{"id":"https://openalex.org/W7170089005","doi":"https://doi.org/10.48550/arxiv.2607.18777","title":"PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects","display_name":"PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects","publication_year":2026,"publication_date":"2026-07-21","ids":{"openalex":"https://openalex.org/W7170089005","doi":"https://doi.org/10.48550/arxiv.2607.18777","pmid":"https://pubmed.ncbi.nlm.nih.gov/42539156","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13419637"},"language":"en","primary_location":{"id":"pmid:42539156","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42539156","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.18777","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143414860","display_name":"Dongkwan Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Dongkwan","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130690827","display_name":"Yiming Gao","orcid":"https://orcid.org/0009-0003-7436-9070","observed_orcids":["https://orcid.org/0009-0003-7436-9070"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gao, Yiming","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109641625","display_name":"Yining Yang","orcid":"https://orcid.org/0009-0003-1231-0997","observed_orcids":["https://orcid.org/0009-0003-1231-0997","https://orcid.org/0009-0000-2419-6106"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Yining","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100716873","display_name":"Yang Shen","orcid":"https://orcid.org/0000-0002-1703-7796","observed_orcids":["https://orcid.org/0000-0002-1703-7796","https://orcid.org/0000-0003-4728-1973"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.3698999881744385,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.3698999881744385,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.11050000041723251,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.10599999874830246,"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/mechanistic-reasoning","display_name":"mechanistic reasoning","score":0.8309999704360962},{"id":"https://openalex.org/keywords/perturbation-effects","display_name":"perturbation effects","score":0.7139999866485596},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.32499998807907104},{"id":"https://openalex.org/keywords/chemical-perturbation","display_name":"chemical perturbation","score":0.9480000138282776},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.9589999914169312},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7070000171661377},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.6430000066757202},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9269999861717224}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620199978351593},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26660001277923584}],"mesh":[],"locations_count":4,"locations":[{"id":"pmid:42539156","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42539156","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2607.18777","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.18777","pdf_url":"https://arxiv.org/pdf/2607.18777","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":"pmh:oai:pubmedcentral.nih.gov:13419637","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13419637/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ArXiv","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2607.18777","doi":"https://doi.org/10.48550/arxiv.2607.18777","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.18777","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.18777","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.18777","pdf_url":"https://arxiv.org/pdf/2607.18777","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":[{"id":"https://openalex.org/G9000878609","display_name":"Unraveling molecular and system-level mechanisms of human disease-associated protein mutations","funder_award_id":"R35GM124952","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334350","display_name":"High Performance Research Computing, Texas A and M University","ror":null},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7170089005.pdf","grobid_xml":"https://content.openalex.org/works/W7170089005.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2993905360","https://openalex.org/W3081168214","https://openalex.org/W4281716291","https://openalex.org/W4297253404","https://openalex.org/W4327900239","https://openalex.org/W4360891289","https://openalex.org/W4384071683","https://openalex.org/W4388890950","https://openalex.org/W4391631327","https://openalex.org/W4391940656","https://openalex.org/W4406152279","https://openalex.org/W4407424959","https://openalex.org/W4409622123","https://openalex.org/W4412929241","https://openalex.org/W4414281281","https://openalex.org/W4414939355","https://openalex.org/W4415798252","https://openalex.org/W7128497447","https://openalex.org/W7159833008","https://openalex.org/W7160933972"],"related_works":["https://openalex.org/W7221824150","https://openalex.org/W7163201207","https://openalex.org/W4415338080","https://openalex.org/W6967242028","https://openalex.org/W7166809731","https://openalex.org/W7203695501","https://openalex.org/W7136170914","https://openalex.org/W7202081072","https://openalex.org/W4415135062","https://openalex.org/W7128497447"],"abstract_inverted_index":{"Evaluating":[0],"machine":[1],"learning":[2],"in":[3,161,182,185],"scientific":[4,187],"domains":[5],"requires":[6],"separating":[7],"correct":[8,11,115],"predictions":[9,146],"from":[10],"reasons":[12],"under":[13],"realistic":[14],"distribution":[15],"shifts.":[16],"We":[17],"introduce":[18],"PertReason,":[19],"a":[20,37,129,138,174],"knowledge-grounded":[21],"benchmark":[22,38],"and":[23,58,65,76,98,123,164,169,179],"framework":[24,176],"suite":[25],"for":[26,177],"cell-state--conditioned":[27],"reasoning":[28,184],"about":[29],"perturbation":[30,67],"effects.":[31],"At":[32],"its":[33],"core,":[34],"PertReasonQA":[35,61],"is":[36],"that":[39],"tests":[40],"whether":[41],"models":[42,91,103],"can":[43],"generate":[44],"mechanistically":[45],"faithful":[46,183],"explanations":[47],"while":[48],"remaining":[49],"robust":[50],"to":[51,84,109,143],"complex":[52],"shifts,":[53],"such":[54,112],"as":[55,113],"new":[56],"cells":[57],"unseen":[59],"perturbations.":[60],"combines":[62],"single-cell":[63],"genetic":[64],"chemical":[66],"data":[68],"across":[69],"multiple":[70],"cellular":[71,121],"contexts":[72],"with":[73,147],"knowledge":[74],"graphs,":[75],"dynamically":[77],"conditions":[78],"pathways":[79,163],"on":[80,89],"cell-specific":[81],"basal":[82],"states":[83],"avoid":[85],"generic":[86],"memorization.":[87],"Evaluations":[88],"state-of-the-art":[90],"reveal":[92],"systematic":[93],"gaps":[94],"between":[95,167],"predictive":[96],"accuracy":[97],"mechanistic":[99,149],"reasoning.":[100,150],"Specifically,":[101],"these":[102],"exhibit":[104],"failure":[105,156],"modes":[106,157],"largely":[107],"invisible":[108],"standard":[110],"benchmarks,":[111],"deriving":[114],"answers":[116],"through":[117],"flawed":[118],"logic,":[119],"ignoring":[120],"context,":[122],"generating":[124],"directionally":[125],"inconsistent":[126],"mechanisms.":[127,170],"As":[128],"reference":[130],"probe":[131],"of":[132],"the":[133,154],"benchmark,":[134],"we":[135,172],"present":[136],"PertReasonLM,":[137],"large":[139],"language":[140],"model":[141,152],"trained":[142],"align":[144],"outcome":[145],"context-specific":[148,162],"Our":[151],"targets":[153],"identified":[155],"by":[158],"grounding":[159],"rationales":[160],"tightening":[165],"agreement":[166],"outcomes":[168],"Together,":[171],"provide":[173],"diagnostic":[175],"exposing":[178],"mitigating":[180],"failures":[181],"data-rich":[186],"systems.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-07-23T00:00:00"}