[ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#assertion", "@graph": [ { "@id": "https://arxiv.org/abs/2308.11696", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "preprint" } ] }, { "@id": "https://arxiv.org/abs/2407.13696", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "preprint" } ] }, { "@id": "https://arxiv.org/pdf/2407.13696", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "unknown" } ] }, { "@id": "https://github.com/IBM/BenchBench", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "computerProgram" } ] }, { "@id": "https://huggingface.co/spaces/ibm/benchbench", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "webpage" } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#assertion", "http://purl.org/dc/terms/creator": [ { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ], "http://purl.org/spar/cito/discusses": [ { "@id": "https://arxiv.org/abs/2308.11696" }, { "@id": "https://arxiv.org/pdf/2407.13696" }, { "@id": "https://x.com/LChoshen/status/1696153656653926581" } ], "http://www.w3.org/2000/01/rdf-schema#comment": [ { "@value": " The BenchBench Leaderboard lets you explore 100s of benchmarks and find trustworthy alternatives that fit your resources.\n\nšŸ‘‰ https://huggingface.co/spaces/ibm/benchbench\n\n Currently, benchmark comparisons are often ad-hoc and inconsistent\nmaking results untrustworthy and benchmark choice šŸ¤®\n\nBenchBench & our findings: https://arxiv.org/pdf/2407.13696\noffer standard and transparent comparisons\nto reduce variance and increase confidence in your evaluations!šŸŽ‰ https://twitter.com/LChoshen/status/1835738770353623053/photo/1\n\n 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.\n\nYou can also use them with our package here: https://github.com/IBM/BenchBench\n\n Want to incorporate your benchmark into BenchBench? Make a PR\n\nskeptical about the idea of BenchBench? comment!\n\nDetails? Read: https://arxiv.org/abs/2407.13696\n\nAnd if you are in the mood for other benchmarking aspects: https://x.com/LChoshen/status/1696153656653926581\n\n" } ], "https://schema.org/keywords": [ { "@value": "Benchmarking" }, { "@value": "CentralizedPlatform" }, { "@value": "CuratedDatabase" }, { "@value": "HuggingFace" }, { "@value": "LanguageModels" }, { "@value": "StandardizedMethodology" } ], "https://sense-nets.xyz/announcesResource": [ { "@id": "https://huggingface.co/spaces/ibm/benchbench" } ], "https://sense-nets.xyz/endorses": [ { "@id": "https://arxiv.org/pdf/2407.13696" }, { "@id": "https://huggingface.co/spaces/ibm/benchbench" } ], "https://sense-nets.xyz/recommends": [ { "@id": "https://arxiv.org/abs/2407.13696" }, { "@id": "https://github.com/IBM/BenchBench" } ], "https://sense-nets.xyz/summarizes": [ { "@id": "https://arxiv.org/abs/2407.13696" } ] }, { "@id": "https://x.com/LChoshen/status/1696153656653926581", "https://sense-nets.xyz/hasZoteroItemType": [ { "@value": "forumPost" } ] } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#head", "@graph": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM", "http://www.nanopub.org/nschema#hasAssertion": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#assertion" } ], "http://www.nanopub.org/nschema#hasProvenance": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#provenance" } ], "http://www.nanopub.org/nschema#hasPublicationInfo": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#pubinfo" } ], "@type": [ "http://www.nanopub.org/nschema#Nanopublication" ] } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#pubinfo", "@graph": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#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": "I5lz+4/xIbaHsmaqNtkbAL0ZQmAmLTB8MjqHiqx5ifUTvyjDx0uWFZwslB9tXL6QZ2pITWfYWDY21vr3QCzSzNMzYWx+EeQbJbuF1D/RUBtHQzQLIl1LqH3WyLLPfzpIpskjshyow+5LUifAQ2GU3tRtdXzAoEz4MKMKHRAZbolbXsjrON65/lIjSqWvDYHAFNCtyBjvTIH3qwycis6GG7vyUKQ+K0FUcOf+CfttB8A+gV/HFXOGId10hn0O/saxCcxhffApPwaIv6yOm0NZOHlE4OpoZg5w3FzEQhKN/NjaFBWCnhxWdJSwpNr8m/gGCDUAmeQkhDprtiq6Obtsng==" } ], "http://purl.org/nanopub/x/hasSignatureTarget": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM" } ], "http://purl.org/nanopub/x/singedBy": [ { "@id": "https://sense-nets.xyz/" } ], "http://www.w3.org/ns/prov#wasAssociatedWith": [ { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16VtssigningDelegation" } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM", "http://purl.org/dc/terms/created": [ { "@value": "2024-09-16T18:17:08.034Z", "@type": "http://www.w3.org/2001/XMLSchema#dateTime" } ], "http://purl.org/dc/terms/creator": [ { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ], "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" } ], "http://www.w3.org/ns/prov#wasAttributedTo": [ { "@id": "https://orcid.org/0000-0002-0085-6496" } ], "https://sense-nets.xyz/hasRootSigner": [ { "@value": "0xf6ECcfD463afB464dcC85b051DF2E93E2646E6D2" } ] }, { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts", "http://xmlns.com/foaf/0.1/account": [ { "@id": "https://orcid.org/0000-0002-0085-6496" } ], "http://xmlns.com/foaf/0.1/name": [ { "@value": "Leshem Choshen šŸ¤–šŸ¤— @ICML wanna talk?" } ] } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#provenance", "@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/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ] }, { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts", "http://xmlns.com/foaf/0.1/account": [ { "@id": "https://orcid.org/0000-0002-0085-6496" }, { "@id": "https://x.com/LChoshen" } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#activity", "@type": [ "https://sense-nets.xyz/unsupervisedActivity" ], "http://www.w3.org/ns/prov#wasAssociatedWith": [ { "@id": "https://sense-nets.xyz/" } ] }, { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#assertion", "http://www.w3.org/ns/prov#linksTo": [ { "@id": "https://x.com/LChoshen/status/1835738766851645622" } ], "http://www.w3.org/ns/prov#wasAssociatedWith": [ { "@id": "https://x.com/LChoshen" } ], "http://www.w3.org/ns/prov#wasAttributedTo": [ { "@id": "https://orcid.org/0000-0002-0085-6496" }, { "@id": "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ], "http://www.w3.org/ns/prov#wasGeneratedBy": [ { "@id": "https://w3id.org/np/RA0at64nVVpsyTU-R4bAsmdCkO8pK2ZFLGsLnJIoS07wM#activity" } ] } ] } ]