{"id":"https://openalex.org/W7215075673","doi":"https://doi.org/10.5281/zenodo.22980059","title":"What the Score Measured: Failure Attribution in an Agent Memory Evaluation","display_name":"What the Score Measured: Failure Attribution in an Agent Memory Evaluation","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215075673","doi":"https://doi.org/10.5281/zenodo.22980059"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22980059","doi":"https://doi.org/10.5281/zenodo.22980059","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980059","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.22980059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133589613","display_name":"Dino Vitale","orcid":"https://orcid.org/0009-0001-5590-3296","observed_orcids":["https://orcid.org/0009-0001-5590-3296"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitale, Dino","raw_affiliation_strings":["Boundary Labs"],"raw_orcid":"https://orcid.org/0009-0001-5590-3296","affiliations":[{"raw_affiliation_string":"Boundary Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153815935","display_name":"Baixin Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Baixin","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"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":0.3953000009059906,"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":0.3953000009059906,"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":0.1680999994277954,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.1348000019788742,"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/reader-model","display_name":"reader model","score":0.6830000281333923},{"id":"https://openalex.org/keywords/retrieval-failure","display_name":"retrieval failure","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7243000268936157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799999833106995},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5267999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47749999165534973},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.424699991941452},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C2775858120","wikidata":"https://www.wikidata.org/wiki/Q3333604","display_name":"Memoria","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2779407169","wikidata":"https://www.wikidata.org/wiki/Q3072083","display_name":"Memory disorder","level":5,"score":0.2777000069618225},{"id":"https://openalex.org/C2778615406","wikidata":"https://www.wikidata.org/wiki/Q11072","display_name":"Amnesia","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22980059","doi":"https://doi.org/10.5281/zenodo.22980059","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980059","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.22980060","doi":"https://doi.org/10.5281/zenodo.22980060","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980060","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.22980059","doi":"https://doi.org/10.5281/zenodo.22980059","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980059","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/W7221511638","https://openalex.org/W7222527758","https://openalex.org/W7222943210","https://openalex.org/W7202048664","https://openalex.org/W7167031124","https://openalex.org/W7167037551","https://openalex.org/W7166700049","https://openalex.org/W7211996894","https://openalex.org/W7163039299","https://openalex.org/W7164511300"],"abstract_inverted_index":{"A":[0],"memory":[1,49,145],"benchmark":[2,73],"run":[3],"against":[4],"a":[5,44,48,52,102,121,132],"deployed":[6],"AI":[7],"agent":[8,144],"with":[9],"three":[10,90,118],"reader":[11,24,53,107],"models":[12],"returned":[13],"36%,":[14,93],"40%":[15,109],"and":[16,86,95,101,140],"40%,":[17],"which":[18],"read":[19],"as":[20],"evidence":[21],"that":[22,38],"the":[23,34,39,61,68,72,83,88,98,115],"model":[25],"barely":[26],"matters":[27],"for":[28,79],"recall.":[29],"An":[30],"external":[31],"audit":[32],"of":[33,60],"public":[35],"artifacts":[36],"established":[37],"evaluation":[40,146],"could":[41],"not":[42],"distinguish":[43],"retrieval":[45,63,125],"failure":[46,50],"from":[47,51,56,108],"failure.":[54],"Reconstruction":[55],"source":[57],"showed":[58],"both":[59],"agent's":[62],"paths":[64],"were":[65],"inert":[66],"under":[67],"tested":[69],"condition,":[70],"so":[71],"had":[74],"been":[75],"measuring":[76],"context-window":[77],"membership":[78],"every":[80],"reader.":[81],"With":[82],"harness":[84],"repaired":[85],"instrumented,":[87],"same":[89,99],"readers":[91],"score":[92],"48%":[94],"76%":[96],"on":[97],"questions,":[100],"single-variable":[103],"comparison":[104],"moves":[105],"one":[106],"to":[110],"76%.":[111],"The":[112],"paper":[113],"decomposes":[114],"outcome":[116],"into":[117,129],"gates,":[119],"documents":[120],"case":[122],"where":[123],"working":[124],"converted":[126],"honest":[127],"abstentions":[128],"fabrications,":[130],"reports":[131],"four-rater":[133],"blind":[134],"judging":[135],"protocol":[136],"over":[137],"150":[138],"predictions,":[139],"specifies":[141],"what":[142],"an":[143],"must":[147],"log.":[148]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-02T00:00:00"}