{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:66YZ2SCWBX5AWHJ5KA5K5DR3MV","short_pith_number":"pith:66YZ2SCW","schema_version":"1.0","canonical_sha256":"f7b19d48560dfa0b1d3d503aae8e3b6556739dff35bded03910ddb59c80a45ab","source":{"kind":"arxiv","id":"2405.20574","version":2},"attestation_state":"computed","paper":{"title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Dahyun Kim, Hwalsuk Lee, Hyeonwoo Kim, Sanghoon Kim, Seonghwan Cho, Sukyung Lee, Yungi Kim","submitted_at":"2024-05-31T02:05:45Z","abstract_excerpt":"This paper introduces the Open Ko-LLM Leaderboard and the Ko-H5 Benchmark as vital tools for evaluating Large Language Models (LLMs) in Korean. Incorporating private test sets while mirroring the English Open LLM Leaderboard, we establish a robust evaluation framework that has been well integrated in the Korean LLM community. We perform data leakage analysis that shows the benefit of private test sets along with a correlation study within the Ko-H5 benchmark and temporal analyses of the Ko-H5 score. Moreover, we present empirical support for the need to expand beyond set benchmarks. We hope th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.20574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T02:05:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db4a33a8662b3e750208b5d19117b5a3cfe66f5a46ad8d707ac586f2299d4bdf","abstract_canon_sha256":"fc47aa9c60069c86e280d9d9199db31c3b7095ff2a53df44e578b8a20ef656af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:21.348038Z","signature_b64":"JcvuPnls4abg89D6vHv6adEXoffEvU5pVG5e6BEklfvmjSyc+dRvpUcKeh7o+KrHewRTdC5v76CJUQmJL5vtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7b19d48560dfa0b1d3d503aae8e3b6556739dff35bded03910ddb59c80a45ab","last_reissued_at":"2026-07-05T08:56:21.347533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:21.347533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Dahyun Kim, Hwalsuk Lee, Hyeonwoo Kim, Sanghoon Kim, Seonghwan Cho, Sukyung Lee, Yungi Kim","submitted_at":"2024-05-31T02:05:45Z","abstract_excerpt":"This paper introduces the Open Ko-LLM Leaderboard and the Ko-H5 Benchmark as vital tools for evaluating Large Language Models (LLMs) in Korean. Incorporating private test sets while mirroring the English Open LLM Leaderboard, we establish a robust evaluation framework that has been well integrated in the Korean LLM community. We perform data leakage analysis that shows the benefit of private test sets along with a correlation study within the Ko-H5 benchmark and temporal analyses of the Ko-H5 score. Moreover, we present empirical support for the need to expand beyond set benchmarks. We hope th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20574","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.20574/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.20574","created_at":"2026-07-05T08:56:21.347596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20574v2","created_at":"2026-07-05T08:56:21.347596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20574","created_at":"2026-07-05T08:56:21.347596+00:00"},{"alias_kind":"pith_short_12","alias_value":"66YZ2SCWBX5A","created_at":"2026-07-05T08:56:21.347596+00:00"},{"alias_kind":"pith_short_16","alias_value":"66YZ2SCWBX5AWHJ5","created_at":"2026-07-05T08:56:21.347596+00:00"},{"alias_kind":"pith_short_8","alias_value":"66YZ2SCW","created_at":"2026-07-05T08:56:21.347596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29523","citing_title":"K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV","json":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV.json","graph_json":"https://pith.science/api/pith-number/66YZ2SCWBX5AWHJ5KA5K5DR3MV/graph.json","events_json":"https://pith.science/api/pith-number/66YZ2SCWBX5AWHJ5KA5K5DR3MV/events.json","paper":"https://pith.science/paper/66YZ2SCW"},"agent_actions":{"view_html":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV","download_json":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV.json","view_paper":"https://pith.science/paper/66YZ2SCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20574&json=true","fetch_graph":"https://pith.science/api/pith-number/66YZ2SCWBX5AWHJ5KA5K5DR3MV/graph.json","fetch_events":"https://pith.science/api/pith-number/66YZ2SCWBX5AWHJ5KA5K5DR3MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV/action/storage_attestation","attest_author":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV/action/author_attestation","sign_citation":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV/action/citation_signature","submit_replication":"https://pith.science/pith/66YZ2SCWBX5AWHJ5KA5K5DR3MV/action/replication_record"}},"created_at":"2026-07-05T08:56:21.347596+00:00","updated_at":"2026-07-05T08:56:21.347596+00:00"}