{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TO54FRNJVM5FL5BZ6HT66BH7CP","short_pith_number":"pith:TO54FRNJ","schema_version":"1.0","canonical_sha256":"9bbbc2c5a9ab3a55f439f1e7ef04ff13d97926f07be7d9ac38d87bb3914a4280","source":{"kind":"arxiv","id":"2507.04014","version":1},"attestation_state":"computed","paper":{"title":"Nunchi-Bench: Benchmarking Language Models on Cultural Reasoning with a Focus on Korean Superstition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kyuhee Kim, Sangah Lee","submitted_at":"2025-07-05T11:52:09Z","abstract_excerpt":"As large language models (LLMs) become key advisors in various domains, their cultural sensitivity and reasoning skills are crucial in multicultural environments. We introduce Nunchi-Bench, a benchmark designed to evaluate LLMs' cultural understanding, with a focus on Korean superstitions. The benchmark consists of 247 questions spanning 31 topics, assessing factual knowledge, culturally appropriate advice, and situational interpretation. We evaluate multilingual LLMs in both Korean and English to analyze their ability to reason about Korean cultural contexts and how language variations affect"},"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":"2507.04014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T11:52:09Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"d5014d9d458cd7f72c7d713250409f6e7cc67eff002012eb56be7946fd5a7cd0","abstract_canon_sha256":"78ed31f2715475e4a8da7ef9d298940ae33bbf156c552177e5afc6baa9b484d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:40.851975Z","signature_b64":"rzP/7cC+23b4K9EXhx3x8y8WAPWpDbPGqAGh6O1c+YA6ZOksVUVfx1l59cIaD4IVfwHnZW1G3/YID5imvYNEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bbbc2c5a9ab3a55f439f1e7ef04ff13d97926f07be7d9ac38d87bb3914a4280","last_reissued_at":"2026-07-05T11:32:40.851526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:40.851526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nunchi-Bench: Benchmarking Language Models on Cultural Reasoning with a Focus on Korean Superstition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kyuhee Kim, Sangah Lee","submitted_at":"2025-07-05T11:52:09Z","abstract_excerpt":"As large language models (LLMs) become key advisors in various domains, their cultural sensitivity and reasoning skills are crucial in multicultural environments. We introduce Nunchi-Bench, a benchmark designed to evaluate LLMs' cultural understanding, with a focus on Korean superstitions. The benchmark consists of 247 questions spanning 31 topics, assessing factual knowledge, culturally appropriate advice, and situational interpretation. We evaluate multilingual LLMs in both Korean and English to analyze their ability to reason about Korean cultural contexts and how language variations affect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04014","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/2507.04014/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":"2507.04014","created_at":"2026-07-05T11:32:40.851577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04014v1","created_at":"2026-07-05T11:32:40.851577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04014","created_at":"2026-07-05T11:32:40.851577+00:00"},{"alias_kind":"pith_short_12","alias_value":"TO54FRNJVM5F","created_at":"2026-07-05T11:32:40.851577+00:00"},{"alias_kind":"pith_short_16","alias_value":"TO54FRNJVM5FL5BZ","created_at":"2026-07-05T11:32:40.851577+00:00"},{"alias_kind":"pith_short_8","alias_value":"TO54FRNJ","created_at":"2026-07-05T11:32:40.851577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP","json":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP.json","graph_json":"https://pith.science/api/pith-number/TO54FRNJVM5FL5BZ6HT66BH7CP/graph.json","events_json":"https://pith.science/api/pith-number/TO54FRNJVM5FL5BZ6HT66BH7CP/events.json","paper":"https://pith.science/paper/TO54FRNJ"},"agent_actions":{"view_html":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP","download_json":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP.json","view_paper":"https://pith.science/paper/TO54FRNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04014&json=true","fetch_graph":"https://pith.science/api/pith-number/TO54FRNJVM5FL5BZ6HT66BH7CP/graph.json","fetch_events":"https://pith.science/api/pith-number/TO54FRNJVM5FL5BZ6HT66BH7CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP/action/storage_attestation","attest_author":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP/action/author_attestation","sign_citation":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP/action/citation_signature","submit_replication":"https://pith.science/pith/TO54FRNJVM5FL5BZ6HT66BH7CP/action/replication_record"}},"created_at":"2026-07-05T11:32:40.851577+00:00","updated_at":"2026-07-05T11:32:40.851577+00:00"}