{"id":"https://openalex.org/W7212433652","doi":"https://doi.org/10.5281/zenodo.22298900","title":"The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts \u2014 code, per-query runs, summary results, and supplementary material (v2.2, IEEE Access resubmission)","display_name":"The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts \u2014 code, per-query runs, summary results, and supplementary material (v2.2, IEEE Access resubmission)","publication_year":2026,"publication_date":"2026-09-13","ids":{"openalex":"https://openalex.org/W7212433652","doi":"https://doi.org/10.5281/zenodo.22298900"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22298900","doi":"https://doi.org/10.5281/zenodo.22298900","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22298900","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":"Software"},"volume":null,"type":"software","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22298900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137628534","display_name":"Aaditya Chauhan","orcid":"https://orcid.org/0009-0000-8652-0071","observed_orcids":["https://orcid.org/0009-0000-8652-0071"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chauhan, Aaditya","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0000-8652-0071","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135933337","display_name":"Arun Agarwal","orcid":"https://orcid.org/0009-0005-3065-9804","observed_orcids":["https://orcid.org/0009-0005-3065-9804"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Arun","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0005-3065-9804","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.9951000213623047,"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":0.9951000213623047,"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":0.00279999990016222,"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/T10203","display_name":"Recommender Systems and Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/hybrid-search","display_name":"hybrid retrieval","score":0.9380000233650208},{"id":"https://openalex.org/keywords/bm25","display_name":"BM25","score":0.7179999947547913},{"id":"https://openalex.org/keywords/dense-retrievers","display_name":"dense retrievers","score":0.7620000243186951},{"id":"https://openalex.org/keywords/cross-encoder-reranking","display_name":"cross-encoder reranking","score":0.8349999785423279},{"id":"https://openalex.org/keywords/beir-benchmark","display_name":"BEIR benchmark","score":0.5540000200271606},{"id":"https://openalex.org/keywords/feature-importance","display_name":"feature importance","score":0.4519999921321869},{"id":"https://openalex.org/keywords/retrieval-efficiency","display_name":"retrieval efficiency","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286999821662903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5703999996185303},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22298900","doi":"https://doi.org/10.5281/zenodo.22298900","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22298900","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":"Software"},{"id":"doi:10.5281/zenodo.22298901","doi":"https://doi.org/10.5281/zenodo.22298901","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22298901","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":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22298900","doi":"https://doi.org/10.5281/zenodo.22298900","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22298900","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":"Software"},"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/W7222218218","https://openalex.org/W7172118215","https://openalex.org/W7219129507","https://openalex.org/W7161199132","https://openalex.org/W7214012637","https://openalex.org/W7172388931","https://openalex.org/W2242887097","https://openalex.org/W7223251273","https://openalex.org/W7172439268","https://openalex.org/W1540841176"],"abstract_inverted_index":{"Code,":[0],"pinned":[1],"environment,":[2],"per-query":[3,66,114],"retrieval":[4],"runs,":[5],"summary":[6,100],"result":[7],"files,":[8],"tables,":[9],"figures,":[10],"and":[11,50,63,81,87,92,102,133,144,149,209,212],"supplementary":[12],"material":[13],"for":[14],"\"The":[15],"Fusion":[16],"Tax:":[17],"A":[18],"Diagnostic":[19],"Analysis":[20],"of":[21,117,199],"When":[22],"Hybrid":[23],"Retrieval":[24],"Hurts\"":[25],"(submitted":[26],"to":[27,98],"IEEE":[28],"Access,":[29],"manuscript":[30],"Access-2026-34033,":[31],"revised":[32],"version).":[33],"The":[34,109],"pipeline":[35,194],"runs":[36,110,116,215],"Anserini/Pyserini":[37],"BM25":[38],"(official":[39],"prebuilt":[40],"BEIR":[41,61,147,189],"indexes),":[42],"five":[43],"dense":[44],"encoders":[45],"(MiniLM,":[46],"BGE-small/base/large,":[47],"Qwen3-Embedding-0.6B),":[48],"SPLADE,":[49],"three":[51],"fusion":[52,67],"functions":[53],"(RRF,":[54],"normalized":[55],"score":[56],"interpolation,":[57],"CombMNZ)":[58],"on":[59,120,135],"seven":[60],"datasets,":[62],"computes":[64],"the":[65,95,103,113,146,150,160,174,188,193,200,205,214],"tax,":[68],"held-out":[69],"fusion-weight":[70],"selection,":[71],"symmetric":[72],"harm/benefit":[73],"accounting":[74],"by":[75],"diagnostic":[76],"quadrant,":[77],"risk-sensitive":[78],"tests,":[79],"predictability":[80],"feature-importance":[82],"analyses,":[83],"cross-encoder":[84],"reranking":[85,175],"recovery,":[86],"efficiency":[88],"measurements.":[89],"Every":[90],"table":[91,132],"figure":[93,134],"in":[94,159,168,192],"article":[96],"traces":[97],"a":[99,136,156],"JSON":[101],"script":[104,127],"that":[105],"produced":[106],"it":[107],"(REPRODUCE.md).":[108],"archive":[111],"holds":[112],"top-100":[115],"every":[118,121,129,166],"retriever":[119],"corpus,":[122],"from":[123],"which":[124],"one":[125,169],"driver":[126],"regenerates":[128],"first-stage":[130],"summary,":[131],"CPU.":[137],"Not":[138],"included,":[139],"because":[140],"they":[141],"are":[142],"large":[143],"regenerable:":[145],"corpora":[148],"document":[151,208],"embeddings.":[152],"Version":[153],"2.2":[154],"fixes":[155],"non-deterministic":[157],"tie-break":[158],"stored":[161],"fused":[162],"ranks":[163],"(v2.0),":[164],"stores":[165],"run":[167,198],"canonical":[170],"rank":[171],"order,":[172],"reruns":[173],"experiment":[176],"with":[177],"deterministic":[178],"candidates,":[179],"pins":[180],"model":[181],"checkpoint":[182],"revisions,":[183],"fingerprints":[184],"cached":[185],"results,":[186],"enforces":[187],"self-match":[190],"protocol":[191],"(a":[195],"Qwen3-Embedding":[196],"ArguAna":[197],"earlier":[201],"deposits":[202],"had":[203],"retained":[204],"query's":[206],"own":[207],"was":[210],"repaired),":[211],"adds":[213],"archive.":[216]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2026-09-14T00:00:00"}