[ {
  "@graph" : [ {
    "@id" : "https://arvix.org/abs/2207.15796",
    "https://sense-nets.xyz/hasZoteroItemType" : [ {
      "@value" : "webpage"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#assertion",
    "http://purl.org/dc/terms/creator" : [ {
      "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY"
    } ],
    "http://purl.org/spar/cito/discusses" : [ {
      "@id" : "https://arvix.org/abs/2207.15796"
    } ],
    "http://purl.org/spar/cito/linksTo" : [ {
      "@id" : "https://arvix.org/abs/2207.15796"
    } ],
    "http://www.w3.org/2000/01/rdf-schema#comment" : [ {
      "@value" : " New paper alert! 🚨 We've been exploring the impact of context on LLM performance evaluation. Turns out, evaluating models on individual examples might not tell the whole story. #MachineLearning #AI\n\n Our findings suggest that batch evaluation allows models to identify patterns and tendencies, leading to more nuanced assessments. Plus, a two-step decision process (analysis + scoring) shows promising results. Exciting times for ML eval! 📊🧠\n\n To learn more, check out the paper: https://arvix.org/abs/2207.15796\n\n"
    } ],
    "https://schema.org/keywords" : [ {
      "@value" : "AI"
    }, {
      "@value" : "LLM"
    }, {
      "@value" : "MachineLearning"
    }, {
      "@value" : "batch-evaluation"
    }, {
      "@value" : "performance-evaluation"
    }, {
      "@value" : "two-step-decision-process"
    } ],
    "https://sense-nets.xyz/announcesResource" : [ {
      "@id" : "https://arvix.org/abs/2207.15796"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#assertion"
}, {
  "@graph" : [ {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0",
    "@type" : [ "http://www.nanopub.org/nschema#Nanopublication" ],
    "http://www.nanopub.org/nschema#hasAssertion" : [ {
      "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#assertion"
    } ],
    "http://www.nanopub.org/nschema#hasProvenance" : [ {
      "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#provenance"
    } ],
    "http://www.nanopub.org/nschema#hasPublicationInfo" : [ {
      "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#pubinfo"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#head"
}, {
  "@graph" : [ {
    "@id" : "https://sense-nets.xyz/",
    "@type" : [ "http://www.w3.org/ns/prov#SoftwareAgent" ],
    "http://www.w3.org/ns/prov#actedOnBehalfOf" : [ {
      "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#activity",
    "@type" : [ "https://sense-nets.xyz/supervisedActivity" ],
    "http://www.w3.org/ns/prov#wasAssociatedWith" : [ {
      "@id" : "https://sense-nets.xyz/"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#assertion",
    "http://www.w3.org/ns/prov#linksTo" : [ {
      "@id" : "https://x.com/sensenets_demo/status/1839674524729483541"
    } ],
    "http://www.w3.org/ns/prov#wasAssociatedWith" : [ {
      "@id" : "https://x.com/sensenets_demo"
    } ],
    "http://www.w3.org/ns/prov#wasAttributedTo" : [ {
      "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY"
    } ],
    "http://www.w3.org/ns/prov#wasGeneratedBy" : [ {
      "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#activity"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY",
    "http://xmlns.com/foaf/0.1/account" : [ {
      "@id" : "https://x.com/sensenets_demo"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#provenance"
}, {
  "@graph" : [ {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0",
    "http://purl.org/dc/terms/created" : [ {
      "@type" : "http://www.w3.org/2001/XMLSchema#dateTime",
      "@value" : "2024-09-27T15:38:26.351Z"
    } ],
    "http://purl.org/dc/terms/creator" : [ {
      "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY"
    } ],
    "http://purl.org/dc/terms/license" : [ {
      "@id" : "https://creativecommons.org/licenses/by/4.0/"
    } ],
    "http://purl.org/nanopub/x/hasNanopubType" : [ {
      "@id" : "https://sense-nets.xyz/SemanticPost"
    } ],
    "http://purl.org/nanopub/x/wasCreatedAt" : [ {
      "@id" : "https://sense-nets.xyz/"
    } ],
    "http://www.w3.org/2000/01/rdf-schema#label" : [ {
      "@value" : "CoSMO Semantic Post"
    } ],
    "https://sense-nets.xyz/hasRootSigner" : [ {
      "@value" : "0x5b9967FC42C160f6146d5ea1f0d08E88370f370b"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#sig",
    "http://purl.org/nanopub/x/hasAlgorithm" : [ {
      "@value" : "RSA"
    } ],
    "http://purl.org/nanopub/x/hasPublicKey" : [ {
      "@value" : "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEArHtI92jm8pAYVsvJabxLGfOT+7G0JyJGh2gwjB5x2pFPga6wWTd+rNBWWUZViIFnaJrBEsJpgdnoupLU9ppwn+khMiGRfxqGsDDzwHcj3Jc75CRys7d3etwXdBdoXfBgjsJiZBazwm13idr6tljRrC1TaEJBnRQAqzBw9cLDeGY77cSznzXT39feUGT168dpCSE9O6u/48DvvWVqciHGsH9cQ+LroJJVsMrorwtsdZnAK+q48wtIP6pIpw5shSJ5LnA0qeN/f4TvTFDV6ItYIXjiWWpTECc/Bxmfnyat3B5xWCu9nvz8fEs7Ns0TuzQwT3/K55iSKDEIi/E0nO97xwIDAQAB"
    } ],
    "http://purl.org/nanopub/x/hasSignature" : [ {
      "@value" : "UfNKMSMxjJF6FmekyAFM3JrDGaiwLMq8OK0b3TsssKDHOlONBvYOzIWsO+Q5sDE3EGKMNcf0L9RvIgAwkaOJd4jgM4DgISHMEE7mOdJJ8+ogj3qea5jjPDXjwPAaUC1v51Hzc7v40LKALWGD3uJEyorHVpAL1z8FO9DlrLbu9sYzQ9zUHxvnRl0fJKGXkzzT1Z5ODlEs5c5/oq2L8LtKlDg5NSW/o2+5ELcKUDXF9cB2qGy8mymmlFXId4D4Q2BuE52/YtOLdRCJQhiEJaC9ZEw8NBUmDILw3NmKj7kOaU9BZzhQkWfc415rNBJSbXxwj6uM5JQIxTX6zUcwTEa9Sw=="
    } ],
    "http://purl.org/nanopub/x/hasSignatureTarget" : [ {
      "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0"
    } ],
    "http://purl.org/nanopub/x/singedBy" : [ {
      "@id" : "https://sense-nets.xyz/"
    } ],
    "http://www.w3.org/ns/prov#wasAssociatedWith" : [ {
      "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJYsigningDelegation"
    } ]
  }, {
    "@id" : "https://w3id.org/np/RA8InlmUPoZ6CTtHP_RkqFBHJSnasnRcjI3qz7EJ-nHJY",
    "http://xmlns.com/foaf/0.1/name" : [ {
      "@value" : "Quinn Zhang, PhD"
    } ]
  } ],
  "@id" : "https://w3id.org/np/RA6amI79BFW1axJuNM0PmqefGYO-SWR72EoGG5fb0KuB0#pubinfo"
} ]