{"id":"https://openalex.org/W7203676309","doi":"https://doi.org/10.26434/chemrxiv.15007582/v1","title":"Measuring AI Scientists: From Exams to Discovery","display_name":"Measuring AI Scientists: From Exams to Discovery","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203676309","doi":"https://doi.org/10.26434/chemrxiv.15007582/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15007582/v1","doi":"https://doi.org/10.26434/chemrxiv.15007582/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007582/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15007582/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006709853","display_name":"Yuanqi Du","orcid":"https://orcid.org/0000-0003-2988-0374","observed_orcids":["https://orcid.org/0000-0003-2988-0374"]},"institutions":[{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanqi Du","raw_affiliation_strings":["Microsoft Research New England"],"raw_orcid":"https://orcid.org/0000-0003-2988-0374","affiliations":[{"raw_affiliation_string":"Microsoft Research New England","institution_ids":["https://openalex.org/I4400600948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147424161","display_name":"Steven Dillmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Dillmann","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031830117","display_name":"Jon M. Laurent","orcid":"https://orcid.org/0000-0001-6583-4741","observed_orcids":["https://orcid.org/0000-0001-6583-4741"]},"institutions":[{"id":"https://openalex.org/I4405259067","display_name":"Edison Scientific Inc. (United States)","ror":"https://ror.org/01p9amb16","country_code":"US","type":"company","lineage":["https://openalex.org/I4405259067"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jon Laurent","raw_affiliation_strings":["Edison Scientific"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edison Scientific","institution_ids":["https://openalex.org/I4405259067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111404777","display_name":"Peter A. Jansen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Jansen","raw_affiliation_strings":["Allen Institute for AI","University of Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034971788","display_name":"Haojun Jia","orcid":"https://orcid.org/0000-0002-9435-2589","observed_orcids":["https://orcid.org/0000-0002-9435-2589"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haojun Jia","raw_affiliation_strings":["Deep Principle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Principle","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110578233","display_name":"Ludwig Schmidt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludwig Schmidt","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133044052","display_name":"Andrew D. White","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259067","display_name":"Edison Scientific Inc. (United States)","ror":"https://ror.org/01p9amb16","country_code":"US","type":"company","lineage":["https://openalex.org/I4405259067"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew White","raw_affiliation_strings":["Edison Scientific"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edison Scientific","institution_ids":["https://openalex.org/I4405259067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037535334","display_name":"Kristin Aslaug Persson","orcid":"https://orcid.org/0000-0003-2495-5509","observed_orcids":["https://orcid.org/0000-0003-2495-5509"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Persson","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029457626","display_name":"Chenru Duan","orcid":"https://orcid.org/0000-0003-2592-4237","observed_orcids":["https://orcid.org/0000-0003-2592-4237"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenru Duan","raw_affiliation_strings":["Deep Principle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Principle","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.5917999744415283,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.5917999744415283,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.1776999980211258,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.06620000302791595,"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/ai-scientists","display_name":"AI scientists","score":0.9869999885559082},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7319999933242798},{"id":"https://openalex.org/keywords/agentic-systems","display_name":"agentic systems","score":0.8759999871253967},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.9739999771118164},{"id":"https://openalex.org/keywords/scientific-workflows","display_name":"scientific workflows","score":0.4000000059604645},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5860000252723694},{"id":"https://openalex.org/keywords/provenance","display_name":"provenance","score":0.671999990940094},{"id":"https://openalex.org/keywords/negative-results","display_name":"negative results","score":0.6209999918937683},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.5099999904632568},{"id":"https://openalex.org/keywords/trustworthy-ai","display_name":"trustworthy AI","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.7035999894142151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6266999840736389},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5781000256538391},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C2994469624","wikidata":"https://www.wikidata.org/wiki/Q101965","display_name":"Experimental science","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C2778149293","wikidata":"https://www.wikidata.org/wiki/Q309823","display_name":"Open science","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C197352329","wikidata":"https://www.wikidata.org/wiki/Q1093434","display_name":"Citizen science","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15007582/v1","doi":"https://doi.org/10.26434/chemrxiv.15007582/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007582/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15007582/v1","doi":"https://doi.org/10.26434/chemrxiv.15007582/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15007582/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"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/W7214677926","https://openalex.org/W4407310674","https://openalex.org/W7171659198","https://openalex.org/W7171682779","https://openalex.org/W7165788481","https://openalex.org/W7127605006","https://openalex.org/W7115165061","https://openalex.org/W7164034365","https://openalex.org/W7172222066","https://openalex.org/W7214780466"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,40],"and":[3,16,24,71,113,119,134,148,151],"agentic":[4],"systems":[5],"are":[6,159],"increasingly":[7],"embedded":[8],"across":[9],"the":[10,100,104,107,110,114,121],"scientific":[11,43,102,170],"work-flow,":[12],"from":[13,155],"literature":[14],"synthesis":[15],"hypothesis":[17],"generation":[18],"to":[19,117,168],"code":[20],"execution,":[21,133],"data":[22],"analysis":[23],"writing.":[25],"This":[26,123],"broadening":[27],"of":[28,57],"use":[29],"exposes":[30],"a":[31],"mismatch":[32],"in":[33,61],"evaluation:":[34],"current":[35],"benchmarks":[36],"can":[37,49],"test":[38],"whether":[39,47],"answer":[41],"difficult":[42],"questions,":[44],"but":[45],"not":[46],"they":[48],"advance":[50],"science":[51],"itself.":[52],"Discovery":[53],"depends":[54],"on":[55],"sequences":[56],"decisions":[58],"under":[59],"uncertainty,":[60],"which":[62],"hypotheses":[63],"must":[64],"be":[65,87],"made":[66,112],"testable,":[67],"interventions":[68],"executed":[69],"reliably,":[70],"imperfect":[72],"evidence":[73],"interpreted":[74],"with":[75],"calibrated":[76],"restraint.":[77],"In":[78],"this":[79],"Perspective,":[80],"we":[81],"argue":[82],"that":[83,139,165],"AI":[84,163],"scientists":[85,164],"should":[86],"evaluated":[88],"through":[89],"discovery":[90,97,154],"episodes":[91],"rather":[92],"than":[93],"isolated":[94],"problems.":[95],"A":[96],"episode":[98],"records":[99],"evolving":[101],"state,":[103],"actions":[105],"taken,":[106],"observations":[108],"produced,":[109],"revisions":[111],"provenance":[115],"needed":[116],"reproduce":[118],"audit":[120],"process.":[122],"framing":[124],"separates":[125],"three":[126],"coupled":[127],"capabilities\u2014hypothesis":[128],"generation,":[129],"computational":[130],"or":[131],"experimental":[132],"result":[135],"interpretation\u2014and":[136],"motivates":[137],"evaluations":[138,158],"score":[140],"trajectories":[141],"as":[142,144],"well":[143],"outcomes,":[145],"preserve":[146],"failures":[147],"null":[149],"results,":[150],"distinguish":[152],"genuine":[153],"rediscovery.":[156],"Such":[157],"central":[160],"for":[161],"developing":[162],"contribute":[166],"responsibly":[167],"trustworthy":[169],"discovery.":[171]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-19T00:00:00"}