{"id":"https://openalex.org/W7203712781","doi":"https://doi.org/10.48550/arxiv.2608.16043","title":"Coverage Is Not Redundancy: Maintenance Cost and Exposure of Query-Aware Admission Indexes in Vector Databases Under Workload Drift","display_name":"Coverage Is Not Redundancy: Maintenance Cost and Exposure of Query-Aware Admission Indexes in Vector Databases Under Workload Drift","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203712781","doi":"https://doi.org/10.48550/arxiv.2608.16043"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16043","pdf_url":"https://arxiv.org/pdf/2608.16043","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/2608.16043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097127390","display_name":"Prashant Kumar Pathak","orcid":"https://orcid.org/0009-0008-8744-9025","observed_orcids":["https://orcid.org/0009-0008-8744-9025"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pathak, Prashant Kumar","raw_affiliation_strings":["Independent Researcher Milpitas , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher Milpitas , CA , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5097127390"],"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.3716000020503998,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.3716000020503998,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.10909999907016754,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07240000367164612,"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":[{"id":"https://openalex.org/keywords/vector-databases","display_name":"vector databases","score":0.7739999890327454},{"id":"https://openalex.org/keywords/hnsw","display_name":"HNSW","score":0.703000009059906},{"id":"https://openalex.org/keywords/pgvector","display_name":"pgvector","score":0.6480000019073486},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7980999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578999757766724},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C2776900844","wikidata":"https://www.wikidata.org/wiki/Q8028383","display_name":"Witness","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2988987868","wikidata":"https://www.wikidata.org/wiki/Q32635","display_name":"Domain name","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2781011336","wikidata":"https://www.wikidata.org/wiki/Q1465133","display_name":"Time limit","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.16043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16043","pdf_url":"https://arxiv.org/pdf/2608.16043","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.2608.16043","doi":"https://doi.org/10.48550/arxiv.2608.16043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16043","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:2608.16043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16043","pdf_url":"https://arxiv.org/pdf/2608.16043","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203712781.pdf","grobid_xml":"https://content.openalex.org/works/W7203712781.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2888975495","https://openalex.org/W3160873191","https://openalex.org/W4382404262","https://openalex.org/W4391801218","https://openalex.org/W4404350843","https://openalex.org/W4405627071","https://openalex.org/W4413144844"],"related_works":["https://openalex.org/W7204620401","https://openalex.org/W7165621893","https://openalex.org/W4416072428","https://openalex.org/W7216215270","https://openalex.org/W4404350843","https://openalex.org/W7165379798","https://openalex.org/W7160928454","https://openalex.org/W7223560955","https://openalex.org/W7163174587","https://openalex.org/W7160150469"],"abstract_inverted_index":{"In":[0],"a":[1,7,24,51,58,69,79,102,110,116,124,165,199,206,232,241,267],"vector":[2],"database":[3],"serving":[4],"production-scale":[5],"retrieval,":[6],"single":[8],"inserted":[9],"document":[10,59],"can":[11,146],"be":[12,85],"retrieved":[13],"for":[14,33],"an":[15,34,46,135,156],"anomalously":[16],"large":[17],"share":[18],"of":[19,53,213],"the":[20,30,91,97,121,182,190,214,219,227,238,246,256,272],"query":[21],"workload":[22,73,224],"--":[23,27,105,187,197],"retrieval":[25,276],"hub":[26,125,257],"and":[28,56,88,152,173,178,236,266],"dominate":[29],"evidence":[31],"returned":[32],"entire":[35],"topic.":[36],"An":[37],"emerging":[38,250],"defense":[39],"guards":[40],"against":[41,65],"this":[42,75,161],"at":[43,194,205,231],"ingest":[44,98,234],"with":[45],"admission":[47,209],"check:":[48],"it":[49],"maintains":[50],"set":[52,77],"sentinel":[54,76,247],"queries":[55],"admits":[57],"only":[60,126,164],"if":[61],"its":[62],"reverse-kNN":[63],"count":[64,253],"them":[66],"stays":[67],"below":[68,179],"threshold":[70],"tau.":[71],"Under":[72],"drift":[74],"is":[78,107,118,163],"query-aware":[80],"auxiliary":[81],"index":[82,169],"that":[83,93,138,244],"must":[84],"maintained":[86],"online,":[87],"we":[89],"study":[90],"cost":[92],"maintenance":[94],"imposes":[95],"on":[96,189],"path.":[99],"We":[100,217],"identify":[101],"structural":[103],"limit":[104],"coverage":[106],"not":[108],"redundancy:":[109],"monitor":[111],"stops":[112,184],"promoting":[113],"sentinels":[114,129],"once":[115,127],"region":[117],"covered,":[119],"but":[120],"predicate":[122],"rejects":[123],"tau":[128],"witness":[130,201],"it,":[131,177],"so":[132],"exposure":[133,172],"has":[134],"observation-limited":[136],"floor":[137,162],"no":[139],"reduction":[140],"in":[141,229],"update":[142],"or":[143],"enforcement":[144],"latency":[145],"close.":[147],"On":[148],"real":[149,222],"HNSW,":[150],"IVF-Flat,":[151],"IVF-PQ":[153,192],"indexes":[154],"over":[155],"8.8M-vector":[157],"MS":[158],"MARCO":[159],"corpus":[160],"best":[166],"case:":[167],"as":[168],"recall":[170,180],"falls,":[171],"churn":[174],"rise":[175],"above":[176],"~0.5":[181],"gate":[183,228],"containing":[185],"altogether":[186],"worst":[188],"memory-compressed":[191],"used":[193],"billion":[195],"scale":[196],"while":[198],"recall-aware":[200],"probe":[202],"restores":[203],"containment":[204],"fixed":[207],"O(|S|d)":[208],"cost,":[210],"under":[211,221],"0.1%":[212],"ANN":[215],"insert.":[216],"validate":[218],"law":[220],"(COVID-19)":[223],"drift,":[225],"implement":[226],"PostgreSQL/pgvector":[230],"0.33%":[233],"tax,":[235],"turn":[237],"bound":[239],"into":[240],"provisioning":[242],"rule":[243],"sizes":[245],"budget":[248],"per":[249],"region.":[251],"A":[252],"test":[254],"contains":[255],"where":[258],"retrieval-time":[259],"score":[260],"normalizers":[261],"(NNN,":[262],"QB-Norm)":[263],"do":[264],"not,":[265],"pre-registered":[268],"causal":[269],"suite":[270],"isolates":[271],"missing-coverage":[273],"mechanism":[274],"from":[275],"fragmentation":[277],"across":[278],"two":[279],"embedding":[280],"families":[281],"(BGE-1024,":[282],"E5-768).":[283]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}