@prefix this: <https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM> .
@prefix sub: <https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix np: <http://www.nanopub.org/nschema#> .
@prefix npx: <http://purl.org/nanopub/x/> .
@prefix dcterms: <http://purl.org/dc/terms/> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix schema: <https://schema.org/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix orcid: <https://orcid.org/> .
sub:head {
  this: np:hasAssertion sub:assertion ;
    np:hasProvenance sub:provenance ;
    np:hasPublicationInfo sub:pubinfo ;
    a np:Nanopublication .
}
sub:assertion {
  <https://arxiv.org/abs/2308.11696> <https://sense-nets.xyz/hasZoteroItemType> "preprint" .
  <https://arxiv.org/abs/2407.13696> <https://sense-nets.xyz/hasZoteroItemType> "preprint" .
  <https://arxiv.org/pdf/2407.13696> <https://sense-nets.xyz/hasZoteroItemType> "unknown" .
  <https://github.com/IBM/BenchBench> <https://sense-nets.xyz/hasZoteroItemType> "computerProgram" .
  <https://huggingface.co/spaces/ibm/benchbench> <https://sense-nets.xyz/hasZoteroItemType> "webpage" .
  sub:assertion dcterms:creator <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> ;
    <http://purl.org/spar/cito/discusses> <https://arxiv.org/abs/2308.11696> , <https://arxiv.org/pdf/2407.13696> , <https://x.com/LChoshen/status/1696153656653926581> ;
    rdfs:comment """ The BenchBench Leaderboard lets you explore 100s of benchmarks and find trustworthy alternatives that fit your resources.

👉 https://huggingface.co/spaces/ibm/benchbench

Currently, benchmark comparisons are often ad-hoc and inconsistent
making results untrustworthy and benchmark choice 🤮

BenchBench &amp; our findings: https://arxiv.org/pdf/2407.13696
offer standard and transparent comparisons
to reduce variance and increase confidence in your evaluations!🎉 https://twitter.com/LChoshen/status/1835738770353623053/photo/1

No need to manually gather and compare benchmark data! BenchBench provides a centralized platform with a curated database and standardized methodology for effortless benchmark agreement testing.

You can also use them with our package here: https://github.com/IBM/BenchBench

Want to incorporate your benchmark into BenchBench? Make a PR

skeptical about the idea of BenchBench? comment!

Details? Read: https://arxiv.org/abs/2407.13696

And if you are in the mood for other benchmarking aspects: https://x.com/LChoshen/status/1696153656653926581

""" ;
    schema:keywords "Benchmarking" , "CentralizedPlatform" , "CuratedDatabase" , "HuggingFace" , "LanguageModels" , "StandardizedMethodology" ;
    <https://sense-nets.xyz/announcesResource> <https://huggingface.co/spaces/ibm/benchbench> ;
    <https://sense-nets.xyz/endorses> <https://arxiv.org/pdf/2407.13696> , <https://huggingface.co/spaces/ibm/benchbench> ;
    <https://sense-nets.xyz/recommends> <https://arxiv.org/abs/2407.13696> , <https://github.com/IBM/BenchBench> ;
    <https://sense-nets.xyz/summarizes> <https://arxiv.org/abs/2407.13696> .
  <https://x.com/LChoshen/status/1696153656653926581> <https://sense-nets.xyz/hasZoteroItemType> "forumPost" .
}
sub:provenance {
  <https://sense-nets.xyz/> a prov:SoftwareAgent ;
    prov:actedOnBehalfOf <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> .
  sub:activity a <https://sense-nets.xyz/unsupervisedActivity> ;
    prov:wasAssociatedWith <https://sense-nets.xyz/> .
  sub:assertion prov:linksTo <https://x.com/LChoshen/status/1835738766851645622> ;
    prov:wasAssociatedWith <https://x.com/LChoshen> ;
    prov:wasAttributedTo orcid:0000-0002-0085-6496 , <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> ;
    prov:wasGeneratedBy sub:activity .
  <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> foaf:account orcid:0000-0002-0085-6496 , <https://x.com/LChoshen> .
}
sub:pubinfo {
  sub:sig npx:hasAlgorithm "RSA" ;
    npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEArHtI92jm8pAYVsvJabxLGfOT+7G0JyJGh2gwjB5x2pFPga6wWTd+rNBWWUZViIFnaJrBEsJpgdnoupLU9ppwn+khMiGRfxqGsDDzwHcj3Jc75CRys7d3etwXdBdoXfBgjsJiZBazwm13idr6tljRrC1TaEJBnRQAqzBw9cLDeGY77cSznzXT39feUGT168dpCSE9O6u/48DvvWVqciHGsH9cQ+LroJJVsMrorwtsdZnAK+q48wtIP6pIpw5shSJ5LnA0qeN/f4TvTFDV6ItYIXjiWWpTECc/Bxmfnyat3B5xWCu9nvz8fEs7Ns0TuzQwT3/K55iSKDEIi/E0nO97xwIDAQAB" ;
    npx:hasSignature "I5lz+4/xIbaHsmaqNtkbAL0ZQmAmLTB8MjqHiqx5ifUTvyjDx0uWFZwslB9tXL6QZ2pITWfYWDY21vr3QCzSzNMzYWx+EeQbJbuF1D/RUBtHQzQLIl1LqH3WyLLPfzpIpskjshyow+5LUifAQ2GU3tRtdXzAoEz4MKMKHRAZbolbXsjrON65/lIjSqWvDYHAFNCtyBjvTIH3qwycis6GG7vyUKQ+K0FUcOf+CfttB8A+gV/HFXOGId10hn0O/saxCcxhffApPwaIv6yOm0NZOHlE4OpoZg5w3FzEQhKN/NjaFBWCnhxWdJSwpNr8m/gGCDUAmeQkhDprtiq6Obtsng==" ;
    npx:hasSignatureTarget this: ;
    npx:singedBy <https://sense-nets.xyz/> ;
    prov:wasAssociatedWith <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16VtssigningDelegation> .
  this: dcterms:created "2024-09-16T18:17:08.034Z"^^xsd:dateTime ;
    dcterms:creator <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> ;
    dcterms:license <https://creativecommons.org/licenses/by/4.0/> ;
    npx:hasNanopubType <https://sense-nets.xyz/SemanticPost> ;
    npx:wasCreatedAt <https://sense-nets.xyz/> ;
    rdfs:label "CoSMO Semantic Post" ;
    prov:wasAttributedTo orcid:0000-0002-0085-6496 ;
    <https://sense-nets.xyz/hasRootSigner> "0xf6ECcfD463afB464dcC85b051DF2E93E2646E6D2" .
  <https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> foaf:account orcid:0000-0002-0085-6496 ;
    foaf:name "Leshem Choshen 🤖🤗 @ICML wanna talk?" .
}