{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FXPOCMDOCXTD3KNBST7Y64KJL3","short_pith_number":"pith:FXPOCMDO","schema_version":"1.0","canonical_sha256":"2ddee1306e15e63da9a194ff8f71495ef24dac4e7408ac75cedb16cc06e8b1b8","source":{"kind":"arxiv","id":"2505.16125","version":1},"attestation_state":"computed","paper":{"title":"KoBALT: Korean Benchmark For Advanced Linguistic Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeyoung Oh, Dongjun Jang, Hyemi Jo, Hyohyeong Chang, Hyopil Shin, Jaeyoon Kim, Jinsik Lee, Sangah Lee, Sihyun Oh, Sunkyoung Kim, Wooseok Song, Youngchae Ahn","submitted_at":"2025-05-22T02:03:07Z","abstract_excerpt":"We introduce KoBALT (Korean Benchmark for Advanced Linguistic Tasks), a comprehensive linguistically-motivated benchmark comprising 700 multiple-choice questions spanning 24 phenomena across five linguistic domains: syntax, semantics, pragmatics, phonetics/phonology, and morphology. KoBALT is designed to advance the evaluation of large language models (LLMs) in Korean, a morphologically rich language, by addressing the limitations of conventional benchmarks that often lack linguistic depth and typological grounding. It introduces a suite of expert-curated, linguistically motivated questions wi"},"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":"2505.16125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T02:03:07Z","cross_cats_sorted":[],"title_canon_sha256":"fc511a880a9b6e163d527557c8d82c4008bf7a781c3eb6680a158729082bd0f2","abstract_canon_sha256":"b4f54a1958dc939d4bc99702a8c750b73debece0e9ef322cca86f13c16a3c40f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:30.355181Z","signature_b64":"ChJdXXSQQf0qsRei23BiJAXYECWe0/HDurkUVmfxPIzKZtrs3X75FBuFTBceL3pRDCFRoSSC8O9vpw5ubf+/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ddee1306e15e63da9a194ff8f71495ef24dac4e7408ac75cedb16cc06e8b1b8","last_reissued_at":"2026-07-05T11:07:30.354686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:30.354686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KoBALT: Korean Benchmark For Advanced Linguistic Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeyoung Oh, Dongjun Jang, Hyemi Jo, Hyohyeong Chang, Hyopil Shin, Jaeyoon Kim, Jinsik Lee, Sangah Lee, Sihyun Oh, Sunkyoung Kim, Wooseok Song, Youngchae Ahn","submitted_at":"2025-05-22T02:03:07Z","abstract_excerpt":"We introduce KoBALT (Korean Benchmark for Advanced Linguistic Tasks), a comprehensive linguistically-motivated benchmark comprising 700 multiple-choice questions spanning 24 phenomena across five linguistic domains: syntax, semantics, pragmatics, phonetics/phonology, and morphology. KoBALT is designed to advance the evaluation of large language models (LLMs) in Korean, a morphologically rich language, by addressing the limitations of conventional benchmarks that often lack linguistic depth and typological grounding. It introduces a suite of expert-curated, linguistically motivated questions wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16125","kind":"arxiv","version":1},"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/2505.16125/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":"2505.16125","created_at":"2026-07-05T11:07:30.354754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16125v1","created_at":"2026-07-05T11:07:30.354754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16125","created_at":"2026-07-05T11:07:30.354754+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXPOCMDOCXTD","created_at":"2026-07-05T11:07:30.354754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXPOCMDOCXTD3KNB","created_at":"2026-07-05T11:07:30.354754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXPOCMDO","created_at":"2026-07-05T11:07:30.354754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.15949","citing_title":"BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3","json":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3.json","graph_json":"https://pith.science/api/pith-number/FXPOCMDOCXTD3KNBST7Y64KJL3/graph.json","events_json":"https://pith.science/api/pith-number/FXPOCMDOCXTD3KNBST7Y64KJL3/events.json","paper":"https://pith.science/paper/FXPOCMDO"},"agent_actions":{"view_html":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3","download_json":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3.json","view_paper":"https://pith.science/paper/FXPOCMDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16125&json=true","fetch_graph":"https://pith.science/api/pith-number/FXPOCMDOCXTD3KNBST7Y64KJL3/graph.json","fetch_events":"https://pith.science/api/pith-number/FXPOCMDOCXTD3KNBST7Y64KJL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3/action/storage_attestation","attest_author":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3/action/author_attestation","sign_citation":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3/action/citation_signature","submit_replication":"https://pith.science/pith/FXPOCMDOCXTD3KNBST7Y64KJL3/action/replication_record"}},"created_at":"2026-07-05T11:07:30.354754+00:00","updated_at":"2026-07-05T11:07:30.354754+00:00"}