{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPRSEBK67YHVNVGBSOKEBFKFAH","short_pith_number":"pith:CPRSEBK6","schema_version":"1.0","canonical_sha256":"13e322055efe0f56d4c1939440954501f8206fd3d3c1207dfbcd96f46b27a918","source":{"kind":"arxiv","id":"2402.03177","version":1},"attestation_state":"computed","paper":{"title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Ashraf, Deema Alnuhait, Gamil Ahmed, Gubran A. Q. Abdulrahman, Khalid Almubarak, Maged S. Al-shaibani, Mustafa Ghaleb, Qais Gawah, Saied Alshahrani, Yousef Ali, Zaid Alyafeai, Zead Saleh","submitted_at":"2024-02-05T16:44:17Z","abstract_excerpt":"Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, resulting in inherent biases toward Western culture. This bias significantly impacts the linguistic structures of non-English languages such as Arabic, which has a distinct grammar reflective of the diverse cultures across the Arab region. This paper addresses this limitation by introducing CIDAR: https://hf.co/datasets/arbml/CIDAR, the first open Arabic instru"},"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":"2402.03177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T16:44:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"069a1949de10f13b1d72b91592c3f757b17955e13d440dc27c4ed660ee5d0baa","abstract_canon_sha256":"81ad68278706bda72a0f959391a8da62d7e73d15584ad22a151e5d84ad6b7b89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:31.991480Z","signature_b64":"cGPxpY1pyThOIO0x8YbTFysKmrgDji/3Obs83iupa4Yt5qXzPN405w/vFP8KN+v3GUVI8It/YfHlPKSJX8/jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e322055efe0f56d4c1939440954501f8206fd3d3c1207dfbcd96f46b27a918","last_reissued_at":"2026-07-05T07:41:31.991061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:31.991061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Ashraf, Deema Alnuhait, Gamil Ahmed, Gubran A. Q. Abdulrahman, Khalid Almubarak, Maged S. Al-shaibani, Mustafa Ghaleb, Qais Gawah, Saied Alshahrani, Yousef Ali, Zaid Alyafeai, Zead Saleh","submitted_at":"2024-02-05T16:44:17Z","abstract_excerpt":"Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, resulting in inherent biases toward Western culture. This bias significantly impacts the linguistic structures of non-English languages such as Arabic, which has a distinct grammar reflective of the diverse cultures across the Arab region. This paper addresses this limitation by introducing CIDAR: https://hf.co/datasets/arbml/CIDAR, the first open Arabic instru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03177","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/2402.03177/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":"2402.03177","created_at":"2026-07-05T07:41:31.991124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03177v1","created_at":"2026-07-05T07:41:31.991124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03177","created_at":"2026-07-05T07:41:31.991124+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPRSEBK67YHV","created_at":"2026-07-05T07:41:31.991124+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPRSEBK67YHVNVGB","created_at":"2026-07-05T07:41:31.991124+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPRSEBK6","created_at":"2026-07-05T07:41:31.991124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":154,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH","json":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH.json","graph_json":"https://pith.science/api/pith-number/CPRSEBK67YHVNVGBSOKEBFKFAH/graph.json","events_json":"https://pith.science/api/pith-number/CPRSEBK67YHVNVGBSOKEBFKFAH/events.json","paper":"https://pith.science/paper/CPRSEBK6"},"agent_actions":{"view_html":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH","download_json":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH.json","view_paper":"https://pith.science/paper/CPRSEBK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03177&json=true","fetch_graph":"https://pith.science/api/pith-number/CPRSEBK67YHVNVGBSOKEBFKFAH/graph.json","fetch_events":"https://pith.science/api/pith-number/CPRSEBK67YHVNVGBSOKEBFKFAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH/action/storage_attestation","attest_author":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH/action/author_attestation","sign_citation":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH/action/citation_signature","submit_replication":"https://pith.science/pith/CPRSEBK67YHVNVGBSOKEBFKFAH/action/replication_record"}},"created_at":"2026-07-05T07:41:31.991124+00:00","updated_at":"2026-07-05T07:41:31.991124+00:00"}