{"id":"https://openalex.org/W7224083779","doi":"https://doi.org/10.48550/arxiv.2610.36510","title":"Identity or Evidence? Auditing Evidence Dependence in Agentic Life-Science Benchmarks","display_name":"Identity or Evidence? Auditing Evidence Dependence in Agentic Life-Science Benchmarks","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224083779","doi":"https://doi.org/10.48550/arxiv.2610.36510"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36510","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36510","pdf_url":"https://arxiv.org/pdf/2610.36510","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160053809","display_name":"Danai Brilli","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brilli, Danai","raw_affiliation_strings":["Zo Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zo Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160061998","display_name":"Maria Georgila","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgila, Maria","raw_affiliation_strings":["Zo Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zo Labs","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":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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2581000030040741,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2581000030040741,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.25220000743865967,"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":0.12770000100135803,"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/named-entity-recognition","display_name":"named entity recognition","score":0.460999995470047},{"id":"https://openalex.org/keywords/positive-control","display_name":"positive control","score":0.5820000171661377},{"id":"https://openalex.org/keywords/clinical-outcome-prediction","display_name":"clinical outcome prediction","score":0.47600001096725464},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6610000133514404},{"id":"https://openalex.org/C2771230","wikidata":"https://www.wikidata.org/wiki/Q4926699","display_name":"Blinding","level":3,"score":0.6111999750137329},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.5195000171661377},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5174999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39590001106262207},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26829999685287476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36510","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36510","pdf_url":"https://arxiv.org/pdf/2610.36510","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.2610.36510","doi":"https://doi.org/10.48550/arxiv.2610.36510","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36510","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":"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":"pmh:oai:arXiv.org:2610.36510","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36510","pdf_url":"https://arxiv.org/pdf/2610.36510","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224083779.pdf","grobid_xml":"https://content.openalex.org/works/W7224083779.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220674086","https://openalex.org/W7160897323","https://openalex.org/W7223041991","https://openalex.org/W7151964127","https://openalex.org/W7211874068","https://openalex.org/W7171505992","https://openalex.org/W7164773583","https://openalex.org/W7169858658","https://openalex.org/W7161178917","https://openalex.org/W6979227780"],"abstract_inverted_index":{"Agentic":[0],"life-science":[1],"benchmarks":[2,134],"give":[3],"an":[4,13],"agent":[5],"evidence":[6,24,44],"about":[7],"a":[8,16,47,62,65,72,80,117,126],"named":[9,86],"entity":[10],"and":[11,43,50,55,82,124,146],"score":[12,20],"answer":[14],"against":[15],"recorded":[17],"outcome.":[18],"That":[19],"tests":[21],"reasoning":[22,139],"over":[23],"only":[25],"if":[26],"the":[27,31,34,76,97,114],"evidence,":[28],"rather":[29],"than":[30],"name,":[32],"determines":[33],"answer.":[35],"We":[36],"examine":[37],"this":[38],"distinction":[39],"by":[40],"varying":[41],"identity":[42,58],"independently":[45],"on":[46],"clinical-outcome":[48],"benchmark":[49],"published":[51],"tasks":[52],"from":[53],"Biomni":[54],"LAB-Bench.":[56],"Blinding":[57],"matters":[59,71],"little":[60],"when":[61,75],"prompt":[63,77],"contains":[64],"decisive":[66],"sequence":[67],"or":[68],"passage.":[69],"It":[70],"great":[73],"deal":[74],"is":[78],"mostly":[79],"name":[81],"candidate":[83],"list":[84],"(0.742":[85],"versus":[87],"0.082":[88],"blinded;":[89],"chance":[90],"0.093).":[91],"Across":[92],"96":[93],"LAB-Bench":[94],"LitQA2":[95],"questions,":[96],"gap":[98],"increases":[99],"under":[100],"one":[101],"fixed":[102],"passage-redaction":[103],"scheme":[104],"(+0.000":[105],"to":[106,136],"+0.135;":[107],"per-instance":[108],"slope":[109],"+0.147,":[110],"p=":[111],"0.004).":[112],"On":[113],"clinical":[115],"benchmark,":[116],"no-evidence":[118],"recall":[119],"probe":[120],"matches":[121],"prediction":[122],"accuracy":[123],"recovers":[125],"database-specific":[127],"programme":[128],"count.":[129],"So,":[130],"we":[131],"argue":[132],"that":[133],"intended":[135],"measure":[137],"evidence-dependent":[138],"should":[140],"report":[141],"identity-blinded":[142],"results,":[143],"retrieval":[144],"telemetry,":[145],"positive":[147],"controls.":[148]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-29T00:00:00"}