{"id":"https://openalex.org/W7214656277","doi":"https://doi.org/10.48550/arxiv.2609.30550","title":"Benchy: towards a universal language for task-oriented AI benchmarks","display_name":"Benchy: towards a universal language for task-oriented AI benchmarks","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214656277","doi":"https://doi.org/10.48550/arxiv.2609.30550"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.30550","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30550","pdf_url":"https://arxiv.org/pdf/2609.30550","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/2609.30550","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144455821","display_name":"Francis F Daniel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel, Francis F","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071184086","display_name":"Mauro Iba\u00f1ez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iba\u00f1ez, Mauro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143757903","display_name":"Francis Perelman","orcid":"https://orcid.org/0009-0009-7040-7846","observed_orcids":["https://orcid.org/0009-0009-7040-7846"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perelman, Francis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100038617","display_name":"Marian Basti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Basti, Marian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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/T11986","display_name":"Scientific Computing and Data Management","score":0.7041000127792358,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.7041000127792358,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.050700001418590546,"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/T10260","display_name":"Software Engineering Research","score":0.03959999978542328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-benchmarks","display_name":"AI benchmarks","score":0.7620000243186951},{"id":"https://openalex.org/keywords/semantic-language","display_name":"semantic language","score":0.5759999752044678},{"id":"https://openalex.org/keywords/yaml","display_name":"YAML","score":0.49799999594688416},{"id":"https://openalex.org/keywords/ontology-information-science","display_name":"ontology (information science)","score":0.546999990940094},{"id":"https://openalex.org/keywords/failure-semantics","display_name":"failure semantics","score":0.8579999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377000093460083},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.7696999907493591},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6333000063896179},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4106999933719635},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C101230327","wikidata":"https://www.wikidata.org/wiki/Q826165","display_name":"Web Ontology Language","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.30550","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30550","pdf_url":"https://arxiv.org/pdf/2609.30550","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.2609.30550","doi":"https://doi.org/10.48550/arxiv.2609.30550","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.30550","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:2609.30550","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30550","pdf_url":"https://arxiv.org/pdf/2609.30550","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214656277.pdf","grobid_xml":"https://content.openalex.org/works/W7214656277.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7138840974","https://openalex.org/W4285293606","https://openalex.org/W7104293672","https://openalex.org/W7162448080","https://openalex.org/W7159637713","https://openalex.org/W7160215297","https://openalex.org/W7160301289","https://openalex.org/W3023785876","https://openalex.org/W4409360946","https://openalex.org/W6941590861"],"abstract_inverted_index":{"Benchy":[0],"is":[1,14,28],"a":[2,18,20,24,35,58,66,117,122],"semantic":[3,50,148],"language":[4],"and":[5,23,27,62,97,108,153,159,164,167],"execution":[6,165],"engine":[7,73,110,184],"for":[8,181],"benchmarking":[9],"AI":[10],"programs.":[11],"A":[12],"benchmark":[13,142],"completely":[15],"specified":[16],"by":[17,57],"program,":[19],"scoring":[21,106,158],"function,":[22],"dataset,":[25],"B=(P,S,D),":[26],"separate":[29],"from":[30],"the":[31,38,72,100,105,109,134,147,151,157,162,168,171,177,182],"AI-system":[32],"taking":[33],"it;":[34],"run":[36],"binds":[37],"two,":[39],"R=(B,AI).":[40],"Benchmarks":[41],"are":[42,104],"authored":[43],"as":[44],"canonical":[45,67],"YAML":[46],"in":[47],"which":[48,129],"each":[49],"concept":[51],"has":[52],"one":[53,112],"valid":[54],"syntax,":[55],"classified":[56],"shared":[59],"task/domain/language":[60],"ontology,":[61],"deterministically":[63],"compiled":[64],"into":[65,141],"JSON":[68],"intermediate":[69],"representation":[70],"that":[71],"executes.":[74],"Compilation":[75],"changes":[76],"representation,":[77],"not":[78,82],"meaning:":[79],"it":[80],"does":[81],"repair":[83],"invalid":[84],"definitions":[85],"or":[86],"inject":[87],"hidden":[88],"defaults.":[89],"Programs":[90],"use":[91],"fixed":[92],"schemas":[93],"of":[94,170],"named":[95],"input":[96,119],"output":[98,102,124],"fields,":[99],"leaf":[101],"fields":[103],"dimensions,":[107],"exposes":[111],"universal":[113],"runtime":[114],"contract":[115,180],"---":[116,127],"named-field":[118,123],"object":[120,125,149],"in,":[121],"out":[126],"to":[128],"external":[130],"AI-systems":[131],"adapt":[132],"at":[133],"boundary,":[135],"so":[136],"integration":[137],"mechanics":[138],"never":[139],"propagate":[140],"semantics.":[143],"This":[144],"paper":[145],"gives":[146],"model,":[150],"ontology":[152],"task-to-program":[154],"validation":[155],"rule,":[156],"failure":[160],"semantics,":[161],"compilation":[163],"architecture,":[166],"scope":[169],"current":[172],"language.":[173],"An":[174],"appendix":[175],"fixes":[176],"normative":[178],"engineering":[179],"first":[183],"implementation.":[185]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-29T00:00:00"}