{"id":"https://openalex.org/W7225328143","doi":"https://doi.org/10.5281/zenodo.23978208","title":"Beyond Flat Vector Retrieval: Mitigating the Dual Collapse and In-Context Prompt Poisoning of RAG via Structured Valid-Time Cognitive Architectures","display_name":"Beyond Flat Vector Retrieval: Mitigating the Dual Collapse and In-Context Prompt Poisoning of RAG via Structured Valid-Time Cognitive Architectures","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225328143","doi":"https://doi.org/10.5281/zenodo.23978208"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23978208","doi":"https://doi.org/10.5281/zenodo.23978208","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23978208","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.23978208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152524653","display_name":"Siddardha Shayini","orcid":"https://orcid.org/0009-0002-6909-073X","observed_orcids":["https://orcid.org/0009-0002-6909-073X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shayini, Siddardha","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-6909-073X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5152524653"],"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/T10028","display_name":"Topic Modeling","score":0.9487000107765198,"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":0.9487000107765198,"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":0.035100001841783524,"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":0.00279999990016222,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/vector-retrieval","display_name":"vector retrieval","score":0.6129999756813049},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.5619999766349792},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"cognitive architecture","score":0.5849999785423279},{"id":"https://openalex.org/keywords/working-memory","display_name":"working memory","score":0.843999981880188},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.6140000224113464},{"id":"https://openalex.org/keywords/spreading-activation","display_name":"spreading activation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/act-r","display_name":"ACT-R","score":0.9399999976158142},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5929999947547913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783999800682068},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.3785000145435333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C53442348","wikidata":"https://www.wikidata.org/wiki/Q745101","display_name":"Content-addressable memory","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23978208","doi":"https://doi.org/10.5281/zenodo.23978208","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23978208","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.23978209","doi":"https://doi.org/10.5281/zenodo.23978209","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23978209","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.23978208","doi":"https://doi.org/10.5281/zenodo.23978208","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23978208","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166077229","https://openalex.org/W7155372395","https://openalex.org/W7163814543","https://openalex.org/W7221729256","https://openalex.org/W7214577888","https://openalex.org/W7130609696","https://openalex.org/W7202216485","https://openalex.org/W7130599345","https://openalex.org/W7153857565","https://openalex.org/W4416034879"],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"connects":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"to":[8,111],"external":[9],"non-parametric":[10],"memory":[11,171],"through":[12],"dense":[13],"bi-encoder":[14],"indices.":[15],"However,":[16],"it":[17],"relies":[18],"on":[19,136,218,230],"a":[20,157,167,195,219,227],"flawed":[21],"assumption:":[22],"semantic":[23],"proximity":[24],"in":[25,76],"vector":[26],"space":[27],"reliably":[28],"indicates":[29],"factual":[30],"validity":[31],"over":[32],"time.":[33],"We":[34],"identify":[35],"three":[36],"systemic":[37],"failure":[38],"modes":[39],"arising":[40],"from":[41],"this":[42],"assumption.":[43],"Temporal":[44],"Inversion":[45],"occurs":[46,116],"because":[47],"transformer":[48],"bi-encoders":[49],"compress":[50],"token":[51],"representations":[52],"into":[53],"fixed-length":[54],"vectors":[55],"without":[56,143],"encoding":[57],"temporal":[58],"ordering.":[59],"Consequently,":[60],"historical":[61],"and":[62,107,194,203,213],"updated":[63],"assertions":[64],"yield":[65],"near-identical":[66],"cosine":[67,103],"similarities":[68,104],"(\u2206":[69],"sim_cos":[70],"<":[71],"0.012),":[72],"causing":[73],"obsolete":[74,125],"retrievals":[75,119],"41.7%":[77],"of":[78,98,134],"state":[79],"transitions.":[80],"Dual":[81],"Collapse":[82],"emerges":[83],"at":[84],"enterprise":[85],"scale":[86],"(10,000":[87],"passages;":[88],"500":[89],"entities),":[90],"where":[91],"entity":[92],"identifiers":[93],"receive":[94],"less":[95],"than":[96],"5%":[97],"self-attention":[99],"weight,":[100],"driving":[101],"cross-entity":[102],"above":[105],"0.98":[106],"reducing":[108],"top-1":[109],"accuracy":[110],"9.0%.":[112],"InContext":[113],"Prompt":[114],"Poisoning":[115],"when":[117],"stale":[118],"enter":[120],"instruction-tuned":[121],"decoders,":[122],"which":[123],"reproduce":[124],"facts":[126],"despite":[127],"conflicting":[128],"parametric":[129],"priors,":[130],"yielding":[131],"hallucination":[132],"rates":[133],"33.3%\u201340.0%":[135],"public":[137],"entities.":[138],"To":[139],"address":[140],"these":[141],"failures":[142],"model":[144],"retraining,":[145],"we":[146],"introduce":[147],"HERM4AI":[148,205],"(Human-like":[149],"Evolving":[150],"&":[151],"Reasoning":[152],"Memory":[153],"for":[154],"Artificial":[155],"Intelligence),":[156],"model-free":[158],"cognitive":[159],"architecture":[160],"combining":[161],"deterministic":[162],"valid-time":[163],"intervals":[164],"[tfrom,":[165],"tto),":[166],"bounded":[168],"7-slot":[169],"working":[170],"with":[172],"salience":[173],"eviction,":[174],"an":[175],"associative":[176],"knowledge":[177],"graph,":[178],"spreading":[179],"activation,":[180],"sleep-phase":[181],"consolidation,and":[182],"ACT-R":[183],"workflows.":[184],"Across":[185],"seven":[186],"benchmark":[187,199],"suites,":[188],"four":[189],"cloud":[190],"GPU":[191],"experiment":[192],"tracks,":[193],"curated":[196],"12-case":[197],"public-entity":[198,223],"informed":[200],"by":[201],"TempLAMA":[202,231],"FreshQA,":[204],"achieves":[206],"100.0%":[207],"accuracy,":[208],"0.065":[209],"ms":[210],"query":[211],"latency,":[212],"under":[214],"6":[215],"MB":[216],"RAM":[217],"standard":[220],"CPU.":[221],"The":[222],"evaluation":[224,229],"is":[225],"not":[226],"direct":[228],"or":[232],"FreshQA.":[233]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}