5281/zenodo.24050873","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24050873","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.24050873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161290531","display_name":"MOHAMMED GHOUSE AHMED","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"AHMED, MOHAMMED GHOUSE","raw_affiliation_strings":["Independent Researcher, Hyderabad, Telangana, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, Hyderabad, Telangana, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161290531"],"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.00039999998989515007,"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/T11269","display_name":"Algorithms and Data Compression","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spelling-errors","display_name":"spelling errors","score":0.8820000290870667},{"id":"https://openalex.org/keywords/paraphrasing","display_name":"paraphrase","score":0.9279999732971191},{"id":"https://openalex.org/keywords/bm25","display_name":"BM25","score":0.8569999933242798},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"latent semantic analysis","score":0.800000011920929},{"id":"https://openalex.org/keywords/reciprocal-rank-fusion","display_name":"reciprocal rank fusion","score":0.9359999895095825},{"id":"https://openalex.org/keywords/scifact","display_name":"SciFact","score":0.753000020980835},{"id":"https://openalex.org/keywords/biomedical-information-retrieval","display_name":"biomedical information retrieval","score":0.6549999713897705},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.492000013589859}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7545999884605408},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6674000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492999792098999},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24050873","doi":"https://doi.org/10.5281/zenodo.24050873","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24050873","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.24050874","doi":"https://doi.org/10.5281/zenodo.24050874","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24050874","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.24050873","doi":"https://doi.org/10.5281/zenodo.24050873","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24050873","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":["https://openalex.org/W3214779765","https://openalex.org/W4408353980","https://openalex.org/W4385958698","https://openalex.org/W7154267581","https://openalex.org/W7218859019","https://openalex.org/W7100615116","https://openalex.org/W4362686793","https://openalex.org/W7164302541","https://openalex.org/W3015713034","https://openalex.org/W7099528476"],"abstract_inverted_index":{"Query-variation":[0],"robustness":[1],"asks":[2],"whether":[3],"a":[4,45,70],"retrieval":[5,67],"system":[6],"keeps":[7],"working":[8],"when":[9],"the":[10,26,60,81,165],"same":[11],"information":[12],"need":[13],"is":[14,133],"worded":[15],"differently.":[16],"This":[17],"paper":[18],"reports":[19],"an":[20],"empirical":[21],"evaluation":[22,117],"across":[23,184,223],"three":[24,65],"benchmarks:":[25],"classic":[27],"Vaswani/NPL":[28],"collection":[29],"(11,429":[30],"abstracts,":[31],"93":[32],"queries)":[33],"and":[34,41,75,107,164,176,233],"modern":[35],"biomedical":[36],"collections":[37],"from":[38],"BEIR":[39],"(SciFact":[40],"NFCorpus),":[42],"accompanied":[43],"by":[44,102,153,181],"human":[46],"audit":[47,231],"of":[48,85],"200":[49],"stratified":[50],"query":[51,90,229],"rewrites":[52,91,175],"(Cohen's":[53],"kappa":[54],"=":[55,157],"1.000,":[56],"100%":[57],"validity":[58],"on":[59,97,135,139,143,147],"analysis":[61,96],"set).":[62],"We":[63],"compare":[64],"first-stage":[66],"systems:":[68],"BM25,":[69],"non-neural":[71],"latent-semantic-analysis":[72],"(LSA)":[73],"retriever,":[74],"their":[76],"reciprocal-rank-fusion":[77],"(RRF)":[78],"hybrid.":[79],"Using":[80],"four":[82],"meaning-preserving":[83],"categories":[84],"Penha":[86],"et":[87],"al.,":[88],"644":[89],"were":[92,168],"kept":[93],"for":[94,161,193],"primary":[95],"Vaswani.":[98],"Misspellings":[99],"degraded":[100],"nDCG@10":[101,131,152,180],"-18.5%":[103],"(BM25),":[104],"-21.4%":[105],"(LSA),":[106],"-20.2%":[108],"(hybrid);":[109],"all":[110,185],"Holm-adjusted":[111],"p-values":[112],"are":[113,236],"below":[114],"0.001.":[115],"Cross-benchmark":[116],"reveals":[118],"that":[119,215],"typo":[120,129],"vulnerability":[121],"scales":[122],"steeply":[123],"with":[124],"document":[125],"specificity:":[126],"under":[127,182],"identical":[128],"perturbations,":[130],"degradation":[132],"moderate":[134],"technical":[136],"abstracts":[137],"(-2.5%":[138],"SciFact)":[140],"but":[141],"severe":[142],"medical":[144],"terminology":[145],"(-50.4%":[146],"NFCorpus).":[148],"Paraphrasing":[149,197],"reduced":[150],"BM25":[151],"-13.3%":[154],"(Holm":[155],"p":[156],"0.004),":[158],"whereas":[159],"changes":[160],"LSA":[162],"(-5.3%)":[163],"hybrid":[166],"(-7.8%)":[167],"not":[169,219],"statistically":[170],"significant":[171],"after":[172],"correction.":[173],"Natural-question":[174],"stop-word":[177],"removal":[178],"moved":[179],"2%":[183],"systems,":[186],"while":[187],"word-order":[188],"permutations":[189],"produced":[190],"zero":[191],"effect":[192],"these":[194],"bag-of-words":[195],"pipelines.":[196],"altered":[198],"top-10":[199],"result":[200],"order":[201],"more":[202],"than":[203],"misspellings":[204],"did":[205],"(lower":[206],"Rank-Biased":[207],"Overlap)":[208],"yet":[209],"incurred":[210],"lower":[211],"metric":[212],"loss,":[213],"establishing":[214],"ranking":[216],"displacement":[217],"does":[218],"track":[220],"effectiveness":[221],"harm":[222],"variation":[224],"categories.":[225],"Complete":[226],"source":[227],"code,":[228],"variations,":[230],"tools,":[232],"test":[234],"suites":[235],"openly":[237],"available.":[238]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-09T00:00:00"}