{"id":"https://openalex.org/W7204921971","doi":"https://doi.org/10.48550/arxiv.2608.30165","title":"Science sandboxes measure the scientific capability of AI agents","display_name":"Science sandboxes measure the scientific capability of AI agents","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204921971","doi":"https://doi.org/10.48550/arxiv.2608.30165"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30165","pdf_url":"https://arxiv.org/pdf/2608.30165","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.30165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148931638","display_name":"Arya S. Rao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rao, Arya S.","raw_affiliation_strings":["Department of Biomedical Informatics , Harvard Medical School ; Boston , MA 02115 , USA","The Broad Institute of MIT and Harvard ; Cambridge , MA 02142 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics , Harvard Medical School ; Boston , MA 02115 , USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"The Broad Institute of MIT and Harvard ; Cambridge , MA 02142 , USA","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156958","display_name":"Rodrigo I. Castro","orcid":"https://orcid.org/0000-0002-9833-4169","observed_orcids":["https://orcid.org/0000-0002-9833-4169"]},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Castro, Rodrigo I.","raw_affiliation_strings":["The Jackson Laboratory ; Bar Harbor , ME 04609 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Jackson Laboratory ; Bar Harbor , ME 04609 , USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044295421","display_name":"Sager J. Gosai","orcid":"https://orcid.org/0000-0003-4494-7362","observed_orcids":["https://orcid.org/0000-0003-4494-7362"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gosai, Sager J.","raw_affiliation_strings":["Sutter Hill Ventures ; Palo Alto , CA 94304 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sutter Hill Ventures ; Palo Alto , CA 94304 , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113045084","display_name":"Kenneth B. Hsu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsu, Kenneth B.","raw_affiliation_strings":["Department of Systems Biology , Harvard Medical School , Boston , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Biology , Harvard Medical School , Boston , MA , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006487374","display_name":"Yasha Ektefaie","orcid":"https://orcid.org/0000-0003-2759-4470","observed_orcids":["https://orcid.org/0000-0003-2759-4470"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ektefaie, Yasha","raw_affiliation_strings":["Massachusetts Institute of Technology , Cambridge , MA 02139 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology , Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071122261","display_name":"Shantanu Singh","orcid":"https://orcid.org/0000-0003-3150-3025","observed_orcids":["https://orcid.org/0000-0003-3150-3025","https://orcid.org/0000-0002-2705-2201"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Singh, Shantanu","raw_affiliation_strings":["Massachusetts Institute of Technology , Cambridge , MA 02139 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology , Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039958236","display_name":"Sangeeta N. Bhatia","orcid":"https://orcid.org/0000-0002-1293-2097","observed_orcids":["https://orcid.org/0000-0002-1293-2097","https://orcid.org/0000-0001-6525-101X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhatia, Sangeeta N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069908459","display_name":"Steven K. Reilly","orcid":"https://orcid.org/0000-0003-3140-1483","observed_orcids":["https://orcid.org/0000-0003-3140-1483"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reilly, Steven K.","raw_affiliation_strings":["Department of Genetics , Yale School of Medicine ; New Haven , CT , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics , Yale School of Medicine ; New Haven , CT , USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079877718","display_name":"Ryan Tewhey","orcid":"https://orcid.org/0000-0002-4607-8001","observed_orcids":["https://orcid.org/0000-0002-4607-8001"]},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tewhey, Ryan","raw_affiliation_strings":["The Jackson Laboratory ; Bar Harbor , ME 04609 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Jackson Laboratory ; Bar Harbor , ME 04609 , USA","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020748592","display_name":"Eric S. Lander","orcid":"https://orcid.org/0000-0003-2662-4631","observed_orcids":["https://orcid.org/0000-0003-2662-4631"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lander, Eric S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047819759","display_name":"Pardis C. Sabeti","orcid":"https://orcid.org/0000-0002-9843-1890","observed_orcids":["https://orcid.org/0000-0002-9843-1890","https://orcid.org/0000-0002-3970-6380"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabeti, Pardis C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T13904","display_name":"Artificial Intelligence Applications","score":0.39820000529289246,"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":0.39820000529289246,"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":0.11500000208616257,"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/T10778","display_name":"Philosophy of Biology and Scientific Explanation","score":0.1137000024318695,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-agents","display_name":"AI