{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LQAWFOGMKK7AYPVHCXYWIATI4R","short_pith_number":"pith:LQAWFOGM","schema_version":"1.0","canonical_sha256":"5c0162b8cc52be0c3ea715f1640268e4547952bbb685cd30ab993beb2c1424a0","source":{"kind":"arxiv","id":"2405.04655","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Honglak Lee, Lajanugen Logeswaran, Moontae Lee, Rada Mihalcea, Siqi Shen, Soujanya Poria","submitted_at":"2024-05-07T20:28:34Z","abstract_excerpt":"Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper, we conduct a comprehensive examination of the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks. Using several general and cultural commonsense benchmarks, we find that (1) LLMs have a significant discrepancy in performance when tested on culture-specific commonsense knowledge for different cultures; (2) LLMs' general co"},"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":"2405.04655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T20:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"0d3167aea99739f11abf8aa8f1d2067eb66bc983d62ea62bb106e17959c5224c","abstract_canon_sha256":"0ccfa8da03b0bc4c44e559dab28e017e7ca12358446785f617b7cdedee1dbdb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:52.088284Z","signature_b64":"RJXs9MUv5LyE35iQFqqVU0hV9OjhHsljLKTIJ6zRX5hzEY7uhYMkbWkGO8k7q9xd9Dd1XonCFHaEQZPuwCb4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c0162b8cc52be0c3ea715f1640268e4547952bbb685cd30ab993beb2c1424a0","last_reissued_at":"2026-07-05T08:16:52.087904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:52.087904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Honglak Lee, Lajanugen Logeswaran, Moontae Lee, Rada Mihalcea, Siqi Shen, Soujanya Poria","submitted_at":"2024-05-07T20:28:34Z","abstract_excerpt":"Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper, we conduct a comprehensive examination of the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks. Using several general and cultural commonsense benchmarks, we find that (1) LLMs have a significant discrepancy in performance when tested on culture-specific commonsense knowledge for different cultures; (2) LLMs' general co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04655","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/2405.04655/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":"2405.04655","created_at":"2026-07-05T08:16:52.087961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04655v1","created_at":"2026-07-05T08:16:52.087961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04655","created_at":"2026-07-05T08:16:52.087961+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQAWFOGMKK7A","created_at":"2026-07-05T08:16:52.087961+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQAWFOGMKK7AYPVH","created_at":"2026-07-05T08:16:52.087961+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQAWFOGM","created_at":"2026-07-05T08:16:52.087961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22645","citing_title":"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R","json":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R.json","graph_json":"https://pith.science/api/pith-number/LQAWFOGMKK7AYPVHCXYWIATI4R/graph.json","events_json":"https://pith.science/api/pith-number/LQAWFOGMKK7AYPVHCXYWIATI4R/events.json","paper":"https://pith.science/paper/LQAWFOGM"},"agent_actions":{"view_html":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R","download_json":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R.json","view_paper":"https://pith.science/paper/LQAWFOGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04655&json=true","fetch_graph":"https://pith.science/api/pith-number/LQAWFOGMKK7AYPVHCXYWIATI4R/graph.json","fetch_events":"https://pith.science/api/pith-number/LQAWFOGMKK7AYPVHCXYWIATI4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R/action/storage_attestation","attest_author":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R/action/author_attestation","sign_citation":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R/action/citation_signature","submit_replication":"https://pith.science/pith/LQAWFOGMKK7AYPVHCXYWIATI4R/action/replication_record"}},"created_at":"2026-07-05T08:16:52.087961+00:00","updated_at":"2026-07-05T08:16:52.087961+00:00"}