[ { "@graph" : [ { "@id" : "https://arxiv.org/abs/2406.17681", "https://sense-nets.xyz/hasZoteroItemType" : [ { "@value" : "preprint" } ] }, { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#assertion", "http://purl.org/dc/terms/creator" : [ { "@id" : "https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ], "http://purl.org/spar/cito/includesQuotationFrom" : [ { "@id" : "https://x.com/neuranna/status/1791465842632454184" } ], "http://purl.org/spar/cito/linksTo" : [ { "@id" : "https://arxiv.org/abs/2406.17681" } ], "http://www.w3.org/2000/01/rdf-schema#comment" : [ { "@value" : " To reduce evaluation contamination\n@XuanmingZhang07 @Zhou_Yu_AI @columbianlp et al.\nconvert dataset examples into templates(Fig.)\nhttps://arxiv.org/abs/2406.17681\n\nEWOK datasets are built to have this trait\nhttps://x.com/neuranna/status/1791465842632454184\nInteresting trend will it last? solve contamination? https://twitter.com/LChoshen/status/1806396147281637645/photo/1\n\n @XuanmingZhang07 @Zhou_Yu_AI @columbianlp If you ask me, a nice step, but it only solves the worst contamination (clear training on the test set). Not on just training on similar formats, synthetic data etc. to improve.\nSo it is a good approach that should last, but we need more. (@deliprao you had similar claim right?)\n\n" } ], "https://schema.org/keywords" : [ { "@value" : "dataset-templates" }, { "@value" : "evaluation-contamination" }, { "@value" : "ewok-datasets" }, { "@value" : "language-model-benchmarking" }, { "@value" : "varbench" } ], "https://sense-nets.xyz/quotesPost" : [ { "@id" : "https://x.com/neuranna/status/1791465842632454184" } ] }, { "@id" : "https://x.com/neuranna/status/1791465842632454184", "https://sense-nets.xyz/hasZoteroItemType" : [ { "@value" : "forumPost" } ] } ], "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#assertion" }, { "@graph" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc", "@type" : [ "http://www.nanopub.org/nschema#Nanopublication" ], "http://www.nanopub.org/nschema#hasAssertion" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#assertion" } ], "http://www.nanopub.org/nschema#hasProvenance" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#provenance" } ], "http://www.nanopub.org/nschema#hasPublicationInfo" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#pubinfo" } ] } ], "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#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/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts" } ] }, { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#activity", "@type" : [ "https://sense-nets.xyz/supervisedActivity" ], "http://www.w3.org/ns/prov#wasAssociatedWith" : [ { "@id" : "https://sense-nets.xyz/" } ] }, { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#assertion", "http://www.w3.org/ns/prov#linksTo" : [ { "@id" : "https://x.com/LChoshen/status/1806396147281637645" } ], "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/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#activity" } ] }, { "@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/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#provenance" }, { "@graph" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc", "http://purl.org/dc/terms/created" : [ { "@type" : "http://www.w3.org/2001/XMLSchema#dateTime", "@value" : "2024-09-12T18:53:31.101Z" } ], "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/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#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" : "IhJE7e2QCuhi9lBnA6zyNAFEnuD0Kq+6UXzbq4THcwqG0odW9IFvLzUeFrsO55KnIGA1Mz4O5TDx9CZvCLnkRxNYmCM4ikItw54oCAYwDE40zONWvcYAZpeSQvECknmIwaTEikPBENjFKF6BxgYEgtxCP0pMc37iuAvUHQq5uBBugkbSr8FgRFi3+3IIOEiiWANOxiioxtznNCG7VdaSnD1XkvGQGwoS7HxUdQCOvj+1cZBs4YnLk2ZAixo0AI0X9N3/ucT0om5uGRBtkMdluhggmrK7v6o4dxGDH6pV/RE5RpnxIjOcdtzczPF0MhpaLCZiPPYbzFkIb3WITivdmw==" } ], "http://purl.org/nanopub/x/hasSignatureTarget" : [ { "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc" } ], "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/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 🤖🤗 @ICML wanna talk?" } ] } ], "@id" : "https://w3id.org/np/RA5onfai3TcQTXxloau--mcY6JKg8yXNeMmqo29rFn4Qc#pubinfo" } ]