{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V7U4UYU3LR6CGQDK5X4PMKVRUI","short_pith_number":"pith:V7U4UYU3","schema_version":"1.0","canonical_sha256":"afe9ca629b5c7c23406aedf8f62ab1a2295c4c42444111a5548633f76ea46a91","source":{"kind":"arxiv","id":"2506.01190","version":1},"attestation_state":"computed","paper":{"title":"Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Madhavendra Thakur","submitted_at":"2025-06-01T21:57:02Z","abstract_excerpt":"Large Language Models (LLMs) struggle with culturally-specific reasoning tasks, particularly in low-resource languages, hindering their global applicability. Addressing this gap is crucial for equitable AI deployment. We introduce Culturally-Grounded Chain-of-Thought (CG-CoT), a novel prompting strategy that combines dense vector retrieval of cultural context with explicit reasoning sequences. Our extensive experiments on Yoruba proverb interpretation demonstrate that CG-CoT provides significantly higher culturally-aligned accuracy and depth than traditional prompting methods, validated throug"},"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":"2506.01190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T21:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"7902c7a4a4efe7c074d68fdf000cecb658106b93fbe6bf57bbe5fd74f7d0f892","abstract_canon_sha256":"5b1c686e278d1d10365f5603dafef0a07a6ce49888d55a76b62e69573f3cede2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:47.892764Z","signature_b64":"Z4m78t7F22jccrNuuj0Rf3dNpolkXx+lTCm0crHSex9vDabG2CbbkkWDESvOLcoKTM7kHyVJUAt1w9LTw+YEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afe9ca629b5c7c23406aedf8f62ab1a2295c4c42444111a5548633f76ea46a91","last_reissued_at":"2026-07-05T11:13:47.892300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:47.892300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Madhavendra Thakur","submitted_at":"2025-06-01T21:57:02Z","abstract_excerpt":"Large Language Models (LLMs) struggle with culturally-specific reasoning tasks, particularly in low-resource languages, hindering their global applicability. Addressing this gap is crucial for equitable AI deployment. We introduce Culturally-Grounded Chain-of-Thought (CG-CoT), a novel prompting strategy that combines dense vector retrieval of cultural context with explicit reasoning sequences. Our extensive experiments on Yoruba proverb interpretation demonstrate that CG-CoT provides significantly higher culturally-aligned accuracy and depth than traditional prompting methods, validated throug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01190","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/2506.01190/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":"2506.01190","created_at":"2026-07-05T11:13:47.892380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01190v1","created_at":"2026-07-05T11:13:47.892380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01190","created_at":"2026-07-05T11:13:47.892380+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7U4UYU3LR6C","created_at":"2026-07-05T11:13:47.892380+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7U4UYU3LR6CGQDK","created_at":"2026-07-05T11:13:47.892380+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7U4UYU3","created_at":"2026-07-05T11:13:47.892380+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/V7U4UYU3LR6CGQDK5X4PMKVRUI","json":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI.json","graph_json":"https://pith.science/api/pith-number/V7U4UYU3LR6CGQDK5X4PMKVRUI/graph.json","events_json":"https://pith.science/api/pith-number/V7U4UYU3LR6CGQDK5X4PMKVRUI/events.json","paper":"https://pith.science/paper/V7U4UYU3"},"agent_actions":{"view_html":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI","download_json":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI.json","view_paper":"https://pith.science/paper/V7U4UYU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01190&json=true","fetch_graph":"https://pith.science/api/pith-number/V7U4UYU3LR6CGQDK5X4PMKVRUI/graph.json","fetch_events":"https://pith.science/api/pith-number/V7U4UYU3LR6CGQDK5X4PMKVRUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI/action/storage_attestation","attest_author":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI/action/author_attestation","sign_citation":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI/action/citation_signature","submit_replication":"https://pith.science/pith/V7U4UYU3LR6CGQDK5X4PMKVRUI/action/replication_record"}},"created_at":"2026-07-05T11:13:47.892380+00:00","updated_at":"2026-07-05T11:13:47.892380+00:00"}