agents","score":0.8069999814033508},{"id":"https://openalex.org/keywords/scientific-reasoning","display_name":"scientific reasoning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/hypothesis-revision","display_name":"hypothesis revision","score":0.7020000219345093},{"id":"https://openalex.org/keywords/experimental-design","display_name":"experimental design","score":0.460999995470047},{"id":"https://openalex.org/keywords/regulatory-genomics","display_name":"regulatory genomics","score":0.8029999732971191},{"id":"https://openalex.org/keywords/protein-fitness-prediction","display_name":"protein fitness prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/biological-priors","display_name":"biological priors","score":0.7829999923706055},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.6510000228881836},{"id":"https://openalex.org/keywords/predictive-model","display_name":"prediction model","score":0.6769999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384000182151794},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C207520454","wikidata":"https://www.wikidata.org/wiki/Q3099911","display_name":"Scientific instrument","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C3020442560","wikidata":"https://www.wikidata.org/wiki/Q4971815","display_name":"Broad spectrum","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C23213167","wikidata":"https://www.wikidata.org/wiki/Q2351730","display_name":"Scientific progress","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30165","pdf_url":"https://arxiv.org/pdf/2608.30165","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.2608.30165","doi":"https://doi.org/10.48550/arxiv.2608.30165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30165","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:2608.30165","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30165","pdf_url":"https://arxiv.org/pdf/2608.30165","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":[{"id":"https://openalex.org/F4320314070","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204921971.pdf","grobid_xml":"https://content.openalex.org/works/W7204921971.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W4400373784","https://openalex.org/W4402345509","https://openalex.org/W4403925918","https://openalex.org/W4409727276","https://openalex.org/W4415936065","https://openalex.org/W4416043407","https://openalex.org/W4417517774","https://openalex.org/W6948174282","https://openalex.org/W6948437691","https://openalex.org/W7131430872","https://openalex.org/W7161734976","https://openalex.org/W7166204187","https://openalex.org/W7168545483"],"related_works":["https://openalex.org/W7164577541","https://openalex.org/W7101416451","https://openalex.org/W7221804992","https://openalex.org/W7166885752","https://openalex.org/W7129076256","https://openalex.org/W7220679195","https://openalex.org/W7203676309","https://openalex.org/W4406092746","https://openalex.org/W7154229203","https://openalex.org/W6948238425"],"abstract_inverted_index":{"Scientific":[0],"progress":[1],"depends":[2],"not":[3],"only":[4],"on":[5,9,71,100],"finding":[6],"solutions,":[7],"but":[8],"learning":[10],"the":[11,55,132,152,155,182],"rules":[12,153,168],"that":[13,20],"explain":[14],"why":[15],"they":[16,164],"work":[17],"and":[18,45,84,103,126,130,188,197],"using":[19],"understanding":[21,151],"to":[22,53,66,74,195],"design":[23],"better":[24],"experiments.":[25],"We":[26],"introduce":[27],"science":[28,92,179],"sandboxes,":[29],"a":[30,80,85,108,147,190],"framework":[31,117],"for":[32,87],"studying":[33],"this":[34,116],"capability":[35,186],"in":[36,58,118,193],"AI":[37],"agents":[38,89,144],"through":[39],"repeated":[40],"cycles":[41],"of":[42,96,110,123,134,184],"experimentation,":[43],"feedback,":[44],"hypothesis":[46],"revision.":[47],"Science":[48],"sandboxes":[49,93,180],"invite":[50],"an":[51],"agent":[52],"query":[54],"natural":[56],"world":[57],"different":[59],"ways,":[60],"ranging":[61],"from":[62],"\"wet\"":[63],"physical":[64],"experiments,":[65],"\"damp\"":[67],"predictive":[68],"models":[69,122],"trained":[70],"empirical":[72,111],"data,":[73],"\"dry\"":[75],"invented":[76],"rules.":[77],"By":[78,174],"establishing":[79],"common":[81],"experimental":[82],"loop":[83],"protocol":[86],"evaluating":[88],"within":[90],"it,":[91],"allow":[94],"assessment":[95],"both":[97],"quantitative":[98,148],"performance":[99],"specific":[101],"metrics":[102],"qualitative":[104],"scientific":[105,160,185],"reasoning,":[106],"across":[107],"spectrum":[109],"verifiability.":[112],"Here,":[113],"we":[114,140],"instantiate":[115],"two":[119],"biological":[120,172],"settings,":[121,139],"regulatory":[124],"genomics":[125],"protein":[127],"fitness":[128],"prediction,":[129],"examine":[131],"capabilities":[133],"frontier":[135,183],"agents.":[136],"Across":[137],"these":[138],"could":[141],"see":[142],"when":[143,163],"successfully":[145],"optimized":[146],"metric":[149],"without":[150],"underlying":[154],"system.":[156],"In":[157],"particular,":[158],"their":[159],"reasoning":[161],"deteriorated":[162],"encountered":[165],"systems":[166],"whose":[167],"fell":[169],"outside":[170],"familiar":[171],"priors.":[173],"highlighting":[175],"such":[176],"failure":[177],"modes,":[178],"make":[181],"measurable":[187],"provide":[189],"controlled":[191],"setting":[192],"which":[194],"study":[196],"ultimately":[198],"expand":[199],"it.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}