{"id":"https://openalex.org/W7225732279","doi":"https://doi.org/10.3390/info17111129","title":"Evidence Fragmentation Is a Distinct Failure Mode in Chunked Retrieval: A Controlled Study Across Three Corpora and Seven Encoders","display_name":"Evidence Fragmentation Is a Distinct Failure Mode in Chunked Retrieval: A Controlled Study Across Three Corpora and Seven Encoders","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225732279","doi":"https://doi.org/10.3390/info17111129"},"language":"en","primary_location":{"id":"doi:10.3390/info17111129","doi":"https://doi.org/10.3390/info17111129","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17111129","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/info17111129","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116116438","display_name":"Saad Aloteibi","orcid":"https://orcid.org/0000-0002-0510-4381","observed_orcids":["https://orcid.org/0000-0002-0510-4381"]},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Saad Aloteibi","raw_affiliation_strings":["Department of Computer Science and Engineering, College of Applied Studies, King Saud University, Riyadh 11437, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, College of Applied Studies, King Saud University, Riyadh 11437, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5116116438"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1930},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1930},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"11","first_page":"1129","last_page":"1129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7250999808311462,"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/T10028","display_name":"Topic Modeling","score":0.7250999808311462,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.2628999948501587,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0013000000035390258,"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":[],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4722999930381775},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3456999957561493},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C41093919","wikidata":"https://www.wikidata.org/wiki/Q2158178","display_name":"Index of dispersion","level":4,"score":0.299699991941452},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C177562468","wikidata":"https://www.wikidata.org/wiki/Q182893","display_name":"Dispersion (optics)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/info17111129","doi":"https://doi.org/10.3390/info17111129","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17111129","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/info17111129","doi":"https://doi.org/10.3390/info17111129","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17111129","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"systems":[3],"divide":[4],"documents":[5],"into":[6],"fixed-size":[7],"chunks":[8],"before":[9],"indexing,":[10],"a":[11,19,29,40,74,85,117,127,169,172,213,238,258,286,348,362],"decision":[12,27,364],"that":[13,25,43,62,89,185,241,252,255,358,366],"the":[14,26,45,51,59,138,149,160,186,194,210,250,273,300,327,339,344,352,367],"literature":[15],"largely":[16],"treats":[17],"as":[18,36],"preprocessing":[20],"convenience.":[21],"This":[22],"study":[23],"shows":[24],"governs":[28],"distinct":[30],"failure":[31],"mode,":[32],"referred":[33],"to":[34,82,297,338],"here":[35],"evidence":[37,72,198,203,282,333],"fragmentation.":[38],"Using":[39],"within-question":[41],"manipulation":[42],"holds":[44,171],"question,":[46],"its":[47,262],"gold":[48],"evidence,":[49,63],"and":[50,105,110,116,126,142,175,226,305,316,347,365],"document\u2019s":[52],"token":[53],"count":[54],"fixed":[55,377],"while":[56],"varying":[57],"only":[58],"arrangement":[60],"of":[61,119,130,137,216,227,278,303],"we":[64],"find":[65],"that,":[66],"in":[67],"this":[68,191],"controlled":[69],"setting,":[70],"dispersing":[71],"across":[73],"document":[75,158],"causally":[76],"reduces":[77],"complete-evidence":[78,293],"retrieval":[79,114,294],"by":[80,281,295,321],"up":[81,296],"0.471,":[83],"against":[84],"measured":[86,214],"noise":[87],"floor":[88],"never":[90],"exceeds":[91],"0.0051.":[92],"The":[93,151,267,355],"effect":[94,211],"is":[95,153,200,242,254,271,307,317,351,361],"established":[96],"on":[97,232,245,313,326],"6200":[98],"questions":[99],"from":[100],"three":[101],"corpora":[102],"spanning":[103],"scientific":[104],"legal":[106],"text":[107],"(QASPER,":[108],"ContractNLI,":[109,306],"CUAD),":[111],"with":[112,164,202,261,285],"two":[113],"families":[115],"panel":[118,139],"seven":[120],"encoders":[121],"covering":[122],"five":[123,235],"pretraining":[124],"lineages":[125],"fifteen-fold":[128],"range":[129],"parameter":[131],"counts;":[132],"all":[133],"252":[134],"non-degenerate":[135],"conditions":[136],"are":[140,335],"significant,":[141],"increasing":[143],"encoder":[144,311],"size":[145,360],"does":[146],"not":[147,318],"reduce":[148],"penalty.":[150],"cause":[152],"passage":[154,207,259],"aggregation":[155],"rather":[156,264,375],"than":[157,265,376],"structure:":[159],"penalty":[161],"grows":[162],"monotonically":[163],"chunk":[165,170,359],"size,":[166],"vanishes":[167],"when":[168],"single":[173],"passage,":[174],"peaks":[176],"at":[177,206,212,299,378],"an":[178],"intermediate":[179],"context":[180],"budget.":[181],"We":[182],"further":[183],"show":[184],"natural":[187],"observational":[188],"design":[189],"for":[190],"question":[192],"yields":[193],"opposite":[195],"conclusion,":[196],"because":[197],"dispersion":[199],"confounded":[201],"quantity.":[204],"Indexing":[205],"granularity":[208],"removes":[209],"cost":[215],"8\u201316\u00d7":[217],"more":[218,322],"index":[219],"entries.":[220],"A":[221],"larger":[222],"residual":[223],"loss":[224],"remains,":[225],"nine":[228],"candidate":[229],"remedies":[230,251],"evaluated":[231],"held-out":[233],"questions,":[234],"fail,":[236],"including":[237],"cross-encoder":[239],"reranker":[240],"significantly":[243],"harmful":[244],"one":[246],"corpus.":[247],"What":[248],"distinguishes":[249],"help":[253],"they":[256],"evaluate":[257],"together":[260],"neighbors":[263],"independently.":[266],"most":[268],"effective":[269],"remedy":[270],"also":[272],"simplest:":[274],"delivering":[275],"contiguous":[276],"spans":[277],"passages":[279,334],"ranked":[280],"per":[283,373],"token,":[284],"mild":[287],"coupling":[288],"between":[289],"neighbors.":[290],"It":[291],"improves":[292],"0.185":[298],"tightest":[301],"budgets":[302],"QASPER":[304],"significant":[308],"under":[309],"every":[310],"tested":[312],"those":[314],"corpora,":[315],"improved":[319],"upon":[320],"elaborate":[323],"schemes":[324],"built":[325],"same":[328],"diagnosis.":[329],"On":[330],"CUAD,":[331],"where":[332],"long":[336],"relative":[337],"budget,":[340],"it":[341],"falls":[342],"below":[343],"flat":[345],"baseline,":[346],"multi-representation":[349],"scheme":[350],"safer":[353],"choice.":[354],"findings":[356],"indicate":[357],"retrieval-behavior":[363],"delivery":[368],"unit":[369],"should":[370],"be":[371],"chosen":[372],"query":[374],"indexing":[379],"time.":[380]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}